TILens Daily Edition 2026-09-02 Filters: github=hidden Stats: 1214 articles, 60 sources, 814 research papers Top topics: AI, AI Research, General ## News - Decoding the new AI lingo: Loops, harnesses, squads, hill climbing… oh my! Source: github-blog Topic: Open Source URL: https://github.blog/ai-and-ml/decoding-the-new-ai-lingo-loops-harnesses-squads-hill-climbing-oh-my/ - IntelliJ IDEA 2026.2.2 Is Out! Source: intellij-idea-blog Topic: Java URL: https://blog.jetbrains.com/idea/2026/09/intellij-idea-2026-2-2/ - Agentic security: Detection and response at machine speed Source: aws-security-blog Topic: DevSec (+AWS) URL: https://aws.amazon.com/blogs/security/agentic-security-detection-and-response-at-machine-speed/ - Kubernetes v1.37: Scale Workloads to Zero with HorizontalPodAutoscaler Source: kubernetes-blog Topic: DevOps URL: https://kubernetes.io/blog/2026/09/02/kubernetes-v1-37-hpa-scale-to-zero-beta/ - How we make AI coding more cost efficient without sacrificing task quality Source: github-blog Topic: Open Source URL: https://github.blog/ai-and-ml/github-copilot/how-we-make-ai-coding-more-cost-efficient-without-sacrificing-task-quality/ - Web Search on Amazon Bedrock is now available in AWS GovCloud (US-West) Source: aws-whats-new Topic: AWS (+AI) URL: https://aws.amazon.com/about-aws/whats-new/2026/09/amazon-bedrock-web-aws-govcloud/ - Fixing Top-Level Await in Safari Source: webkit-blog Topic: Web URL: https://webkit.org/blog/18227/fixing-top-level-await-in-safari/ - Amazon Connect Customer expands automated performance evaluations to Malay Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/09/amazon-connect-customer-automated-evaluations-malay/ - Amazon Quick adds new tool settings and Model Context Protocol (MCP) sync support for connectors Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/09/amazon-quick-adds-tool-settings-mcp-sync/ - Amazon Connect Customer announces general availability of agentic CX designer Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/09/agentic-cx-designer/ - Second-generation AWS Outposts racks now in the AWS GovCloud (US) Regions Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/09/aws-outposts-govcloud-us-regions/ - Introducing strands-dynamodb-storage: Durable agent storage for the Strands Agents SDK Source: aws-database-blog Topic: AWS (+PostgreSQL) URL: https://aws.amazon.com/blogs/database/introducing-strands-dynamodb-storage-durable-agent-storage-for-the-strands-agents-sdk/ - AWS CloudFormation now supports contract tests v2 for resource types Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/09/aws-cloudformation-contract-tests-v2-resource-types/ - AWS Config now supports 60 new resource types Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/09/aws-config-new-resource-types/ - Amazon MemoryDB now supports AWS PrivateLink in the AWS GovCloud (US) Regions Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/09/amazon-memorydb-privatelink/ - Real-Time Intelligence with IBM Time Series Models on Confluent Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/ibm-research/real-time-intelligence - AWS User Experience Customization (UXC) is now available in all commercial AWS Regions Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/08/aws-uxc-aws-regions - ATV Big Air Tour turned 3 days of work into 3 hours with ChatGPT Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/atv-big-air-tour - An Organizational Second Brain: Building an AI That Learns From Experts Source: meta-engineering Topic: Architecture URL: https://engineering.fb.com/2026/09/02/ml-applications/organizational-second-brain-ai-learns-from-experts/ - AWS Lambda now supports SnapStart for container image functions Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/07/aws-lambda-snapstart-container/ - Amazon SageMaker Unified Studio CI/CD adds notebook promotion and AI-assisted manifest generation Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/09/sagemaker-cicd-notebook-ai-manifest/ - Amazon RDS for SQL Server supports additional SQL trace flags Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/09/rds-sqlserver-supports-additional-trace-flags/ - 1.98.1 pre-release testing Source: inside-rust Topic: Rust URL: https://blog.rust-lang.org/inside-rust/2026/09/02/1.98.1-prerelease/ - The Builders Stage brings practical strategies for scaling startups to TechCrunch Disrupt 2026 Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/02/the-builders-stage-brings-practical-strategies-for-scaling-startups-to-techcrunch-disrupt-2026/ - Doubling Thermal Printer Resolution by Wiggling Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/02/doubling-thermal-printer-resolution-by-wiggling/ - Sora API dừng ngày 24/09/2026: checklist cần làm ngay Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/bean_bean/sora-api-dung-ngay-24092026-checklist-can-lam-ngay-57cc - Gemini 3.8 Flash giá $0.75/1M: dev có nên đổi model? Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/bean_bean/gemini-38-flash-gia-0751m-dev-co-nen-doi-model-42dm - Palo Alto Networks paid $500M for Thrive-backed Console, sources say Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/02/palo-alto-networks-paid-500m-for-thrive-backed-console-sources-say/ - Your CI is green and your pipeline produced nothing Source: devto-javascript Topic: JavaScript URL: https://dev.to/provedone/your-ci-is-green-and-your-pipeline-produced-nothing-213o - Zuck's Muse to Spark joy with open weights release 'soon' Source: theregister Topic: General URL: https://www.theregister.com/ai-and-ml/2026/09/02/zucks-muse-to-spark-joy-with-open-weights-release-soon/5294093 - TechCrunch Disrupt 2026’s new Real World AI Stage features Nvidia, robots, and extinct animals Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/02/techcrunch-disrupt-2026s-new-real-world-ai-stage-features-nvidia-robots-and-extinct-animals/ - How I Built In-Game Hot Reloading with an LLM Chat (Zero Build Steps, Pure ESM) Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/carlos/how-i-built-in-game-hot-reloading-with-an-llm-chat-zero-build-steps-pure-esm-2a2h - Making three years of a Telegram group chat queryable Source: devto-javascript Topic: JavaScript URL: https://dev.to/mikhkonkov/making-three-years-of-a-telegram-group-chat-queryable-54j2 - VMware swings its focus back to low-end server virt, promises vSphere Standard upgrade Source: theregister Topic: General URL: https://www.theregister.com/virtualization/2026/09/02/vmware-swings-its-focus-back-to-low-end-server-virt-promises-vsphere-standard-upgrade/5294083 - The Builder Design Pattern: A Better Approach to Complex Object Construction Source: freecodecamp Topic: General URL: https://www.freecodecamp.org/news/the-builder-design-pattern-a-better-approach-to-complex-object-construction/ - How Quantum Connectivity Shapes What Your Quantum Computer Can Actually Compute Source: freecodecamp Topic: General URL: https://www.freecodecamp.org/news/how-quantum-connectivity-shapes-what-your-quantum-computer-can-actually-compute/ - Google spared from ad-business breakup, but judge orders changes to how it operates Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/02/google-spared-from-ad-business-breakup-but-judge-orders-changes-to-how-it-operates/ - 12 Open Source Gems To Become The Ultimate Developer 🔥 Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/anthonymax/12-open-source-gems-to-become-the-ultimate-developer-671 - Freeze the Repo Seam Before You Cut a Single File Source: devto-javascript Topic: JavaScript URL: https://dev.to/hackrs_6393/freeze-the-repo-seam-before-you-cut-a-single-file-5df7 - Claude Mythos only model to complete full cyber kill chain, experts say Source: theregister Topic: General URL: https://www.theregister.com/security/2026/09/02/claude-mythos-only-model-to-complete-full-cyber-kill-chain-experts-say/5294071 - Spending deal comes with a bonus: Blocking political control of grants Source: ars-technica Topic: General URL: https://arstechnica.com/science/2026/09/budget-deal-puts-political-control-of-grants-on-hold-until-december/ - AI's Vulnerability Surge May Be More Manageable Than First Feared Source: darkreading Topic: DevSec URL: https://www.darkreading.com/application-security/ai-vulnerability-surge-manageable-than-first-feared - TypeScript Tips: Unlocking the Jedi Mind Trick for Safer Code Source: devto-javascript Topic: JavaScript URL: https://dev.to/timevolt/typescript-tips-unlocking-the-jedi-mind-trick-for-safer-code-3gmh - I wanted comments on my static site without another SaaS, so I built StaticLayer Source: devto-javascript Topic: JavaScript URL: https://dev.to/abla25/i-wanted-comments-on-my-static-site-without-another-saas-so-i-built-staticlayer-530d - SonicWall SMA 1000 Zero-Days Enable Unauthenticated RCE Source: darkreading Topic: DevSec URL: https://www.darkreading.com/vulnerabilities-threats/sonicwall-sma-1000-zero-days-unauthenticated-rce - Accessible and Functional Quantity Spinbutton Pattern Source: devto-javascript Topic: JavaScript URL: https://dev.to/micaavigliano/accessible-and-functional-quantity-spinbutton-pattern-1945 - Microsoft devs rejoice: Union types coming to C# in November Source: theregister Topic: General URL: https://www.theregister.com/devops/2026/09/02/microsoft-devs-rejoice-union-types-coming-to-c-in-november/5294056 - AI-assisted mushroom hunting is a recipe for a bad trip Source: theregister Topic: General URL: https://www.theregister.com/offbeat/2026/09/02/ai-assisted-mushroom-hunting-is-a-recipe-for-a-bad-trip/5294060 - React Email Checks Need Decision States Source: devto-javascript Topic: JavaScript (+React) URL: https://dev.to/ryanlee91/react-email-checks-need-decision-states-394e - OpenAI’s new reasoning technique alarms AI safety experts Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/02/openais-new-reasoning-technique-alarms-ai-safety-experts/ - Fine, I’ll build my own text editor Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/02/fine-ill-build-my-own-text-editor/ - Multiverse says its 438B model is fast enough for AI agents. The benchmarks tell a more complicated story. Source: newstack Topic: DevOps URL: https://thenewstack.io/quasar-438b-agent-compression/ - Your next OpenAI API timeout might not be a timeout at all Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/astra-api-safety-stops/ - Anthropic’s Claude failures have made agent observability a security priority Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/anthropic-claude-agent-security/ - MapQuest is now the No. 1 US app after bucking Trump’s ‘Lake America’ renaming Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/02/mapquest-is-now-the-no-1-u-s-app-after-bucking-trumps-lake-america-renaming/ - The WT | Wearable Tech Conference is Happening this Month Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/02/the-wt-wearable-tech-conference-is-happening-this-month/ - 3D PCB previews are a delight Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/02/3d-pcb-previews-are-a-delight/ - Query Every Token on the XRP Ledger With One Endpoint Source: devto-javascript Topic: JavaScript URL: https://dev.to/nyxagi/query-every-token-on-the-xrp-ledger-with-one-endpoint-49bl - Harvesting Namib Desert Fog with High Voltage Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/02/harvesting-namib-desert-fog-with-high-voltage/ - With Gemini 3.8 Flash, Google reminds everyone it's still in the race Source: theregister Topic: General (+AI) URL: https://www.theregister.com/ai-and-ml/2026/09/02/with-gemini-38-flash-google-reminds-everyone-its-still-in-the-race/5294049 - FCC plans robocall scorecard to grade phone companies on spam call blocking Source: ars-technica Topic: General URL: https://arstechnica.com/tech-policy/2026/09/fcc-plans-robocall-scorecard-to-grade-phone-companies-on-spam-call-blocking/ - A GeoJSON map viewer Source: adafruit-blog Topic: Hardware (+AI) URL: https://blog.adafruit.com/2026/09/02/a-geojson-map-viewer/ - AI Gives Cybercriminals a Dangerous Time Advantage Source: darkreading Topic: DevSec URL: https://www.darkreading.com/threat-intelligence/ai-gives-cybercriminals-dangerous-time-advantage - Wary of Artemis IV timeline, NASA is changing lunar spacesuit design Source: ars-technica Topic: General URL: https://arstechnica.com/space/2026/09/wary-of-artemis-iv-timeline-nasa-is-changing-lunar-spacesuit-design/ - It sure looks like hackers breached a major ID card verification service Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/02/it-sure-looks-like-hackers-breached-a-major-id-card-verification-service/ - Sounds of the 1980s: NES Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/02/sounds-of-the-1980s-nes/ - Delivery Hero board backs Uber’s $15B takeover bid Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/02/delivery-hero-board-backs-ubers-15b-takeover-bid/ - How Gold Plastic Syndrome is killing toys and game consoles Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/02/how-gold-plastic-syndrome-is-killing-toys-and-game-consoles/ - A Safari extension that hides YouTube AI-labeled videos Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/02/a-safari-extension-that-hides-youtube-ai-labeled-videos/ - Creating green clothing with living fungi Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/02/creating-green-clothing-with-living-fungi/ - Three registers, three alphabets, no APIs: building pay-per-event actors for company data Source: devto-javascript Topic: JavaScript URL: https://dev.to/apify/three-registers-three-alphabets-no-apis-building-pay-per-event-actors-for-company-data-1b0m - FLOSS Weekly Episode 880: The Two Wolves Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/02/floss-weekly-episode-880-the-two-wolves/ - JavaScript Functions & Its Hoisting Rules Source: devto-javascript Topic: JavaScript URL: https://dev.to/abishek_m_82/js-functions-its-hoisting-rules-58ho - AI agents carried out every step of this ransomware attack – then left the victim an 80-page security audit Source: theregister Topic: General URL: https://www.theregister.com/security/2026/09/02/ai-agents-carried-out-every-step-of-this-ransomware-attack-then-left-the-victim-an-80-page-security-audit/5294009 - JP’s Product Pick of the Week 9/1/26 @adafruit @johnedgarpark #adafruit #newproductpick Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/02/jps-product-pick-of-the-week-9-1-26-adafruit-johnedgarpark-adafruit-newproductpick/ - Google releases Gemini 3.8 Flash, its third Flash model in six weeks Source: ars-technica Topic: General (+AI) URL: https://arstechnica.com/ai/2026/09/google-releases-gemini-3-8-flash-its-third-flash-model-in-six-weeks/ - Apple tells Mac App Store developers they can now drop Intel support Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/02/apple-tells-mac-app-store-developers-they-can-now-drop-intel-support/ - The Matrix of Python List Comprehensions: When to Use Generators Source: devto-javascript Topic: JavaScript URL: https://dev.to/timevolt/the-matrix-of-python-list-comprehensions-when-to-use-generators-1jm0 - UPDATED GUIDE: Adafruit Sparkle Motion Mini #AdafruitLearningSystem #WipperSnapper @Adafruit Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/02/updated-guide-adafruit-sparkle-motion-mini-adafruitlearningsystem-wippersnapper-adafruit/ - Five more brands onto one framework, a board that knows when QA passed, and a stream panel that talks to OBS Source: devto-javascript Topic: JavaScript URL: https://dev.to/ianwieds/five-more-brands-onto-one-framework-a-board-that-knows-when-qa-passed-and-a-stream-panel-that-3bcc - Trump may be forced to reveal secret rules feds use for AI safety testing Source: ars-technica Topic: General URL: https://arstechnica.com/tech-policy/2026/09/trump-may-be-forced-to-reveal-secret-rules-feds-use-for-ai-safety-testing/ - Infosec pros say we're not ready to lose control of AI Source: theregister Topic: General URL: https://www.theregister.com/ai-and-ml/2026/09/02/infosec-pros-say-were-not-ready-to-lose-control-of-ai/5294001 - How We Built NovaTik: A Modern TikTok Downloader for the Web Source: devto-javascript Topic: JavaScript URL: https://dev.to/mohamed_aitlahsen_b8689e/how-we-built-novatik-a-modern-tiktok-downloader-for-the-web-5hla - Your OG tags look fine in the browser and still break on Twitter — here's the part I got wrong Source: devto-javascript Topic: JavaScript URL: https://dev.to/ktg0215/your-og-tags-look-fine-in-the-browser-and-still-break-on-twitter-heres-the-part-i-got-wrong-3m31 - Copy-Paste Fonts Are Not Fonts. Here Is What Broke My Code Source: devto-javascript Topic: JavaScript URL: https://dev.to/iris_khan_dev/copy-paste-fonts-are-not-fonts-here-is-what-broke-my-code-4kc9 - Top 32 Sites to Buy Verified OnlyFans Accounts/www.progmb.com/ Source: devto-javascript Topic: JavaScript URL: https://dev.to/uluerock/top-32-sites-to-buy-verified-onlyfans-accountswwwprogmbcom-3a6f - TIME Trailblazers: Designing and Making the Future Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/02/time-trailblazers-designing-and-making-the-future/ - Functions in JavaScript Source: devto-javascript Topic: JavaScript URL: https://dev.to/ragul_kannadasan/functions-in-javascript-39hj - Pangram’s Max Spero on why AI detection is harder than ‘Real or Fake’ Source: techcrunch Topic: General URL: https://techcrunch.com/video/pangrams-max-spero-on-why-ai-detection-is-harder-than-real-or-fake/ - [$] Securely suspending LUKS-encrypted disks Source: lwn Topic: Open Source URL: https://lwn.net/Articles/1090568/ - X shifts US creator payouts from Stripe to X Money Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/02/x-shifts-us-creator-payouts-from-stripe-to-x-money/ - Expo / React Native for a Food Delivery Marketplace Source: devto-javascript Topic: JavaScript URL: https://dev.to/goodfoodpro/expo-react-native-for-a-food-delivery-marketplace-2e83 - US government sides with OpenAI on issue of training LLMs on copyrighted material Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/02/u-s-government-sides-with-openai-on-issue-of-training-llms-on-copyrighted-material/ - Fixing the Invisible Camera Preview in Capacitor Barcode Scanners Source: devto-javascript Topic: JavaScript URL: https://dev.to/capawesome/fixing-the-invisible-camera-preview-in-capacitor-barcode-scanners-4dd7 - AI APIs & Productivity: Build Smarter Apps Today Source: devto-javascript Topic: JavaScript URL: https://dev.to/zyctraai/ai-apis-productivity-build-smarter-apps-today-31c0 - Google ships its third Gemini Flash model in six weeks Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/google-ships-its-third-gemini-flash-model-in-six-weeks/ - Enhanced geothermal notches another win as Google buys 400 MW from Fervo Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/02/enhanced-geothermal-notches-another-win-as-google-buys-400-mw-from-fervo/ - Threat Gang 'Springs' Vishing Attacks on Microsoft Teams Users Source: darkreading Topic: DevSec URL: https://www.darkreading.com/cyberattacks-data-breaches/threat-gang-springs-vishing-attacks-microsoft-teams-users - US court rules Google will not have to sell ad exchange after losing antitrust case Source: ars-technica Topic: General URL: https://arstechnica.com/gadgets/2026/09/us-court-rules-google-will-not-have-to-sell-ad-exchange-after-losing-antitrust-case/ - How to change Raspberry Pi WiFi details from the SD card Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/02/how-to-change-raspberry-pi-wifi-details-from-the-sd-card/ - I vibecoded Morrowind, Duke Nukem, and Serious Sam onto an iPhone Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/02/664081/ - SonicWall's SMA1000 boxes under active attack again Source: theregister Topic: General URL: https://www.theregister.com/security/2026/09/02/sonicwalls-sma1000-boxes-under-active-attack-again/5293969 - Wonderful more than doubles its valuation to $5B in under 6 months Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/02/wonderful-more-than-doubles-its-valuation-to-5b-in-under-6-months/ - 😺 Claude Fable 5.1 can do the work. The hard part is managing it. Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/claude-fable-5-1-live-test/ - India’s richest man now wants to turn aging computers into AI-ready PCs Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/02/indias-richest-man-now-wants-to-turn-aging-computers-into-ai-ready-pcs/ - Smart Phone Mittens #AdafruitLearnSystem Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/02/smart-phone-mittens-adafruitlearnsystem/ - GPIBee (UsbGpib V3) USB-to-GPIB adapter gains PoE Ethernet Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/02/gpibee-usbgpib-v3-usb-to-gpib-adapter-gains-poe-ethernet/ - Where will RISC-V be in 20 Years? Poll results Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/02/where-will-risc-v-be-in-20-years-poll-results/ - The CALM Theorem: When Distributed Consistency Doesn’t Need Coordination Source: java-code-geeks Topic: Java URL: https://www.javacodegeeks.com/2026/09/the-calm-theorem-when-distributed-consistency-doesnt-need-coordination.html - Atari Lynx: the first color handheld game console Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/02/atari-lynx-the-first-color-handheld-game-console/ - Why Your RAG System Is Only as Good as Its Translator Model Source: bytebytego Topic: Architecture (+AI) URL: https://blog.bytebytego.com/p/how-to-shrink-a-language-model-without - Microsoft will stop finishing your sentences in Word and Outlook Source: theregister Topic: General URL: https://www.theregister.com/ai-and-ml/2026/09/02/microsoft-will-stop-finishing-your-sentences-in-word-and-outlook/5293860 - How a 1981 RAM Expansion Worked Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/02/how-a-1981-ram-expansion-worked/ - Vercel built a feedback loop that treats agent instructions like software Source: newstack Topic: DevOps URL: https://thenewstack.io/vercel-agent-design-guidance/ - HDMI For the Tandy/Radio Shack Color Computer 2 Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/02/hdmi-for-the-tandy-radio-shack-color-computer-2/ - [$] Governing GNOMEs: how the project's technical decision-making is evolving Source: lwn Topic: Open Source URL: https://lwn.net/Articles/1091619/ - Incus 7.4 released Source: lwn Topic: Open Source URL: https://lwn.net/Articles/1092229/ - HiddenLayer nabs $100M as enterprises rush to secure their AI deployments Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/02/hiddenlayer-nabs-100m-as-enterprises-rush-to-secure-their-ai-deployments/ - LIVE! 3D Hangouts with Noe and Liz Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/02/live-3d-hangouts-with-noe-and-liz-2/ - Your organization prioritized AI adoption, but you actually need AI fluency. Source: newstack Topic: DevOps URL: https://thenewstack.io/ai-fluency-operating-model/ - NASA's Swift shortens orbital lifetime for the sake of science Source: theregister Topic: General URL: https://www.theregister.com/science/2026/09/02/nasas-swift-shortens-orbital-lifetime-for-the-sake-of-science/5293911 - Input-Remapper Key Macros Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/02/input-remapper-key-macros/ - PSA: Amazon’s shopping AI can now tell you if that message is a scam Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/02/psa-amazons-shopping-ai-can-now-tell-you-if-that-message-is-a-scam/ - Firefox and Thunderbird hit the fortnightly release treadmill Source: theregister Topic: General URL: https://www.theregister.com/software/2026/09/02/firefox-and-thunderbird-hit-the-fortnightly-release-treadmill/5293953 - FBI investigates as hackers sell digital scans of 153M drivers licenses Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/02/fbi-investigates-as-hackers-sell-digital-scans-of-153m-drivers-licenses/ - Toyohiro Akiyama, first Japanese citizen and journalist in space, dies at 84 Source: ars-technica Topic: General URL: https://arstechnica.com/space/2026/09/toyohiro-akiyama-first-japanese-citizen-and-journalist-in-space-dies-at-84/ - Anthropic makes changes to stop AI agents running amok, again Source: adafruit-blog Topic: Hardware (+AI) URL: https://blog.adafruit.com/2026/09/02/anthropic-makes-changes-to-stop-ai-agents-running-amok-again/ - The curiosity that is Minecraft: Pi Edition Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/02/the-curiosity-that-is-minecraft-pi-edition/ - Legacy Lenovo login opens 5,000 Dropbox accounts to attackers Source: theregister Topic: General URL: https://www.theregister.com/security/2026/09/02/legacy-lenovo-login-opens-5000-dropbox-accounts-to-attackers/5293924 - Adobe acquires Indian market intelligence startup Rilo Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/02/adobe-acquires-indian-market-intelligence-startup-rilo/ - 3D Print a Minecraft Jukebox Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/02/3d-print-a-minecraft-jukebox/ - “I’m Not Dead Yet!” Reverse Polish Notation Calculators You Can Still Buy Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/02/im-not-dead-yet-reverse-polish-notation-calculators-you-can-still-buy/ - Facilitating AI integration with simplicity at scale Source: mit-ai Topic: AI URL: https://www.technologyreview.com/2026/09/02/1142879/facilitating-ai-integration-with-simplicity-at-scale/ - Python 3.15 Preview: UTF-8 by Default Source: real-python Topic: Python URL: https://realpython.com/python315-utf8-default/ - A Windows 98 disk defrag simulator in your browser Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/02/a-windows-98-disk-defrag-simulator-in-your-browser/ - Swiggy Uses 350+ Features and Multi-Task MLP to Predict Customer Lifetime Value Source: infoq-architecture Topic: Architecture URL: https://www.infoq.com/news/2026/09/swiggy-pltv-multitask-mlp/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Architecture+%26+Design - Offshoots of cancelled TrueNAS Core upgrade to FreeBSD 15 Source: theregister Topic: General URL: https://www.theregister.com/storage/2026/09/02/offshoots-of-cancelled-truenas-core-upgrade-to-freebsd-15/5293725 - The Python on Microcontrollers Newsletter: subscribe for free Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/02/the-python-on-microcontrollers-newsletter-subscribe-for-free-9-2/ - Best AI Presentation Makers for Business in 2026 Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/guides/best-ai-presentation-makers/ - Eight stable kernels for Wednesday Source: lwn Topic: Open Source URL: https://lwn.net/Articles/1092151/ - Security updates for Wednesday Source: lwn Topic: Open Source (+AI) URL: https://lwn.net/Articles/1092149/ - Anthropic hires architect of UK AI policy as MPs warn of 'clear conflict of interest' Source: theregister Topic: General (+AI) URL: https://www.theregister.com/public-sector/2026/09/02/anthropic-hires-architect-of-uk-ai-policy-as-mps-warn-of-clear-conflict-of-interest/5293903 - Norway considers ban on camera-enabled wearable ‘pervert glasses’ Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/02/norway-considers-ban-on-camera-enabled-wearable-pervert-glasses/ - Adobe is making its tools available in Slack Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/02/adobe-is-making-its-tools-available-in-slack/ - The Army just used a 20-kilowatt laser to take out three drones Source: ars-technica Topic: General URL: https://arstechnica.com/gadgets/2026/09/the-army-just-used-a-20-kilowatt-laser-to-take-out-three-drones/ - Next-gen AI networks may hinge on the telephone switchboard's return Source: theregister Topic: General URL: https://www.theregister.com/networks/2026/09/02/nvidia-joins-investment-into-ipronics-to-build-out-optical-circuit-switching-ocs-tech/5293764 - Turn Moodle Pages into NotebookLM Markdown with a Local Chrome Extension Source: devto-javascript Topic: JavaScript URL: https://dev.to/paladini/turn-moodle-pages-into-notebooklm-markdown-with-a-local-chrome-extension-5e8k - The Engineering Lead's Guide to Hiring React Native Developers in 2026 Source: devto-javascript Topic: JavaScript URL: https://dev.to/saawahi/the-engineering-leads-guide-to-hiring-react-native-developers-in-2026-gag - Building a Barcode Generator That Actually Works — The bwip-js EAN-13 Deep Dive Source: devto-javascript Topic: JavaScript URL: https://dev.to/toolzip_7e9a28bbade/building-a-barcode-generator-that-actually-works-the-bwip-js-ean-13-deep-dive-10j4 - How to Use a JSON-LD Structured Data Generator Free (Step by Step) Source: devto-javascript Topic: JavaScript URL: https://dev.to/tavigogogo/how-to-use-a-json-ld-structured-data-generator-free-step-by-step-58e3 - Microsoft update disarms Outlook and Teams on Arm PCs Source: theregister Topic: General URL: https://www.theregister.com/os-platforms/2026/09/02/microsoft-update-disarms-outlook-and-teams-on-arm-pcs/5293849 - FirebaseError: Expected first argument to collection() — Fix Source: devto-javascript Topic: JavaScript URL: https://dev.to/mahdi_benrhouma_fe1c6005/firebaseerror-expected-first-argument-to-collection-fix-3lli - The Accessibility Features Players Actually Use First Source: devto-javascript Topic: JavaScript URL: https://dev.to/paulcrinigan/the-accessibility-features-players-actually-use-first-46hn - OpenAI Details GPT-Live’s Architecture for Continuous Stateful Voice Interaction Source: infoq-architecture Topic: Architecture (+AI) URL: https://www.infoq.com/news/2026/09/openai-gpt-live/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Architecture+%26+Design - Uber is laying off 10% of staff, or 3,300 people Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/02/uber-is-laying-off-10-of-staff-or-3300-people/ - JS Barcode Universal SDK: Read & Write 1D and 2D Barcodes Source: devto-javascript Topic: JavaScript URL: https://dev.to/sythos/js-barcode-universal-sdk-read-write-1d-and-2d-barcodes-28dm - OpenAI faces 30 more lawsuits tied to Tumbler Ridge shooting Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/02/openai-faces-30-more-lawsuits-tied-to-tumbler-ridge-shooting/ - RustConf 2026 Source: ardan-labs Topic: Go (+Rust) URL: https://www.ardanlabs.com/community-gallery/rust-conf-26/ - Quiz: Python Project Structure: How to Choose the Right Layout Source: real-python Topic: Python URL: https://realpython.com/quizzes/python-application-layouts/ - Quiz: Python 3.15 Preview: UTF-8 by Default Source: real-python Topic: Python URL: https://realpython.com/quizzes/python315-utf8-default/ - A cloud engineer walked into a bar and – no joke – ended up having to migrate a datacenter Source: theregister Topic: General URL: https://www.theregister.com/virtualization/2026/09/02/a-cloud-engineer-walked-into-a-bar-and-no-joke-ended-up-having-to-migrate-a-datacenter/5293835 - React Native Architecture (Old vs New/Fabric) Source: devto-javascript Topic: JavaScript URL: https://dev.to/godofgeeks/react-native-architecture-old-vs-newfabric-4n3g - Before I Call GPT Image 2, I Validate These 7 Things Source: devto-javascript Topic: JavaScript URL: https://dev.to/_86f41ebeb2cab43917bd42/before-i-call-gpt-image-2-i-validate-these-7-things-3f6h - How I Built a Desktop Movie Streamer with Electron and WebTorrent Source: devto-javascript Topic: JavaScript URL: https://dev.to/qazi_absaar_404e7c8bb9076/how-i-built-a-desktop-movie-streamer-with-electron-and-webtorrent-ag4 - London Tube closes the 5G gap with streets above Source: theregister Topic: General URL: https://www.theregister.com/networks/2026/09/02/london-tube-closes-the-5g-gap-with-streets-above/5293878 - Is Russia's rival to Starlink failing? Here's what we know. Source: ars-technica Topic: General URL: https://arstechnica.com/space/2026/09/rassvet-russias-rival-to-starlink-is-getting-off-to-a-slow-start/ - BGP hijack infecting networks caused by a comedy of errors that’s not funny at all Source: ars-technica Topic: General URL: https://arstechnica.com/security/2026/09/well-executed-bgp-attack-uses-hijacked-ips-to-infect-real-networks/ - HDMI For the Color Computer 2 Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/02/hdmi-for-the-color-computer-2/ - Presentation: Beyond Prompting: Context Engineering for Production-Grade AI Source: infoq-java Topic: Java (+AI) URL: https://www.infoq.com/presentations/context-engineering-redis-llm-architecture/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Java - Shadow DOM Needed JavaScript to Exist. Now It Doesn't. Source: devto-javascript Topic: JavaScript URL: https://dev.to/parsajiravand/shadow-dom-needed-javascript-to-exist-now-it-doesnt-2lla - LightMake L4 3D printer features four independent heads for simultaneous or multi-color printing (Crowdfunding) Source: cnx-software Topic: Hardware URL: https://www.cnx-software.com/2026/09/02/lightmake-l4-3d-printer-features-four-independent-printing-heads/ - UK goes shopping for homegrown AI with £100M procurement scheme Source: theregister Topic: General URL: https://www.theregister.com/ai-and-ml/2026/09/02/uk-goes-shopping-for-homegrown-ai-with-100m-procurement-scheme/5293680 - The Most In-Demand Tech Skills for Developers in 2026 Source: devto-javascript Topic: JavaScript URL: https://dev.to/saliha_chudhary_52def3ed7/the-most-in-demand-tech-skills-for-developers-in-2026-1el1 - Northern Ireland adds £15M to Fujitsu education deal without competition Source: theregister Topic: General URL: https://www.theregister.com/public-sector/2026/09/02/northern-ireland-adds-15m-to-fujitsu-education-deal-without-competition/5293648 - GPIBee (UsbGpib V3) USB-to-GPIB adapter gains Ethernet (PoE), but launches as closed-source hardware Source: cnx-software Topic: Hardware URL: https://www.cnx-software.com/2026/09/02/gpibee-usbgpib-v3-usb-to-gpib-adapter-gains-ethernet-poe-but-launches-as-closed-source-hardware/ - MongoDB Search Server, improved! Source: foojay-today Topic: Java (+MongoDB) URL: https://foojay.io/today/mongodb-search-server-improved/ - Fable 5.1 kicks off launch week at the frontier Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/fable-5-1-kicks-off-launch-week-at-the-frontier - UK cyber bill targets AI users, not the vendors building it Source: theregister Topic: General URL: https://www.theregister.com/security/2026/09/02/uk-cyber-bill-targets-ai-users-not-the-vendors-building-it/5293738 - 😺Anthropic launched Fable 5.1: and now, the agents cost less Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/anthropic-launched-fable-5-1-and-now-the-agents-cost-less/ - Cloudflare Adds Optional OAuth Scopes, Letting Developers Mark What Users May Decline Source: infoq-architecture Topic: Architecture URL: https://www.infoq.com/news/2026/09/cloudflare-optional-oauth-scopes/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Architecture+%26+Design - UK digital ID may be dead, but its legacy IT problem lives on Source: theregister Topic: General URL: https://www.theregister.com/public-sector/2026/09/02/uk-digital-id-may-be-dead-but-its-legacy-it-problem-lives-on/5293677 - Creating the Greenest Possible Clothing with Living Fungi Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/02/creating-the-greenest-possible-clothing-with-living-fungi/ - Circuit Valley CHC5 – A modular USB, HDMI, and Ethernet camera system (Crowdfunding) Source: cnx-software Topic: Hardware URL: https://www.cnx-software.com/2026/09/02/circuit-valley-chc5-a-modular-usb-hdmi-and-ethernet-camera-system/ - The cost of simplicity Source: devto-javascript Topic: JavaScript URL: https://dev.to/cartmann68/the-cost-of-simplicity-1o42 - 10 Best Platforms to Buy Aged Telegram Accounts in Any ... Source: devto-javascript Topic: JavaScript URL: https://dev.to/abbiepiper9u3di/10-best-platforms-to-buy-aged-telegram-accounts-in-any--18l6 - Why I Stopped Using Canva for Bingo Cards Source: devto-javascript Topic: JavaScript URL: https://dev.to/jack_green_7b74cb2cdf9e23/why-i-stopped-using-canva-for-bingo-cards-139d - Arm in the enterprise is at least three years away, says Broadcom software boss Source: theregister Topic: General URL: https://www.theregister.com/virtualization/2026/09/02/arm-in-the-enterprise-is-at-least-three-years-away-says-broadcom-software-boss/5293804 - How My AI-Powered Site Generates Leo's Daily Horoscope Automatically Source: devto-javascript Topic: JavaScript URL: https://dev.to/zongkai_sun_0946ae0d49db2/how-my-ai-powered-site-generates-leos-daily-horoscope-automatically-4km6 - Temporal in Production: Field Notes on Replacing JavaScript Date, the Same-Day Bug, and What Doesn't Cross the RSC Boundary Source: devto-javascript Topic: JavaScript URL: https://dev.to/ahmed_mahmoud360/temporal-in-production-field-notes-on-replacing-javascript-date-the-same-day-bug-and-what-20cl - The 18 Pages I Missed: How Template Drift Broke My Widget on 70 Pages Source: devto-javascript Topic: JavaScript URL: https://dev.to/its_me_jai/the-18-pages-i-missed-how-template-drift-broke-my-widget-on-70-pages-23c7 - I added WebMCP to a live Stripe checkout in ~40 lines Source: devto-javascript Topic: JavaScript URL: https://dev.to/flovoice53tech/i-added-webmcp-to-a-live-stripe-checkout-in-40-lines-4ekk - JavaScript Functions: A Simple Explanation Source: devto-javascript Topic: JavaScript URL: https://dev.to/candyx3/javascript-functions-a-simple-explanation-3ih2 - WebSocket Engineering — Part 2 Source: devto-javascript Topic: JavaScript URL: https://dev.to/surajrkhonde/websocket-engineering-part-2-20b5 - Array and their methods in javascript Source: devto-javascript Topic: JavaScript URL: https://dev.to/antony_stark_a79381705a5a/array-and-their-methods-in-javascript-3fo0 - Swift’s Ownership And Noncopyable Types Source: java-code-geeks Topic: Java URL: https://www.javacodegeeks.com/2026/09/swifts-ownership-and-noncopyable-types.html - A Defrag Simulator In Your Browser Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/01/a-defrag-simulator-in-your-browser/ - Only 11.8% of insider trades are actual purchases: lessons from polling SEC EDGAR Source: devto-javascript Topic: JavaScript URL: https://dev.to/jaredmansu/only-118-of-insider-trades-are-actual-purchases-lessons-from-polling-sec-edgar-4ki6 - Drain In-Flight HTTP Before Kubernetes Sends SIGKILL Source: devto-javascript Topic: JavaScript URL: https://dev.to/karuha/drain-in-flight-http-before-kubernetes-sends-sigkill-a2g - Software That Must Not Be Wrong: Property Tests for a Pediatric Dosing Calculator Source: this-week-in-rust Topic: Rust URL: https://rust-blog.github.io/post/favi-child-property-tests - The 'rnull' Rust block driver Source: this-week-in-rust Topic: Rust URL: https://lwn.net/SubscriberLink/1090378/b33a6fe3f4033507/ - Rust concurrency vs Go concurrency: stackless vs stackfull coroutines Source: this-week-in-rust Topic: Rust URL: https://kerkour.com/rust-vs-go-concurrency - Functional State Machines in Rust: Typestate and Newtype Patterns Source: this-week-in-rust Topic: Rust URL: https://dl.acm.org/doi/10.1145/3830438.3830958 - Could Cargo's scheduler be better? Source: this-week-in-rust Topic: Rust URL: https://spirali.github.io/blog/cargo-scheduler/ - Nine Rules for Compile-Time Work with Rust const fn: Parse files, build tables, and catch mistakes … without a build script (Part 1) Source: this-week-in-rust Topic: Rust URL: https://medium.com/@carlmkadie/nine-rules-for-compile-time-work-with-rust-const-fn-part-1-a29f7dd62b2f - Welcome to the machine: emulating a CPU Source: this-week-in-rust Topic: Rust URL: https://bitfieldconsulting.com/posts/welcome-to-machine - An Agentic VM in Rust — by Cristian Sánchez Source: this-week-in-rust Topic: Rust URL: https://www.youtube.com/watch?v=d7jQXm1KcOA - Wasmi 2.0 - Engineering of the Fastest Wasm Interpreters Source: this-week-in-rust Topic: Rust URL: https://wasmi-labs.github.io/blog/posts/wasmi-v2.0/ - How we developed the world's first safety-certified product written in Rust – and why we went bare metal Source: this-week-in-rust Topic: Rust URL: https://www.sonair.com/journal/how-we-safety-certified-the-worlds-first-rust-implementation - Proving my Rust NVR doesn't leak memory (it did) Source: this-week-in-rust Topic: Rust URL: https://murlet.com/blog/hunting-rust-memory-leaks/ - How we saved 100 terabytes of memory by optimizing 1.1.1.1’s DNS cache Source: this-week-in-rust Topic: Rust URL: https://blog.cloudflare.com/dns-cache-memory-optimization-1111/ - Your First GPUI App - Building a Desktop UI in Rust Source: this-week-in-rust Topic: Rust URL: https://blog.sheerluck.dev/posts/your-first-gpui-app-building-a-desktop-ui-in-rust/ - The Embedded Rustacean Issue #79 Source: this-week-in-rust Topic: Rust URL: https://www.theembeddedrustacean.com/p/the-embedded-rustacean-issue-79 - Drawing Shapes with GPUI's Canvas Source: this-week-in-rust Topic: Rust URL: https://hlcfan.github.io/gpui-canvas-shapes.html - Making Progress on AsyncIterator — by Jack O'Connor Source: this-week-in-rust Topic: Rust URL: https://www.youtube.com/watch?v=zQAia_u8WPM - Claude Fable 5.1 LIVE: Testing Anthropic’s New AI Agent Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/claude-fable-5-1-can-do-the-work-the-hard-part-is-managing-it/ - Haiku OS Releases Beta 6 Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/01/haiku-os-releases-beta-6/ - Everything That Happened in AI Today (Tuesday, September 1, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-today-tuesday-september-1-2026/ - Tape still isn’t dead, but shipments slipped by 16 exabytes in 2025 Source: theregister Topic: General URL: https://www.theregister.com/storage/2026/09/02/tape-still-isnt-dead-but-shipments-slipped-by-16-exabytes-in-2025/5293813 - Old, Unpatched Flaws Give Attackers Access to Philippines Nuclear Agency Source: darkreading Topic: DevSec URL: https://www.darkreading.com/cyberattacks-data-breaches/old-unpatched-flaws-attackers-philippines-nuclear-agency - Debugging Async/Await Deadlocks in JavaScript: Proven Strategies to Fix Stalled Promises Source: devto-javascript Topic: JavaScript URL: https://dev.to/deep_fix_71a17f6aa38ff28a/debugging-asyncawait-deadlocks-in-javascript-proven-strategies-to-fix-stalled-promises-432h - Inside `Neet-Nestor/Telegram-Media-Downloader`: A Practical Look at Browser-Based Media Export Source: devto-javascript Topic: JavaScript URL: https://dev.to/sloves/inside-neet-nestortelegram-media-downloader-a-practical-look-at-browser-based-media-export-40na - async/await without the pitfalls Source: devto-javascript Topic: JavaScript URL: https://dev.to/stackhorizon/asyncawait-without-the-pitfalls-3g15 - Starlight 0.42 Source: astro-blog Topic: Web (+JavaScript) URL: https://astro.build/blog/starlight-042/ - htmx 4.0 takes HTML-driven apps further Source: frontend-focus Topic: Web (+PostgreSQL) URL: https://frontendfoc.us/issues/756 - MERGE/SPLIT PARTITION reverted again Source: postgres-weekly Topic: PostgreSQL URL: https://postgresweekly.com/issues/663 - Nifty Django Feature: Use Index for Custom Migration Operations Source: pythonhub-digest Topic: Python (+Django) URL: https://www.better-simple.com/django/2026/09/02/nifty-feature-use-index-for-custom-migrations/ - Fable 5.1 🤖, Waymo vs Tesla 🚕, agentic testing 👨‍💻 Source: tldr-tech Topic: General URL: https://tldr.tech/tech/2026-09-02 ## Research - Avoiding Entity Key Drift in a Data Lake: Step 2, When Fuzzy Matching Stops Working Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/avoiding-entity-key-drift-in-a-data-lake-step-2-when-fuzzy-matching-stops-working/ - A RAG That Says “Not in This Document” Has to Show Four Kinds of Evidence Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/a-rag-that-says-not-in-this-document-has-to-show-four-kinds-of-evidence/ - Graph Neural Networks: GCN, MPNN, and GAT, Explained Simply Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/graph-neural-networks-gcn-mpnn-and-gat-explained-simply/ - A Practical Introduction to PySpark Window Functions Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/a-practical-introduction-to-pyspark-window-functions/ - Who Judges the Judges? A Chinese Safety QA Benchmark for Evaluating LLM Responses and Safety Judges Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01210 - Benchmarking Vision-Language Models for Automated Pathology Diagnosis and Report Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00866 - Scalable Rao-Blackwellized Online Planning for High-Dimensional POMDPs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01351 - A Closed-Loop Evaluation of Capability Loss and Recovery in Compressed Driving Policies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00718 - RACE: Scalable Statistical Estimation of Functional Consistency in LLM Neurons Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24758 - Taming Modality Entanglement in Continual Audio-Visual Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.17234 - GeM-NR: Geometry-Aware Multi-View Editing for Nonrigid Scene Changes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05142 - Authority Bias in Conversational Search Engines for Academic Paper Recommendation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00248 - Towards a Reliable and Practical Eval Pipeline Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00805 - RestoreBench: Can AI Agents Restore Power Flow Convergence? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00384 - Deploying and Evaluating a Smart-Agriculture Agentic Engine for Full-Season Soybean Farm Operations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00106 - Position Matters: Feature Inversion Attacks in ViT Split Inference with Token Reduction and Shuffling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01232 - Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.31075 - Triple-Bottom-Line Sustainability of Language Models for Edge AI: A Comparison Between SLMs and Quantized LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00665 - Validity-Aware Jailbreak Evaluation for Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00498 - Analog-DB: An Agent-First Analog Integrated Circuit Database, From Blocks to Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01286 - Are We There Yet? Assessing Computer-Use Agents for Blind Users' Accessible Interaction with Desktop Applications Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00524 - CacheBridge: Efficient Cross-Model KV Cache Transfer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00891 - Differentially Private Paired Table-Image Multimodal Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00708 - MutMem-V2: Cryptographically Authorized Mutation in Persistent Agent Memory Portable Verification and Reproducible Evidence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01235 - Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01481 - Evaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and Searching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01404 - Revisiting Face Recognition for Monozygotic Twins: The Celeb Twins Test Set Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01141 - Residual Sparsification via Output Importance for Compressing Mixture-of-Experts LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00575 - Data-Driven Persona-Conditioned Agents for A/B Test Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01038 - SymFold: Synergizing Evolutionary and Structural Priors for Accurate Protein Inverse Folding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01353 - Self-EmoQ: Plutchik-Guided Value-based Planning to Drive Streaming Emotional TTS Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09837 - ADGNet: Asymmetric Dual-text Guided Network for Infrared Small Target Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00853 - Parsing the Stream: A Live Trace Model for Long-Horizon Agents and Their Observers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01466 - Revealing Multi-View Hallucination in Large Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.23934 - Beyond the Image Plane: World-Grounded Queries for Multi-Object Tracking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00924 - ISO-RAG: Isoperimetric Noise Control for Retrieval-Augmented Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00513 - Heard but Not Heeded: Paralinguistic Information Encoding and Loss in Audio-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00727 - ConvDeck: Conversational Paper-to-Slide Generation via Stage-Specific User Feedback Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00226 - BS: Take the Hint - Interactive Multitracer PET/CT Lesion Segmentation with a Scribble-Conditioned ResEnc U-Net Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01554 - A Human-AI Theorem Connecting Spontaneous and Field-Induced Mechanisms of Collective Behavior in One Dimension Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00322 - EDGE: Error Dependency Graph-Guided Multi-Error Attribution in Multi-Agent LLM Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01360 - Don't Let the Model Write the YAML: Deterministic, Minimal-Diff GitOps Remediation from LLM-Proposed Field Changes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00227 - The Irreversibility Budget: Fleet-Level Risk Accounting and Admission Control for Agent Operating Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00275 - Visual Attention Faithfulness in Vision-Language Models is Heterogeneous Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00830 - Intelligent Edge Computing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00181 - GeoGR^2:Zero-Shot Geospatial Inference via Geostatistically-Guided Iterative Refinement with LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.04080 - When Oracle Conditioning Misleads Deployment: Conditioning-Availability Bias in Echocardiographic Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.03342 - Recursive Criticality of AI Self-Improvement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00137 - Semi-Supervised Virtual Staining via Morphology Preservation and Histopathological Realism Constraints Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00984 - SARTM: Segment Any RGB Thermal Model with Language aided Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.01950 - Investigating Hyperparameter Optimization and Transferability for ES-HyperNEAT: A TPE Approach Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00449 - LifeAgentBench: Benchmarking LLMs for Long-Horizon, Cross-Dimensional Lifestyle Health Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.13880 - WiseSpec: Requirements-Driven Agents for Code Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00568 - S^3martCirc: Self-supervised Smart Circuit Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00755 - Accelerating Unified Multimodal Models with Core-Expansion Routing and Unified Computation Scheduling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29291 - TempCloze: Can Video-LLMs Identify the Missing Middle? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01515 - HyperWorld: Hypergraph-Structured State Serialization Improves Learned Textual World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00002 - Solaris: Towards Interfaces That Are Generated, Not Coded Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00776 - A Hybrid Insider Threat Detection Framework Combining Multi-Agent Simulation, Layered SIEM Correlation, and Theory-of-Mind Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.04243 - MADS: A Multiview Acoustic Descriptor Set Beyond Standard Spectral Summaries Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00792 - Causal Probing for Internal Visual Representations in Multimodal Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05593 - Automated Event Log Generation from Unstructured Text Using Finetuned LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01320 - CoVer: Conflict-Aware Claim Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00508 - EmbodiedSkills: A Unified Framework for Orchestrating, Training, and Deploying VLA Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01281 - Autoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30751 - Towards reliable multimodal disaster severity assessment through preference optimization and explainable vision-language reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00879 - Generativism: Toward a Learning Theory for the Age of Generative Artificial Intelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.12441 - A Network Science Perspective on Evaluating Deep Graph Generative Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01015 - Measuring the Behavioral Fidelity of Long-Horizon Human Activity Simulations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01257 - Escaping Redundant Reasoning: Structure-Aware Search for Inference-Time LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00738 - Few-Shot Out of Domain Intent Detection with Covariance Corrected Mahalanobis Distance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00961 - On the Human and Computer Alignment of Attribute-Based Music Matches Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00987 - Autoresearch for Marketplace Catalogs: From Legacy Forms to AI-Native Matching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00274 - ViPlan: A Benchmark for Visual Planning with Symbolic Predicates and Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.13180 - Relational-Core Graph Analytics Querying graphs at SQL scale, and why the node/edge model is a performance tax, not a truer picture of connected data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01525 - IMPACT: Attention Is the Interaction Map for Scalable Interaction-Aware World Model Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00161 - Automated Tree Knowledge Graph Construction using Ontology Expansion and Retrieval from Vietnamese History Textbooks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00763 - Distributed Implicit Harm: A Compositional Safety Blind Spot in MLLM-Based Video Moderation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00206 - When the Algorithm Becomes the Brand Crisis: A Sociotechnical Theory of Distributed Responsibility and Accountable Transparency Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00510 - Does Runtime Topology Context Improve LLM-Generated Kubernetes Security Patches? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.25995 - Causal Evidentiary Governance for High-Risk Machine Learning Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01040 - Discrete-Time MDP Modeling for Multi-Item Capacitated Lot Sizing with Stochastic Demand Timing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00004 - Rock, Paper, Scissors, ... Dynamite - A Model of Disruption from New Technologies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00207 - Make Some Noise: Unsupervised Remote Sensing Change Detection Using Latent Space Perturbations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.19881 - DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.06161 - UrbanDS: A Graph-Guided LLM Multi-Agent System for Data-Intensive Urban Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.26724 - Flow Reasoning Models: Turning Flows Into Efficient Recurrent Reasoners Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.29150 - ReDeck: Step-Level Render-Grounded Refinement for Document-to-Slide Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00194 - Does Reasoning Mitigate Backdoor Attacks? A Neuro-Symbolic Perspective Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00464 - VectorGym: A Multi-Task Benchmark for SVG Code Generation, Sketching and Editing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.29852 - SlideBank: A Persistent Hierarchical Evidence Bank for Consistent Whole-Slide Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00342 - One Prompt Is Enough: Watermark Laundering Through Foundation Image Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01249 - Can LLMs Design Video Coding Tools? A Case Study on Planar Mode Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01535 - Agentic Large Language Models for Training-Free Neuro-Radiological Image Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.16729 - Human-AI Co-Interpretation for Responsible AI: A Hermeneutic Perspective Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00334 - One Policy, Any Budget: Internalizing Budget-Aware Search via Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00813 - Dependency-Aware Chain-of-Thought Compression for Financial Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00413 - EGT-KG: Evidence-Grounded Typed KG Retrieval for Practical Scientific QA with Small Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00479 - Electronic Navigational Chart Change Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20218 - Mechanism Design for Alignment and Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01595 - A Formal Analysis of Agent Payment Protocols Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00060 - UniACE: A Unified Framework for Evaluating LLM Agentic Capabilities Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.27898 - ContextPipe: Database-Inspired Context Assembly for Long-Horizon Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00749 - EvoSCM: Scientific Belief Revision Through Causal Model Evolution and Experimentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01526 - FLaG: Frequency-Domain Latent-attention Gated Pooling for Token Aggregation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00831 - HiLRP: Toward One Trustworthy Explanation for Vision Transformer: Conservation-Valid Attribution via Attention Primitives Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01282 - LUNA: Learning Universal 3D Human Animation Beyond Skinning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31981 - Long-Horizon State Tracking in LLMs: Executing MD5 through a Deep Sequence of Dependent Tool Calls Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00012 - The Assistant's Ideal Self Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00304 - StudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00787 - TUTTI: Toward generalizable audio-to-score transcription via fully synthesized data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00640 - AutoXRD: Autonomous LLM Agents and Comprehensive Evaluation for Powder Diffraction Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00070 - AgentFactory: Towards Automated Agentic System Design and Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01045 - SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05726 - StainPresetNet: Stain Preset Network for Fast Multi-to-Multi Stain Normalization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01146 - IWP: Token Pruning as Implicit Weight Pruning in Large Vision Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.00757 - REVISE: Validity-Guided Recovery for Online Revisions in Agent Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00643 - Figures as Programs: Recursive Generation of Editable Scientific Figures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01006 - When Guardrails Look Effective: Construct Validity Failures in LLM Agent Commerce Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01519 - KGFR: A Foundation Retriever for Generalized Knowledge Graph Question Answering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.04093 - RAPIDMap: Rapid Multi-Agent Pipeline for Interpretable Disaster Mapping from Satellite and Street-view Imagery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00046 - FoldingAgent: Inferring Parametric Origami Procedures from Demonstration Videos Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00377 - Prompt-Robust Language Models: Which Training Strategies Work? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01217 - SCAFFOLD: A Large-Scale Structured Dataset of Computer Science Research Figures with Diagram QA and Chain-of-Thought Reasoning Traces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00018 - Guided Prompt Evolution for Vision-Language Models Adaptation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.09493 - Autonomous discovery of new structure-plausibility laws for explainable and rapid crystal diagnosis and screening Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01209 - Uncovering the Computational Ingredients of Human-Like Representations in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.01030 - Restrict, Don't Retrain: Inference-Time VLM Guidance for Zero-Shot Aerial Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00628 - The Safeguard Worked. Is the LLM System Safer? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00519 - A Machine Learning-Driven Solution for Denoising Inertial Confinement Fusion Images Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.16717 - V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16792 - Athena: Vulnerability-Affected Library Identification via Knowledge Graph Completion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01187 - Socrates went Nuclear: Comparing Interaction Strategies for AI systems in a Learning Context using Brain Sensing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00584 - Cost-efficient Active Learning for Referring Image Segmentation and Grounding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30621 - OpenAgentFlow: Enabling System-Wide Safety Boundaries for Heterogeneous AI Agent Fleets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00015 - Incremental Risk Assessment of Progressive Elder Financial Scams via Instruction-Tuned Small Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00005 - Reinforcement Learning Enhanced LLM Agents for Complex Vehicle Routing Problems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00859 - The zbMATH Open Knowledge Graph: Tracing Centuries of Mathematical Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00969 - Event-Aligned Analysis of Multi-Rater Pain Assessments Using Continuous Wearable Physiology Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23705 - Jailbreaking Text-to-Image Models Through Cracks: Navigating Heterogeneous Safety Filters via Multi-Agent Debate Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01168 - LEAP: Likelihood Elicitation and Aggregation for LLM-based Probabilistic Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01337 - In-Context Neurofeedback: Can LLMs Control Their Internal Representations through Privileged Access? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00904 - DiagEvo: Diagnosis-Guided Self-Evolution via Hierarchical Error Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00768 - DNC-IMM: Early Lane-Change Intention Recognition via Neural Calibration Based on Driving Context Information Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01120 - Reasoning-supported Robustness Validation of Automotive E/E Components Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16421 - SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00595 - Agentic programs: an emerging form of scientific software in computational materials science Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00795 - Training-Free Refinement of Flow Matching with Divergence-based Sampling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.04646 - pro-team at LLMs4OL 2026 Tasks Flagship and Reuse: Retrieval-Augmented Generation and Vocabulary-Constrained Filtering for Ontology Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27101 - Reconstruct! Don't Encode: Self-Supervised Representation Reconstruction Loss for High-Intelligibility and Low-Latency Streaming Neural Audio Codec Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.05887 - H2Table: Hierarchical Hypergraph-Enhanced Large Language Models for Complex Table Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01216 - A Mathematical Framework for Legacy, Governance, and Decision Integrity in Enterprise AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00572 - Operational Regimes in Non-Convex Optimization: A Multiplier-Based Taxonomy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00471 - Conversation Coach: A Voice-enabled AI System that Helps Practice Difficult Workplace Conversations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00441 - PopPert: Population-level Joint-Distribution Modeling for Single-Cell Perturbation Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01357 - HiveTraceGuard-Pro: A Compact Generative Guardrail for Prompt Injection, Jailbreaks, and Adversarial Obfuscation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01046 - Making Prospective Memory SLM-Shaped: Typed Intention Stores for Small-Model Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01272 - Invalidation Contracts for Cross-Episode Agent Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00243 - Space Generative AI with Solar Energy Harvesting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01062 - TimeSteer: Inference-Time Speech Scheduling in Joint Audio-Visual Diffusion Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01277 - Wave Function Backpropagation with Explicit Temporal-Interval Dynamics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00503 - Probabilistic Model Checking of Autoregressive Neural Sequence Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00838 - The Artificial Experimentalist: Discovery and Control of Self-Organizing Phenomena with Autotelic Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26116 - CoBRA: Learning Tool-Use Boundaries via Counterfactual Margins Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00967 - Dual Process Motion Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01260 - MicroEvo: Knowledge-Guided LLM Sampling for Efficient Microarchitecture Design Space Exploration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06183 - Asymmetries in Spontaneous and Instructed Deception Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00180 - ARISE-RL: Agentic Rubric-Grounded Iterative Self-Evolution with Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01058 - H3-World: Turning Language Understanding into World Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01560 - Neuro-Symbolic Geometric Abstraction (NeuSOGA): From Observations to Symbolic Mathematical Representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01408 - Diffusion Large Language Models for Visual Speech Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28456 - AI Morbidity and Mortality: A Framework for Clinical AI Failure Review Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00076 - X-SG$^2$S: Safe and Generalizable Gaussian Splatting with X-dimensional Watermarks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.10475 - QILP-0: Constructing Observational Declarative Twins of Quantum Circuits Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01049 - Towards Generalizable Visually Grounded Exploration of Household Devices Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00845 - The Answer Is Not the Argument Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00264 - SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.15550 - User Representation via Cross Multi-source Behavior Pre-training for Mobile Games Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01057 - Neural-Primitive: An Efficient End-to-end Local Planner with Primitive-based Imitation Learning for Autonomous Flight Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20948 - The Lifecycle of LLM-as-a-Judge for Large-Scale Recommendation Explanations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18300 - Beyond the Clock: Measuring the Value of Adaptive Revision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00874 - Same Request, Different Boundary: Evaluating Cybersecurity Assistance across Conversational Contexts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00578 - A Composable Evaluation System for Reproducible Omni-Modal Foundation Model Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01315 - ParaStudent: Closing the Sim2Real Gap in User Simulators for AI Tutor Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.12674 - AI Should Not Only Be Helpful. It Should Be Contingent. Artificial Intimacy, Sycophancy, and the Future of Social Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00211 - Text-guided flow matching enables sample-efficient crystal structure generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01076 - mimeo: Compiling Public Expert Corpora into Agent Skills and Testing What Transfers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00453 - CARE: Contrastive Anchor-based Rubric Evolution for Large Language Model Post-Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00892 - When Safety Routing Breaks: Understanding Alignment Fragility under Benign Fine-Tuning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01455 - EULER: Exploring Underused Links with Evidence-Checked Return for Multi-Agent Mathematical Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00032 - Verifiable abstention makes AI leak diagnosis accountable in urban water distribution networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18836 - Hypotheses-Guided Self Distillation for Continual Personalization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00251 - SpecMind: Enabling Spectrum Intelligence via Multi-Agent Hybrid Retrieval-Augmented Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00427 - RecalibrateGPT: AI Fatigue Resilient Conversational Interfaces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00506 - DramaChain Bench: An End-to-End Benchmark for Short-Drama Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00646 - Feedback-Assisted Trust Propagation over Document Relation Graphs for Retrieval-Augmented Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00543 - On Synthesis of Metric Interval Temporal Logics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01032 - VOIM: Training-Free Open-Vocabulary 3D Instance Mapping for RGB-D and Monocular SLAM Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00775 - Runtime-Independent Persistent Agents: Preserving Identity, Memory, and Code Across Models, Harnesses, and Servers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00546 - Individualized Algorithmic Advice as a Strategic Signal on Competitive Markets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.09454 - Cleaner Speech, Weaker Generalization: Revisiting Pitt-Derived Benchmarks for Alzheimer's Disease Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00276 - TRU: Targeted Reverse Update for Efficient Multimodal Recommendation Unlearning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.02183 - Drift-Aware LLM Routing with Sparse Contexts and Shared Budgets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00662 - Successive Capacity Growth: Task-Complexity-Driven Width and Depth Expansion for Vision Transformer Encoders in JEPA World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27367 - AnalysisBank: An Expert Analysis Pattern Library for Financial Report Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00818 - Multi-Agent LLM Orchestration Achieves Deterministic, High-Quality Decision Support for Incident Response Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.15755 - AREX: Towards a Recursively Self-Improving Agent for Deep Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.21461 - Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01487 - Towards a Belief-Based World Model for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00455 - Delegation Without Trust: An Empirical Gap Analysis of Identity, Authorization, and Runtime Governance in Multi-Agent LLM Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00267 - Towards a Characterization of Counting and Alternating Classes via Discrete Ordinary Differential Equations Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2608.05431 - A Dichotomy for Complex Boolean Holant with Binary Disequality Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2609.00219 - Depth-1 expanders on the unitary group and applications Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2609.01605 - SVP Is NP-Hard for Some Rank-2 Cyclotomic Modules Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2609.01469 - Subgroup Accessibility in Group Order Logic Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2609.00499 - Quantified propositional calculi and narrow implicit proofs Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2606.10535 - Convergence and efficiency proof of quantum imaginary time evolution for bounded order systems Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2506.03014 - Scope3Trace: Evidence-Based Identification and Extraction of Scope 3 GHG Emissions from Sustainability Reports Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.17122 - Investigating Assistant Bias in LLM User Simulators Using a Role Vector Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00608 - Do as I Say, Not as I Do: Instruction-Induction Conflict in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.20382 - Auditing Generative Audio Calls for Known-Task Audio-LLM Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27817 - When Modality Gap Reduction Fails: Prediction-Level Hubness in CLIP Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01103 - Self-Evolving World Models for LLM Agent Planning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.30639 - Beyond Static Summarization: Proactive Memory Extraction for LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.04463 - Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.19011 - trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00038 - SciTrue: Reliable Scientific Claim Validation with Frontier and Open Language Models at the NTCIR SciClaimEval Task Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00654 - Separating Syntax from Language: A Mechanistic Account of Translation in Multilingual LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01356 - FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00660 - XQDT: eXplainable and Quantitative Data-Text Alignment Metric with Feedback Signals Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29948 - Membership Inference in Fine-tuned Diffusion Language Models via Token-level Memorization Asymmetry Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00873 - Arkios: An Open Bilingual English-Nepali Language Model Trained From Scratch, with a Devanagari-Aware Tokenizer Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30092 - Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01532 - Same Semantics, Different Outcome: On the Modality Robustness of Multimodal LLMs under Knowledge Conflict Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00550 - Simple Additions, Substantial Gains: Expanding Scripts, Languages, and Lineage Coverage in URIEL+ Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.27183 - Deep Thought Alignment: Trajectory-Level Latent Distillation for Video Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16316 - Some Emotions Run Deeper: Layer-wise Probing and Causal Intervention in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01279 - DigitalCoach: Communication and Grounding Gaps in Human and Agentic Computer Use Coaching Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31980 - Instella-MoE Technical Report Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00791 - Zero-Shot Respiratory Sound Classification through LLM-Augmented Audio-Text Alignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00055 - ChatDev 2.0: A No-Code Multi-Agent Platform for Developing Everything Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00714 - Slow to See, Slow to Suppress: Understanding the Effects of Modality in Context-Memory Conflicts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00293 - Phrase-Localized Language-Contrastive Guidance: Training-Free Localized Accent Control for Code-Switching Text-to-Speech Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01016 - SDARE-Bench: Evaluating Large Language Models on Conversational Stigma Detection and Response in Dyadic and Group Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01548 - TopoAlign: A Framework for Aligning Code to Math via Topological Decomposition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.11944 - Emotional Labor Strategy Preferences in LLM Personas Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00310 - The Importance of Being Statistically Earnest: A Critical Re-evaluation of GSM-Symbolic Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28700 - SURE-Challenge: Evaluating Speech Evidence Before Speech-LLM Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27783 - SpokenUS: A Spoken User Simulator for Task-Oriented Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16783 - One-shot Style Transfer LLM log-probabilities for Authorship Attribution and Verification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.13302 - NewsRECON: News Article Retrieval for Image Contextualization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.14121 - KItCAT: Knowledge Injection via Input Corruption for Auto-regressive Training Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00082 - Energy-Based Transformers as Predictors of Reading Difficulty Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23382 - FaST: Feature-aware Sampling and Tuning for Personalized Preference Alignment with Limited Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.04698 - SCoNE: Selective Context-aware Neuron Editing for Robust Retrieval-Augmented Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00689 - Human-Anchored Factuality Evaluation with Strategic Annotation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00494 - HiDiffTIR: Hierarchical Difficulty-Aware Policy Optimization for Multi-Turn Tool-Integrated Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21863 - LLM-as-a-Demographic: Whom Sociodemographic Prompting Helps, and Whom It Hurts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00222 - Is Human Annotation Necessary? Iterative MBR Distillation for Error Span Detection in Machine Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.12983 - Exploring Collaboration between a language and a non-language agent Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00474 - Who Annotates in NLP? A Large-scale Assessment of Human Annotation Reporting between 2018 and 2025 Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02255 - ExpArt-KG: Artwork Image Description Generation through Iterative Exploration of Knowledge Graphs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00629 - Post-hoc Alignment of LLM-judges to Human Judgment Distribution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01073 - PCoMoE: Shifting MoE Inference from Monolithic Expert Selection to Fine-Grained Path Composition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01024 - Replacing Training with Memory: Listwise Selection for Text-to-SQL Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00834 - Padamitra: Grounded Glossary Generation for Classical Sanskrit Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25038 - PropUQ-MAS: Propagation-Aware Uncertainty Quantification for LLM Multi-Agent Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22130 - AfriSUD: A Dependency Treebank Collection for Evaluating Models on African Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.12708 - Calibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00949 - Efficient SWE Agent Benchmarking via Trajectory-Aware Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01603 - MemeBridge: A Dataset for Benchmarking and Mitigating the Bidirectional Cultural Gap in Meme Interpretation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00491 - The Interlingua Hypothesis: LLMs Translate via a Latent Task-agnostic Feature Space Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00515 - LOOMSUM:Weaving Quantitative and Narrative Evidence for Faithful Long Text-Table Summarization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00241 - A systematic Approach to constructing a Chance-and-Risk Matrix for Semiconductor Supply Chains Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01563 - Graph Evidence Is Not Enough: Diagnosing Native Decoder Use in Graph-Augmented LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30437 - LLMBridge: An LLM Pipeline for End-to-end Referential Bridging Resolution in English Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29048 - Automatic Item Generation for Personality Situational Judgment Tests with Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.12144 - TEIDAN: A Multilingual Multiparty Dialogue Corpus Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00802 - Argument Quality Assessment with Large Language Models: A Pairwise Bradley-Terry Approach Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28313 - Subword Segmental BabyLMs: Learning to Tokenise for Sample-Efficient Pretraining Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01151 - Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01601 - Skill Following: Evaluating Actual Skill Use in Retrieval-Enabled LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00549 - Two locked tests of phase-structure features for transition prediction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00335 - On the Design Fundamentals of Pixel Text Representation Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01147 - Do Multimodal LLMs See Before They Read? Diagnosing Contextual Sycophancy Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00067 - M4FC: a Multimodal, Multilingual, Multicultural, Multitask Real-World Fact-Checking Dataset Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.23508 - OASIS: Optimizing Attacker Sequences for Hard-Label Black-Box Text Attacks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29568 - The Privacy-Hallucination Tradeoff in Differentially Private Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00492 - FormalTCS: Benchmarking End-to-End Frontier Formal Theoretical Computer Science Research of Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20153 - Beyond Tokens: Semantic-Aware Speculative Decoding for Efficient Inference by Probing Internal States Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.03708 - ALEE: Any-Language Evaluation of Embeddings via English-Centric Minimal Pairs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.00171 - Attribute-Based Activation Steering of LLMs for Group-Specific Explanation Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29215 - GUI-CC: Benchmarking Contextual Consistency of GUI World Models as Agent Environments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00048 - Polish ModernBERT: The Long and Short of Polish Language Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01379 - Creative Generation via Multi-Agent Debate: Does Debate Suppress Diversity? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00683 - From Terminology to Diagrams: Visual-Instruction Generation for Scientific Diagram Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00948 - GuidedBench: Measuring and Mitigating the Evaluation Discrepancies of In-the-wild LLM Jailbreak Methods Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.16903 - Latent Recurrent Thoughts: Recurrent Refinement of Proposed Latents for Reasoning with Frozen LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01117 - InteractBench: Benchmarking LLMs on Competitive Programming under Unrevealed Information Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29632 - GlossoGen: Emergent Language in Complex Multi-Agent LLM Interactions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01491 - MiNER: Fine-Tuned Biomedical Natural Language Processing for Malaria Disease Entity Recognition in Clinical Texts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00073 - Probing Factual Knowledge Transfer with Training Data Interventions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01341 - Think Like a Doctor: Conversational Diagnosis through the Exploration of Diagnostic Knowledge Graphs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01995 - SFAD: Speculative Factuality-Aware Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00796 - Enoki: Efficient Multi-Level Hallucination Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00581 - From Tool Use to Technological Agency: LoopCAT as a Local-First, Open-Source Tool for Translation Technology Education Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00344 - Designing Proactive Thought Partners for Writing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01588 - Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29464 - CaRL-EM: Cost-Aware Reinforcement Learning for Entity Matching with LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01195 - VIBE-Bench: Evaluating Personalized Large Language Models When Profiles Don't Mean Preferences Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00921 - CoLT-Drive: Counterfactual Long-Tail Benchmarking and Knowledge-Preserving Adaptation for Driving Affordance Prediction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00242 - Beyond Magnitude: Contrastive Routing for Modular Mixture-of-Experts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01100 - Beyond Token Positions: Safety Alignment Across Denoising Steps in Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00495 - Medical Causal Hypothesis Verification with Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00063 - From Base Rollouts to RL Reasoning: A Budgeted Search Perspective Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01274 - PersuaRL: Reinforcement Learning-Driven Multi-Expert Selection for Persuasive Dialogue Generation in Insurance Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01188 - CordisBench: Can Language Models Reason About Component Lifecycles in Dynamic Agent Harnesses? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01600 - AdaSearch: Balancing Parametric Knowledge and Search in Large Language Models via Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.16883 - MusTBench: Benchmarking and Advancing Temporal Grounding in Music LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29300 - MELD: Mel-Spectrogram-Based Speech Language Modeling with Discrete Latent Variables Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29859 - A Dataset for Modeling Iterative Problem-Solving Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00940 - Learning What to Retain: Gated-Memory Routing for Efficient Collaboration in Multi-Agent LLM Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00237 - Life Operators: a self-evolving framework for multiscale life modelling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00068 - Overfitting Mitigation via Singular Value Decomposition in Minimum Bayes Risk Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01135 - EdiTikZ: Scientific Figure Editing from Revision Trajectories Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01409 - Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00621 - Multilingual Medical Reasoning for Question Answering with Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.05658 - SafeMath: Safe Solutions for Unsafe Math Word Problems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.25201 - ClinTraceBench: Source-Verifiable Longitudinal Clinical Reasoning over EHR-Derived Dialogues Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01111 - BOW: Training Language Models to Reason Over Plausible Next Words Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.13502 - A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.12781 - Retrieval, Scoring, and Decoding Shape Performance and Stability in LLM-based Conversational Recommendation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00086 - Latent Mechanisms of Language Control in Multilingual Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00325 - Consistency Without Alignment: Item-Sensitive Language Models Indistinguishable From Random Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00576 - Measuring Optimal Transport in Transformer Depth Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00748 - When Features Become Instances: Inverted Contrastive Learning for Unsupervised Feature Selection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00782 - Can Large Language Models Handle Discourse Particles? A Case Study of Colloquial Malay Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28782 - Over-Refusal and Representation Subspaces: A Mechanistic Analysis of Task-Conditioned Refusal in Aligned LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.27518 - Inspicio: Open-Vocabulary, LLM-Based Sense Retrieval for Historical Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00998 - Oblivion: Self-Adaptive Agentic Memory Control through Decay-Driven Activation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.00131 - Compile, Don't Memorize: A Context Compilation Architecture (CCA) for In-Context Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00759 - Hints Help But Do They Teach? Evaluating Skills Transfer in Code Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01106 - PlanarBench: Evaluating LLM Spatial Reasoning via Planar Graph Drawing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02010 - InComeS: Integrating Compression and Selection Mechanisms into LLMs for Efficient Model Editing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.22156 - The Scientific Contribution Graph: Automated Literature-based Technological Roadmapping at Scale Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.15011 - FinLifeBench: Exhaustive Life-Event History and Financial-State Reconstruction from Longitudinal Banking Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01198 - EDRAC: Benchmarking Arabic Dialect Reading Comprehension Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01113 - Explore Before Committing: Hypothesis-Guided Search for Deep Research Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01294 - Evaluating Style-Personalized Text Generation: Challenges and Directions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.06374 - Verifiable Disaster Storylines and Causal Knowledge Graphs: A Citation-Grounded Pipeline from Heterogeneous Humanitarian Sources Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00858 - Detoxifying Toxic Communication: A Design Science Approach to Responsible AI Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00361 - Toppling the Hierarchy in Byte-level Language Modeling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00463 - WorldBench: Culturally Grounded Benchmark for Multilingual Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01056 - Ready to Speak: Aligning LLMs for TTS-Friendly Text Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01246 - A Unified Mechanistic Analysis of Knowledge- and Safety-Based Refusals Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00760 - Commit-first LLM judging inherits the judge's own errors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00088 - Detecting Hidden Behaviors in LLMs via Activation-matched Finetuning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00351 - Whether LLMs Can Navigate Beliefs and Facts Depends on How You Phrase It Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.17809 - Can Large Language Models Forecast What Researchers Study Next? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00747 - From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00051 - What Does an Agentic Software Engineering Benchmark Measure? Profiling Task Demands and Agent Behaviour Beyond What Category Labels Reveal Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01271 - Vision Is Not Overhead: One-Pass Block Drafting for Lossless Speculative Decoding in Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00355 - Bridging the English-Arabic Medical Knowledge Gap: Targeted Low-Rank Adaptation via Causal Layer Selection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00207 - StudentSim: Training LLM-based Student Simulators Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01591 - VocalAffectBench: Evaluating Vocal Emotion Recognition in AI Audio Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.28932 - Does task decomposition improve automatic NLG evaluation? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01139 - Disclosure-Gated User Simulation for Companion-Agent Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00982 - PersianAnonymizer: Evaluating LLM-Labeled Training for Efficient NER-based Anonymization in Persian Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00958 - Beneath the Diff: Diagnosing and Mitigating Algorithmic Mode Collapse in Code-Level Autonomous Research Loops Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00077 - HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01437 - Evaluating Second-Order Bias of LLMs Through Epistemic Entitlement Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17506 - TWIX: a Two-Stage Approach for End-To-End Named Entity Recognition and Relation Extraction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00832 - CHARM: Character Hallucination for Multicultural Role Play Benchmark Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01352 - RPCBench: A Benchmark for Proactive Premise Critique in LLM-based Recommendation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00918 - How Correct Is Your Answer? A Semantic Correctness Framework for Open QA Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01369 - MAS-ProVe: Understanding the Process Verification of Multi-Agent Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.03053 - Scientific Agent Skills: A Library of Procedural Knowledge for Research Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00065 - (V)LMs generalize beyond surface co-occurrence: Evidence from cross-modal number agreement Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00443 - Camellia: Benchmarking Cultural Biases in LLMs for Asian Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.05291 - CWoMP: Morpheme Representation Learning for Interlinear Glossing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18184 - How Human-Like Are Large Language Models? A Register-Aware Linguistic Evaluation Framework Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23651 - Unified Multi-Dialectal Neural Machine Translation for Bangla Using the Dwadash Benchmark Corpus Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12018 - When Tokenization is Secretly Output Supervision Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01386 - Zero Hallucination, by Construction: Hallucination-Aware Layered Oversight for Trustworthy Enterprise AI Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.17883 - DECSELFMASK: Leveraging Unlabeled Text via Self-Relevance-Guided Masking for Decoder-Only Classification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09466 - Can LLMs Reliably Self-Report Adversarial Prefills, and How? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23671 - Closing Cost-Quality Gap in Document VLMs: Difficulty-Aware Data Curation and Quality-Adjusted Deployment Economics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01575 - PromptNCE: Conditional Probabilities and PMI Using Only LLMs and Contrastive Estimation Prompts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21776 - Predicting Program Exit Code with LLMs and Programming Language Semantics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00579 - When History Is Multimodal: Rethinking Context Management for Long-Horizon Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29897 - DART: Draft-Agreement Routing for Training-Free Adaptive Thinking Budgets in Hybrid Reasoning Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23181 - Removable and Irreducible: A Token-Cost Ledger for the Multilingual Tokenization Tax Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00378 - CUDA-Harness: Harnessing Agentic CUDA Kernel Generation and Optimization from Natural Language Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00058 - Towards AI-Assisted Clinical Trial Matching: Practical Considerations, Multicenter Evaluation, and Real-World Deployment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01202 - Aligned but Flattened: Analyzing the Trade-off between Cultural Alignment and Diversity in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00565 - Citing Less Critically: LLMs Reshape the Rhetoric and Reach of Scientific Citation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01432 - Reliability Challenges in Diffusion Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01318 - Do General NLP Embeddings Capture Ontological Reasoning? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00177 - Toward Workflow-Aware Benchmarking for Healthcare NLP Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00296 - Apples on the Table? Evaluating Text-Guided 3D Scene Synthesis via Fine-Grained Constraint Verification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.03001 - DiscoTrace: Representing and Comparing Answering Strategies of Humans and LLMs in Information-Seeking Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.15140 - Late Transformer Layers Recode Syntax Canonically: Evidence from Greek Scrambling and Cross-Layer Generalisation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00416 - GRRM: Group Relative Reward Modeling for Machine Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.14028 - Location-Aware Language Models via Secondary Embeddings Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00454 - LLM-Driven Autonomous Vehicles Inherit Human Driver Biases in Pedestrian Yielding: Results and Implications From A New Benchmark Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00192 - LLMPEDIA: Browsing, Verifying, and Comparing the Parametric Encyclopedic Knowledge of LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01182 - HugAgent: A Human Simulation Benchmark for Individual-Level Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.15144 - Quit While You're Ahead: Quit for Efficient Candidate Generation in Machine Translation Reranking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00588 - Calibrating Small Language Models for Claim Check-Worthiness Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30731 - Joint Training Is Not Enough: Conditioned Cross-Granularity Training for Multimodal Document Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00756 - Trust Your Guide Only When Certain: Uncertainty-Aware Sparse Alignment at Inference Time Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00624 - CoMMET: A Psychologically Grounded Benchmark for Evaluating Theory of Mind in Multimodal LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.11915 - Lagged Coupling: Internal Representations Become Readable Before They Become Causal Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01048 - Bridging Lexical Divergence: LLM-Assisted, Cost-Efficient, Zero-shot Scientific Entity Linking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00228 - Suffix-Constrained Greedy Search Algorithms for Causal Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.01243 - Value Over Language Model: Detecting Original Contribution in Writing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00700 - When Irrelevant Text Matters: Affine Margin Shifts in Multimodal Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19208 - StateSwap: Probing Support-Elimination Hidden States in Multiple-Choice Questions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01081 - OUTLETS: Output-Length Prediction from Speculative Decoding Backbones Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01068 - From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01572 - Assessing Suicide Risk in Arabic Crisis Helpline Calls: A Comparison of Arabic and English Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00191 - Anamnesis: An Open-Source Platform for Large-Scale Backstory-Conditioned Survey Simulation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.10628 - Will the User Ever Know? Covert Indirect Prompt Injection Attacks on Tool-Using LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30362 - Automated Researchers Can Reliably Mitigate Alignment Failures Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.28945 - When Compression Helps and When It Hurts: Condition-Aware Analysis of Chain-of-Thought Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.21704 - From Confusion to Clarity: Confusion-Aware Retrieval and Knowledge Injection for Text Classification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01564 - From Rollouts to Recipes: Self-Contained Post-Training for LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01422 - Polished but Unresolved: Identifying Late-Stage Pressure States in Long-Horizon Tool-Use Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00823 - AI Alignment through a Game-theoretic Lens: A Survey Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27910 - SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19799 - NSIDDx: A Design Framework for Neuro-Symbolic, Practitioner-First Differential Diagnosis in Low-Resource Settings Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00256 - The Rise of Verbal Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01597 - InSight: A Benchmark for Agentic Claim Verification in Interactive Visualizations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01383 - IntroConformal: Conformal Factuality Guarantees for Large Vision-Language Models via Introspective Signals Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01375 - HiVe: Beyond Static Prompts for Multitask Learning via Hierarchy-based Vertical Mixture-of-Experts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29790 - Behaviorally Effective LoRA Writes Are Sparse and Structured Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01374 - Behaviorally Grounded User Profiles from the Wild for Personalized Alignment and Multi-Perspective Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00014 - CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23181 - Uncovering and Mitigating Aggregation-Induced Reward Hacking in Multi-Reward Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00213 - Lazy Grounding: Attacking Search Agents with Factual Evidence Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30303 - RePro: Proof-Verified Benchmark Rewriting for Reliable Evaluation of LLM Mathematical Problem Solving Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00062 - Visual Framing for News Stance Detection via Image Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00685 - A Certificate-Producing Cascade for Equational Implication: The SAIR EQT2 Stage 2 Solver Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00706 - Auditing Harness Tampering in Self-Improving Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00069 - Bounded Relative Boundary Implies Narrow DNF Approximation Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2609.00240 - Graphs with Long Pseudosimilarity Chains under Consecutive Vertex Deletions Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2609.00394 - On the Extension Theorem for Packing Steiner Forests Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2603.16956 - The Most Malicious Ma\^{i}tre D' Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2407.09000 - Eleven, twelve, and thirteen lonely runners Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2604.23906 - Improved bounds for the variant of lazy cops and robbers on generalized hypercubes Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2609.00720 - Logarithmic Chowla Correlations Across All Shift Scales Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2608.23500 - A Simpler Analysis of the Bansal-Jiang Quasi Monte-Carlo Algorithm via Haar Wavelets Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2608.27986 - Two-State Max-Plus Comparison Is Decidable Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.00678 - Random-Priority Frontier Routing: Tight $\Theta(n^c)$ Bounds Against $c$-Node Cartels Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.00893 - Improved lower bounds of the time complexity of shellsort Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2607.08997 - Fuzzy Pattern Matching in Ordered Structures Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2608.25032 - Beyond the Bethe Approximation of the Permanent Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2608.28031 - Kernelization of 2-Club Cluster Edge Deletion on Interval Graphs Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.01021 - Sensitivity Oracles for Matroid Packing, Matroid Covering, and Matching Problems with Applications Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.01283 - Finding Shortest Reconfiguration Sequences on Independent Set Polytopes Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2604.24132 - On the Instance Optimality of Bidirectional Dijkstra's Algorithm Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2608.26952 - Finding $b$-colorings Using Feedback Edges Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2512.14390 - Designing Compact ILPs via Fast Witness Verification Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2509.25445 - Bridging the Gap Between Stable Marriage and Stable Roommates: A Parameterized Algorithm for Optimal Stable Matchings Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2603.26943 - Disproving the Greedy Superstring Conjecture Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.01365 - Quantum matrix arithmetics with Hamiltonian evolution Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2510.06316 - Optimality of Random Regular Graphs in Sparse Network Designs Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2606.14995 - Staged Linguistic Seeding: Grounded Query Expansion for Verified-Unit QA in AI Contact Centers Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.00844 - APEX-EM: Non-Parametric Online Learning for Autonomous Agents via Structured Procedural-Episodic Experience Replay Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2603.29093 - Two-Sided State-Space Models for Sequential Recommendation with Non-Random Multimodal Review Feedback Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.00165 - World Model-Guided Reinforcement Learning via Counterfactual User Engagement Simulation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.01067 - Towards Effective Structured Context Modeling for Conversational Recommender Systems via Dual-node Monte Carlo Tree Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.00618 - DCA-MoE: Spatially Adaptive Cross-Layer Fusion and Density-Routed Experts for Crowd Counting Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.15213 - It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.00638 - Closed Forms and Synthetic Twins: Predicting Approximate Nearest Neighbor Recall from Embedding Statistics Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.00364 - VerTox: Verifiable Reward-Guided Corpus Poisoning Against Neural Ranking Models Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.01325 - SwapRec: Warming Up Cold Items Through Training-Time Swaps Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.00913 - Ctrl-F-Resist. Practices, Challenges, and Technical Needs of Civil Society Organizations Monitoring the Far-Right Online Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.00808 - MUSES: A Benchmark for Prospective Intellectual-Roots Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.00313 - E-SENS: Exclusion-Sensitive Penalization for Negative-Constraint Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.30130 - TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2408.09199 - From Saliency to Discriminability: Rank-Preserving Visual Token Pruning for VLM Rerankers Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.00667 - RATIO: A Benchmark for Retrieval Across Typed Ideation Operations in Scientific Literature Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.27394 - TGR: Advancing Industrial Recommendation from Generative-Paradigm Ranking toward Unified Generation and Reasoning Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.00986 - AutoConcept: Training-Free Concept-Guided Reranking for Metadata-Available Composed Image Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.01456 - Sources of Truth: A Multi-Platform, Multilingual Audit of Citations in AI Mental Health Information Queries Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.00319 - SilentProbe: Measuring Silent Failure in Production APIs Used as Agent Tools Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.00035 - TRIS: A Tri-Layer Retrieval Integrity Sieve Against Knowledge Poisoning Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.00470 - NeuroGraph: An AI Graph-Driven Neuro-Symbolic Framework for Explainable Threat Reasoning in Advanced Manufacturing Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.00604 - REIGN: Refurbished Embeddings with Integrated Guidance Networks for Efficient Context-Length Scaling Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.29899 - From Prompt to Purchase: How AI Brand Recommendations Move Consumers on the Open Web Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2606.10907 - DISTAL: Distillation and Self-Supervised Pretraining for Structure-Agnostic Materials Property Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00059 - Generative artificial intelligence for reliable mechanistic reasoning for corrosion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00099 - AgentProv: Auditing Agentic LLM API Providers via Tool-use Policy Probes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00052 - Multi-Head Self Attention is a Parameter Identification Mechanism Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01231 - iPINN for Broadband CARS Phase Retrieval: A Framework for Function Approximation and Inverse Modeling Problems in Nonlinear Spectroscopy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00883 - Semi-Supervised Classification with Informative Missing Labels in Weibull Mixture Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00774 - Reparameterization through Coverings and Topological Weight Priors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.23804 - MemoryWalker: Stop Training Agents on Contexts They Never Saw Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00865 - REAL-Q: E2E LLM Quantization via Dynamic Gradient Descent Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00049 - Can We Trust In-Distribution Success? Locked Evaluation Reveals Transfer Failure and Sampling-Depth Entanglement in CRISPRi Perturbation Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00152 - Recurrent State Encoders for Efficient Neural Combinatorial Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.05084 - Retrieved but not ranked: surface-form bias in structural retrieval, from mathematics to agent trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01556 - Spawn Freely, Act Sparingly: Progressive Risk Vesting for Recursive LLM-Agent Trees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01035 - ReproRepo: Scaling Reproducibility Audits with GitHub Repository Issues Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18237 - Performative Privacy: When Differential Privacy Maximizes Utility Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.28198 - AdaptNTK: Adaptive Uncertainty Quantification and Active Learning for Neural Network Potentials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00488 - RW-LoRA: Communication-Efficient Decentralized LoRA Fine-Tuning via Random Walks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00078 - Gradient-Update Mismatch: Rethinking Conflict-Free Training of Physics-Informed Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01558 - DeSyR: A Decoupled Symbolic Recovery Framework with PINN-Guided Structure Search and Physics-Informed Coefficient Refinement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00530 - Synthetic Worlds for Temporal Evaluation and Knowledge Updating in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00184 - Non-Parametric Spatiotemporal Trajectory Prediction via State-Conditioned Transition Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14349 - Latent-Space No-Arbitrage Geometry of Generative Models for Implied Volatility Surfaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00332 - ViTAMINS: An Empirical Study of Training Self-Supervised Vision Transformers with Synthetic Hard Negatives Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01041 - Online simultaneous inference for quantiles via smoothed stochastic gradient descent Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.13299 - Quantum Sparse Autoencoders for Q-Matrix Estimation in Cognitive Diagnosis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01537 - Controllable Image Captioning with Prompt-Conditioned Scene Rewards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00709 - Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26797 - AutoScientist-Quant: Self-Evolving Coding Agents for Automatic Research in Quantitative Investment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.28632 - MRMAD: A Multi-Round Multi-Audio Benchmark for Evaluating Acoustic Degradation Perception in Large Audio-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22236 - Prediction-Assisted Pricing and Admission for LLM APIs with Stochastic Token Consumption Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00710 - Higher Structures in Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00472 - Three-dimensional Conditional Diffusion Models for Cosmological 21 cm Lightcone Emulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29016 - Can machines think efficiently? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.26954 - DAGGER: Distractor-Aware Graph Generation for Executable Reasoning in Math Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.06853 - Shallower ReLU Network Representations via Exact Linear Algebra Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.21651 - CADKnitter: Compositional CAD Generation from Text and Geometry Guidance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.11199 - A penalised Saito functional for heuristic search of free line arrangements Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.02995 - MMAI Gym for Science: Training Liquid Foundation Models for Drug Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.03517 - Let Confidence Change, Not the Prediction: Prediction-Preserving Repair for Post-hoc Calibration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01072 - Attention Sensitivity Is Not Enough: Dissociating Attention-Level and Behavioural In-Context Learning under Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00064 - CATeye: Coupled Attribute-Topology Invariance Learning for Voucher Abuse Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01425 - Stress Testing Unlearning Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22527 - Context Window Failures in Relational Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00460 - DynaNDE: Dynamic Near-Data Expert Scheduling for Batched MoE Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00407 - Uniform a priori bounds and error analysis for the Adam stochastic gradient descent optimization method Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18899 - CopyShield: A Cross-Level Benchmark of Copyright Defenses in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01161 - The Multiple Timescales of Gradient Descent on the Edge of Stability: A Perturbative Derivation of the Central Flow Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01034 - TRIAGE: Three-level Routing and Intelligent Agent Guidance for Efficient Execution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01428 - Denoising the Deep Sky: Physics-Based CCD Noise Formation for Astronomical Imaging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.23276 - Post-Training Science for Supervised Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01244 - Silence is Golden: Mitigating Hallucinations in Large Audio-Language Models via Layer-Weighted Vector Steering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.12851 - Web Price Extraction: State of the Art and an Adaptive Browserless Implementation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01030 - Real-Time Neuromorphic Spectrum Intelligence Simulator Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00585 - Coordinate-Residual Physics-Driven Neural Network for Inverse Scattering Imaging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09382 - A Multi-Branch Feature Fusion Approach for Health Misinformation Detection and Propagation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00403 - Denoising Diffusion Generative Models Secretly Calculate Attentions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00885 - Exploring Sparse Autoencoders in Text-Based Causal Confounding Adjustment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01322 - Disciplined Bilevel Programming Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00644 - How Temporal Correlations Shape Memory in Linear Recurrent Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00420 - ReNFT: Repairing Mode Collapse in Reward Post-Training via Internal Probability-Mass Recalibration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00061 - Online Regime-aware Calibration for Black-box Social Simulators via Posterior-assisted Evolutionary Dynamic Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.19481 - PEARL: Training Socratic Tutors with Pedagogically Aligned Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29582 - Learning to Remember: End-to-End Training of Memory Agents for Long-Context Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.18493 - Can LLMs Use Relational Transformer Embeddings? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00457 - Modeling Information Blackouts in Missing Not-At-Random Time Series Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.01480 - Topological Steering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00597 - Predicting Subsurface Abnormalities Growth using Physics-Informed Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01417 - Can LLMs Imagine Moral Alternatives Beyond Binary Dilemmas? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31213 - Training-Free Policy Violation Detection via Activation-Space Whitening in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.03994 - VATO: A Vortex-Force-Aware Transformer Operator for Unsteady Separated Aerofoil Flows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00507 - Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.25050 - One-Layer Transformer Provably Learns Multiclass One-Nearest Neighbor in Context Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01311 - Towards Provable and Scalable Training of Quantized Neural Networks with Ising Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.18240 - Solving In-Table Prediction Problems by Deep Neural Networks with Performance Evaluation Using Synthetic Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01262 - Deep learning based numerical approximation algorithms for stochastic partial differential equations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2012.01194 - Superposed Latent Autoencoder Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01158 - HBQ: Hierarchical Scaling Block Quantization with Hardware-Efficiency-Aware Design for Accurate LLM Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00450 - CRAFT: Fine-Tuning Pre-hoc Explainability in AI-native 6G RAN Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00590 - When Does Online Adaptation Pay on the Edge? A Leakage-Free Evaluation of Warmup, Learning-Rate Selection, and Resource Trade-offs for Time-Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01126 - LLM-driven design of physics-constrained constitutive models: two agents are better than one Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23754 - Universal Approximation of Nonlinear Operators and Their Derivatives Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.15285 - Rigorous Error Certification for Neural PDE Solvers: From Empirical Residuals to Solution Guarantees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.19165 - Flawed in Nature, Perfect through Evolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00129 - Auditing Frozen-Encoder Anomaly Detection Across Mechanical Systems: Representation Provenance, Calibration, and Protocol Effects Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.11415 - LatentPress: Context Compression Beyond Text and Vision Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01507 - Skill Reuse as Compression in Agentic RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.31509 - What Do Students Learn? A Feature-Level Analysis of Dark Knowledge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03052 - Cheap Verifiers, Large Blind Spots: Measuring the Reliability Cost of Cost-Saving Cascades Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01345 - Hidden State Poisoning Attacks against Mamba-based Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.01972 - Assessing Alignment and Stability of Feature Importance Explanations via Weight of Evidence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00090 - Contribution-Aware Bandwidth Allocation for Multimodal Split Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01406 - Diffusion as a Training Curriculum for Timestep-Free Iterative Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01449 - FedReview: Review and Dispose Poisoned Updates without Validation Datasets or Historic Knowledge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2402.16934 - When Prediction Error Is Not Enough: Evaluating Nuisance-Function Prediction for Causal Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00071 - Workload Identification with Physical Side Channels for AI Governance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00309 - Frozen Cores Need Task Signal: Fisher-Whitened Cross-Covariance for Low-Resource LLM Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00762 - Pre-carved Niches: The Formation Dynamics of Modular Task Partitions in Early LLM Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01170 - Rethinking Learnability in Offline Data-driven Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01493 - Freeze, Diffuse, Decode: Geometry-Aware Adaptation of Pretrained Transformer Embeddings for Antimicrobial Peptide Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.23120 - The Topological Trouble With Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.17121 - FlexP-SFT: A Flexible Aggregation-Free Framework for On-Device Personalized Split Federated Fine-Tuning of LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.10349 - Learning Task-Specific Antibody Representations via Function-Aware Masking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00518 - HEAL: Hindsight Entropy-Assisted Learning for Reasoning Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.10359 - BeamRMX: Radiation-Pattern-Driven Learning for Generalizable Beam Radio Map Prediction and Beam Management Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00615 - Topic Matching in the Wild: Benchmark and Lessons from Real-World ASR Transcripts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00330 - Position: Privacy Is a Claim, Not a Property of Synthetic Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01273 - Context-Grounding Gains Are Mediated by Pre-existing Machinery: Auditing GRPO, SFT, and DPO Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00925 - Sierpi\'nski--Knopp Wasserstein Distance for Persistence Diagrams and Applications to 2-Wasserstein Approximation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01528 - Building Expressive and Tractable Probabilistic Generative Models: A Review Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2402.00759 - Good Memory Has ECC: Evaluating the Memory of Vision-Language Models Beyond Accuracy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00103 - QTEA: Ternary LLMs with Sparse Residual Salient Weight and By-Column Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00224 - Hyper-Fold: Exploring the Expressive Limit of Sequence-Geometry Learning for Proteins via Hypergraph Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29207 - Embedded Conditional Independence Tests for Large Language Model Generated Text with an Application to German Parliament Speeches Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00946 - Capability-Gated Language Models: Security Composes, Utility Does Not Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00445 - Selective Agent Guidance via Entropy: Learning Autonomous Policies from Imperfect VLM Teachers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01567 - Adapting Without Gradients: Affine Statistics Transport and What Its Certificate Can Tell You Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00374 - Task-Specific Prompt with Global Context for Multi-Task Graph Pre-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00047 - Can LLMs Discover Scientific Laws in Real and Parallel Worlds? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01552 - CompanionSim: Synthetic Data for Evaluating Anthropomorphism in Human-AI Relationships Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00250 - Agentic Empirical Asset Pricing: Methodological Foundations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00731 - WiSDoM: Wireless Sparse Decision Transformer with Mixture-of-Experts for Multi-Task Mobile Network Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00284 - Beyond Scores: Understanding LLM-as-a-Judge Mechanisms in Summarization Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01604 - Explore More, Drift Less: Outcome-Only Reinforcement Learning Can Suffice for Long-Horizon Interactive Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01245 - When Metropolis and Hastings Meet Bradley and Terry: Exact MCMC From Preference Voting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00905 - Facet-0: A Robotic Foundation Model for Contact-Rich Precise Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01596 - Leakage-Audited Benchmarking Reveals Limited Evidence for Cross-Subject Auditory-Evoked EEG Vowel Perception Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.00865 - From Language to Behavior: Scaling Sequence Transformers for Industrial Recommendation Ranking with Rec-Native Designs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01240 - Verdict Instability of OOD Scores under Reference Resampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00691 - Local Reference Geometry Residual Augmentation for Imbalanced Time Series Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00093 - SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01343 - CRAD: Class-wise Reliability-Aware Distillation for Decentralized Heterogeneous Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00446 - Enabling KV Caching of Shared Prefix for Diffusion Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07571 - Steer, Don't Solve: Training Small Critic Models for Large Code Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.21811 - Is Knowledge Distillation Actually Greener? A Case Study in Machine Translation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.09691 - Neural means and kernel corrections for operator learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00389 - Backspace as a Natural Experiment: An Accelerated Failure Time Model of Selective Post-Error Motor Impairment in Parkinsons Disease Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.24796 - Debiased Inference for AI-Generated Data without Gold-Standard Labels: Identification via Multiple Imperfect Measurements Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18294 - Any-Order GPT as Masked Diffusion Model: Decoupling Formulation and Architecture Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.19935 - Artificial Rosetta Stone: Constrained Maximum A Posteriori (MAP) Reconstruction of Symbolic Raga Sequences via Order-k Markov Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01064 - WHALE: A Simple Recipe for Joint Harness-Weight Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00196 - Elite-Weighted Supervised Fine-tuning for Goal-Directed Molecular Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00189 - Matched Queries for Curvature and Density at Branching Junctions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01319 - REFACTOR-VLA: Unsupervised Library Learning of Typed Motor Programs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01215 - Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.01706 - Final Checkpoints Are Not Enough: Analyzing Latent Reasoning Faithfulness Along Training Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.06648 - Conditional Flow Matching for ML-Based Inverse Design Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00863 - Variable Selection for Feature-Based Newsvendor Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01544 - Edge-Girth as a Structural Edge Feature for Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01441 - Fractal dimension predicts quantum kernel collapse in angle-encoded data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00475 - EEG-AS: Instance-Level Foundation Model Selection for EEG Foundation Models via Behavior Reconstruction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00653 - SOVER: Formal Certification of Optimization Reformulations via LLM-Assisted SMT Verification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00728 - Global Attention with Linear Complexity for Exascale Generative Data Assimilation in Earth System Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.16590 - Are Near-Tied LLM Rankings Robust to Family-DIF-Guided Benchmark Recomposition? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00482 - QABBA: Symbolic Time-Series Compression via Integer-Quantized Aggregation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.15209 - Text Capability Loss in Vision-Language Adaptation: An Attention-Sink Diagnosis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00746 - DualStake: Dual-Path Confidence Calibration in Deep Research Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00935 - Accelerating Chemical Kinetics for Exoplanet Atmospheres using Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00428 - ValueGraph: Value-Signal Guided Graph Pre-training for Contextualized User Representation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00057 - Nonlinear Dynamics In Optimization Landscape of Shallow Neural Networks with Tunable Leaky ReLU Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.25060 - KV Cache Offloading for Context-Intensive Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.08426 - NeuroPriv: Adversarial Representation Learning for Privacy in Wearable EEG Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00390 - EEG-VID: Task-Guided Latent Predictive Pretraining for EEG Decoding and Assistive Target Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00566 - FedSPDnet: Geometry-Aware Federated Deep Learning with SPDnet Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.22494 - Beyond AHI: An Interpretable Causal-Discovery-Guided Framework for Sleep Recovery in Connected Health Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18506 - A Stable Aggregation Method for Quantum Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00356 - Towards Agentic Cloud Engineering: Graph and Loop Engineering with a Zero-Trust Agent Harness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00050 - DiscoverPhysics: Benchmarking LLMs for Out-of-the-Box Scientific Thinking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26087 - Scaling Near-Optimal SFT-RL Annotation Budget Allocation from Small to Large LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01573 - The Curse of Multilinguality in Lexical Normalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00329 - TACS: Trajectory-Aware Candidate Selection for LLM Jailbreak Suffix Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29564 - SupraTok: Cross-Boundary Tokenization for Enhanced Language Model Performance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.11857 - Towards unsupervised representation learning for quantum data: quantum models with inference and generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00372 - GeoPAR: Large-Scale Multi-Agent Combinatorial Optimization with Geometry-Guided Parallel Autoregressive Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00577 - MUGEN: Generating Unlearnable Graph Examples for Multiple Learning Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00696 - The Alexander-Hirschowitz theorem for neurovarieties Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.19703 - EchoSonar-R: A Multi-View Reasoning-Enabled Model for Disease Classification and Report Generation in Echocardiography Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.28164 - Provably Safe Sim-to-Real Transfer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01418 - SinkPruner: Sink-Free Visual Token Pruning for Multimodal Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01004 - Dense Process Supervision for Search Agents via Fact Utility Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00833 - The Visual Insensitivity Gap: Diagnosing When Vision-Language Models Fail to Use Visual Evidence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00868 - Direct Optimization of a 3D Finite-Source Reflector via Neural-Network Parameterization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00899 - Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00097 - Reading the Gate, Not the Interference: Output-Side Interference Measurement Does Not Track Merge Collapse Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11797 - Dense Weak Hiding: Closing Complexity Gaps in Nonconvex and PL Finite-Sum Optimization under Individual Smoothness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00045 - Learning Sparse Decision Trees via Transformer Variational Auto-Encoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01430 - Efficiently Estimating Optimal Hyperparameter Scaling Laws through Power-Law Entropy Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01431 - HiMPO: Hindsight-Informed Memory Policy Optimization for Less-Entangled Credit in Long-Horizon Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16285 - Iterative GRPO: Batch-Online Policy Iteration for Multi-Turn RL via Single-Turn RLHF Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.21638 - Efficient Learning of Balanced Signed Graphs via Sparse Linear Programming Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.01826 - Geometry-aware Latent Autoregressive Generative Model for PDEs in Complex Domains Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00297 - Provably Efficient Federated Reinforcement Learning with Linear Function Approximation and Logarithmic Communication Cost Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00193 - UI-Venus-2 Technical Report Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00028 - Where the Verifier Fails: A Category-Level Audit of Reward Signals in RLVR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01354 - Logarithmic-Free Moment and Generalization Bounds for Uniformly Stable Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09870 - ES-AHD: An Evolution Strategy Framework for Automatic Heuristic Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00023 - EM^2Mem: Event-Centric Multimodal Memory for Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00551 - I-CARE: Analysis of interference-related phenomena in a controllable, diverse and representative unlearning setting for text-to-image models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00003 - GENIE: Watermarking Graph Neural Networks for Link Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.04805 - RECAP: Regression Evaluation for Continual Adaptation of Prompts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.06698 - Safin-1: Safety from Within through Memory-Native State Evolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00092 - Inverse Reconstruction of Shock Time Series from Shock Response Spectrum Curves using Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.03229 - Do LLMs Know Your Neighborhood? Auditing LLM Priors for Neighborhood-Level Mobility Prediction and Structural Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00345 - Neurosymbolics for Data Engineering: Achieving Long Context Token Reduction Without Finetuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00367 - TopoCompress: Long Context Compression via Graph-Wired Semantic Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30811 - FractalNet-Based Heterogeneous Federated Learning for Orbital Edge Intelligence in Satellite Mega-Constellations: A Wildfire Case Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00875 - Unsupervised Partner Design Enables Robust Ad-hoc Teamwork Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.06336 - OCGQuant: Outlier-Companion Grouping for NVFP4 Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00066 - Optimizing Byzantine Node Placement in Decentralized Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01495 - Why Do Reasoning Models Lose Coverage? The Role of Data and Forks in the Road Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.17026 - Does Imitation Learning Preserve Temporal Robustness in Dexterous Manipulation? An Expert-Learner Comparison Across Task Execution Speeds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01453 - Accelerating Reinforcement Learning via MPC Solver-Gradient Guidance for Weights-varying MPC Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01061 - Sharp Mixed Spectral Barron Regularity of Coulombic Many-Electron Wave Functions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00872 - A hybrid quantum-classical neural network for learning to route Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00489 - GazeRefine: Expert Gaze as a Test-Time Prompt for Training-Free Medical Image Segmentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01310 - Relational Task Generation Language: A Declarative Specification Framework for Relational Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01292 - 3D-Consistent Multi-View Editing by Correspondence Guidance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.22228 - Manifold-Aware General Coded Computing for Straggler-Resilient Distributed Computing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00552 - Field-Aware Agent Skill Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02880 - Fair Minimum Labeling: Efficient Temporal Network Activations for Reachability and Equity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.03899 - SCALE:Scalable Conditional Atlas-Level Endpoint transport for virtual cell perturbation prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.17380 - On the Existence of Consistent Adversarial Attacks in High-Dimensional Linear Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.12454 - What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.08524 - DOG-DPO:Dynamic Optimization in Geometry for Safety Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07678 - On the Reliability of Generative Augmentation: A Wasserstein-Based Theoretical and Empirical Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01410 - Breaking the Structural Identity: Personalized Federated LoRA Fine-tuning under Rank Heterogeneity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00632 - D3-Gym: Constructing Real-World Verifiable Environments for Data-Driven Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.27977 - Lightweight Adaptation of EEG Foundation Models for Stroke Motor Imagery Decoding: Domain Shift and Subject-Level Robustness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00282 - Integrated Noise and Safety Management in UAM via A Unified Reinforcement Learning Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.16440 - ToSCA: Leveraging Hierarchical Reinforcement Learning on Temporal and Strategic Abstractions of Conversational Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21969 - Learning to Refine Hidden States for Reliable LLM Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17524 - Control Variate Score Matching for Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.20003 - HarmoCore: Functional Latent Diffusion for Sparse Reconstruction of Oscillatory Wave Fields Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00679 - A Study of Hidden-State Optimization Order in Predictive Coding Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00686 - Beyond Dense Adam States: Adaptive Log-Space Quantization for Memory-Efficient Optimizers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22322 - NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01549 - BiasGym: A Simple and Generalizable Framework for Analyzing and Removing Biases through Injection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.08855 - SAGE: State-Grounded, Abstention-Aware Evaluation of Task-Oriented Dialogue Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00434 - Subspace Levenberg Marquardt Algorithms in Training Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00789 - SAGE: Subpopulation-Aware Generative Enhancement for Mitigating Spurious Correlations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01051 - Are You Thinking What I am Thinking? : Examining Conceptual Separation in Neural Architectures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00764 - HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00829 - Risk-Aware Decision-Making for Autonomous Overtaking: A World Model-Based Mixture-of-Experts Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00385 - Polarizable atomic multipoles for learning long-range electrostatics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05746 - Subliminal Learning as Trait-Direction Drift: A Mechanism and Targeted Control under SFT Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01091 - Compositional Machine Design as Program Synthesis with LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.14980 - The Frame Kernel Method for Multiscale Operator Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25084 - Exact Global MCMC with Denoising Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00279 - The Structure of Quantization Damage in LLMs: Why the Next Bit Should Be Spent Globally Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01587 - Generalization Bounds for Markov Algorithms through Entropy Flow Computations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.07584 - Ontology-Guided Neuro-Symbolic Inference: Grounding Language Models with Mathematical Domain Knowledge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.17826 - Neural Symbollic Regression Using Deep Learning and Sparse Modelling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01102 - Replicating TRACE: A Practitioner's Guide to Its Threshold and Particle Budget Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01108 - Stochastic complexity of vectors containing cluster structure Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00084 - Poisson-Gamma Dynamical Systems with Time-varying Transition Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00896 - Persistent Entropy as a Detector of Phase Transitions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.09058 - Dr. Claw: An AI Scientist Workspace for Vibe Research Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00365 - Performance-Efficiency Tradeoffs in Transformers: An Approximation Theory Perspective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.03784 - Hidden relationships in a document-derived property graph: top-k chunk embeddings and inverse-distance weighting over a dynamically evolving ontology Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00387 - mzCache: On-Device LLM Memory Management under Multitasking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01338 - Group Adaptive Clipping Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00444 - SEBA: Sample-Efficient Black-Box Attacks on Visual Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.09681 - Common-Center Geometry and Certified Radial Reconstruction for Energy-Form Full Conformal Regions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24964 - Recent Developments in Transformer Inference Deployment on FPGA Platforms: A Survey Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01212 - Different representation learning objectives recover distinct latent structures from the same psychometric data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00100 - Channel-Adaptive Edge AI: Maximizing Inference Throughput by Adapting Computational Complexity to Channel States Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.03146 - How Do Language Models Choose Between Context and Memory? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00753 - VoiceLongMemEval: Do Assistants Remember How You Sounded? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00570 - Measuring consistency via ensemble margin and local prediction variability: Auditing decision systems in the presence of predictive multiplicity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01397 - Counterfactual Fragility Certificates: Exposing High-Confidence Brittleness under Structured Evidence Failure Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00366 - The Constitutional Coverage Trilemma in AI Governance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01275 - S-CEReBrO: Breaking the Memory Barrier in Continuous EEG Monitoring Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.27913 - How Does Alignment Tuning Shape Representations of Sycophancy and Related Cue-Induced Biases in LLMs? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.18114 - A Compositional Kernel Model for Feature Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.14158 - MIDR: Enrichment-Augmented Indexing for Multimodal Document Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01316 - Validating FKG.in: Soundness Assessment in LLM-Augmented Indian Food Knowledge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29249 - Self-Reports Are Not Verification: Environment-Grounded Auditing of LLM Operators in Evolutionary Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00652 - Foundation models for electricity price forecasting and battery arbitrage: Can they replace market-specific forecasting models? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00089 - MaskCode: Mask Transformer for Feedback-Assisted Coding With Linear Block Codes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00715 - Closing the Operational Gap in Semantic Caching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.19719 - Modelpedia: A Catalog of Model Findings for the Meta-Science of AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01090 - Explicit Interaction Architectures for Dynamical Learning: A Controlled Study of Structural Inductive Bias Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.19101 - Why Fine-Tuning Encourages Hallucinations and How to Fix It Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.15574 - Physiological Information Reliability: Cross-Layer Adaptive Resource Allocation for Cardiovascular Sensing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00435 - A Checklist to assess the energy and carbon impacts of ML/AI applications in Earth System Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00847 - DK-GBMKKM: Dynamic Kernel-Space Granular-Ball Multiple Kernel $k$-Means Clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00647 - BiG-SURE - Bipartite Graph for Semantic Uncertainty and Reliability Estimation of LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30646 - Exact Risk-Complexity Laws for Projective Boundaries in Scenario Optimization and Distribution-Free Certification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01355 - Keep Everyone Happy: Online Fair Division of Numerous Items with Few Copies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2408.12845 - Births are difficult to predict even with rich survey and full-population register data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01194 - Bandits in Prod: Hyperparameter Optimization at Inference Time Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01335 - A convolutional framework for detecting event-driven dynamics in energy price series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00402 - A Mathematical Theory of Reusable Neural Bases for Network Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01550 - Deterministic LLM Inference Across GPU Kernels: Power-of-Two INT8 Quantization Scales and the Limits of Tolerance-Based Conformance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00363 - TRUST: Threshold-Recalibrated Uncertainty-Safe Training for Certified Dismissal in Breast Cancer Screening Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00300 - Confess What You Know: Forget-Set Misalignment with Model Knowledge in LLM Unlearning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00605 - Patterning in Practice: Debiasing Reward Models with Susceptibilities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00699 - Lingua Franca or Probing Artifact? Rethinking Latent Language in Multilingual LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00155 - Probabilistic Multi-Agent Aircraft Landing Time Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.08281 - Breaking the Reasoning Horizon in Entity Alignment Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21174 - Vision-Language-Guided Pseudo-Labels for Unsupervised Domain Adaptation in Semantic Segmentation for Waste Sorting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00898 - Variance-Adaptive Muon: Pre-Orthogonalization Variance Modulation for Efficient Language Model Pretraining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.14603 - Investigating Linear Probe Robustness to Linguistic Register, Medical Specialty, and Corpus Shifts in Medical QA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01361 - Does Fault Localization Beat a Fresh Attempt? A Placebo-Controlled Study of Test-Guided Code Repair Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00854 - Independent Reinforcement Learning in Discounted Markov Games Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00504 - From Truncation to Commitment: Persistent Context in Uniform Discrete Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01043 - GenONet: A Generative operator Network for High-Resolution Precipitation Nowcasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00544 - When the Strongest Teacher Is Not the Best Teacher: Student-Centric Answer Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26872 - FloydNet: A Learning Paradigm for Global Relational Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.19094 - RetroReasoner: A Reasoning LLM for Strategic Retrosynthesis Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.12666 - Efficient Adaptation of ROMs for Unsteady Flows Using Data Assimilation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.23188 - Semantic-Guided Multimodal Preprocessing for Vision Transformer-Based Clear Cell Renal Cell Carcinoma Grading Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01426 - Scaled Idempotence in Transformer Attention: Paired OV Geometry and Shared-Value Algebras Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01129 - Process-Aware AI for Rainfall-Runoff Modeling: A Mass-Conserving Neural Framework with Hydrological Process Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.25093 - Right Frame, Wrong Rule: Cultural Cues Expose the Financial Knowledge Gap They Were Meant to Close Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00999 - Multi-View Causal Discovery without Non-Gaussianity: Identifiability and Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.20115 - MineDraft: A Framework for Batch Parallel Speculative Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18016 - Why Multi-Layer Message Passing Works: Completeness Theory for Graph Neural Network Interatomic Potentials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00528 - EvoFlint: An Evolutionary Atlas of Multi-Turn LLM Vulnerabilities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00487 - Online Self-Weighted Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00734 - Soft-Argmax for the Projective Plane via the Veronese Embedding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00521 - Convergence issues in Relational Concept Analysis based on AOC-posets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00054 - A Classifier That Teaches Itself: Self-Improving, Frozen-gate Training (SIFT) for Dynamic Document Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.18358 - Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibility Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.04001 ## Community - Bliki: Paracelsus Maxim Source: martin-fowler Topic: Architecture URL: https://martinfowler.com/bliki/ParacelsusMaxim.html - How to transmit a D-Bus message with the exact same body? Source: rust-users-forum Topic: Rust URL: https://users.rust-lang.org/t/how-to-transmit-a-d-bus-message-with-the-exact-same-body/142202 - Need help about AI Source: rust-users-forum Topic: Rust URL: https://users.rust-lang.org/t/need-help-about-ai/142201 - llm-openrouter 0.7.1 Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/2/llm-openrouter/ - llm 0.34 Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/2/llm/ - Failing to read a file due to it not being valid UTF-8 Source: rust-users-forum Topic: Rust URL: https://users.rust-lang.org/t/failing-to-read-a-file-due-to-it-not-being-valid-utf-8/142197 - llm-anthropic 0.28 Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/2/llm-anthropic/ - llm-gemini 0.34 Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/2/llm-gemini/ - An Accidental Blackboard Source: martin-fowler Topic: Architecture URL: https://martinfowler.com/articles/exploring-gen-ai/an-accidental-blackboard.html - Claude's new system prompt really doesn't want to reproduce song lyrics Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/2/claudes-new-system-prompt/ - How to lookup a value in HashMap with a composite key containing a String without allocating Source: rust-users-forum Topic: Rust URL: https://users.rust-lang.org/t/how-to-lookup-a-value-in-hashmap-with-a-composite-key-containing-a-string-without-allocating/142193 - List types of a struct Source: rust-users-forum Topic: Rust URL: https://users.rust-lang.org/t/list-types-of-a-struct/142192 - Finding the origin of a Result::Err Source: rust-users-forum Topic: Rust URL: https://users.rust-lang.org/t/finding-the-origin-of-a-result-err/142191 - New User Tutorial Source: rust-users-forum Topic: Rust URL: https://users.rust-lang.org/t/new-user-tutorial/142186 - Quoting Rick Brewster Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/2/rick-brewster/ - New to Rust, converting a project from Python Source: rust-users-forum Topic: Rust (+AI) URL: https://users.rust-lang.org/t/new-to-rust-converting-a-project-from-python/142184 - Django Weblog: Django bugfix release issued: 6.1.1 Source: planet-python Topic: Python (+Django) URL: https://www.djangoproject.com/weblog/2026/sep/02/bugfix-releases/ - Christopher Winslett: Postgres Calculations and the Ambiguity of NULL Source: planet-postgresql Topic: PostgreSQL URL: https://postgr.es/p/9tL - Dave Stokes: Loading the Northwinds Database Into PostgreSQL with DBeaver Source: planet-postgresql Topic: PostgreSQL URL: https://postgr.es/p/9tI - Jimmy Angelakos: LinkedIn Live: All right, so you inherited a bad database... Source: planet-postgresql Topic: PostgreSQL URL: https://postgr.es/p/9tN - Do not release the GIL during object destruction Source: discuss-python-ideas Topic: Python URL: https://discuss.python.org/t/do-not-release-the-gil-during-object-destruction/108859 - Proposal: Add new method to `HTMLParser`: `flush(self) -> str: ...` Source: discuss-python-ideas Topic: Python URL: https://discuss.python.org/t/proposal-add-new-method-to-htmlparser-flush-self-str/108855 - Tryton News: Tryton News September 2026 Source: planet-python Topic: Python URL: https://discuss.tryton.org/t/tryton-news-september-2026/9356 - Python GUIs: Are there any built-in QIcons? — Using built-in icons for your apps. Source: planet-python Topic: Python URL: https://www.pythonguis.com/faq/built-in-qicons-pyqt/ - Python GUIs: Understanding QPainter Coordinates in PyQt6 — How the coordinate system works for drawing on canvases in PyQt6 Source: planet-python Topic: Python URL: https://www.pythonguis.com/faq/coordinates-on-qpainter/ - Class-level private property isolation Source: discuss-python-ideas Topic: Python URL: https://discuss.python.org/t/class-level-private-property-isolation/108853 - Christophe Pettus: All Your GUCs in a Row: log_min_duration_sample, log_statement_sample_rate, and log_transaction_sample_rate Source: planet-postgresql Topic: PostgreSQL URL: https://postgr.es/p/9tH - Mark Dufour: Shed Skin restricted-Python-to-C++ compiler v0.9.13 released Source: planet-python Topic: Python URL: http://shed-skin.blogspot.com/2026/09/shed-skin-restricted-python-to-c.html - Graham Dumpleton: Unit testing with wrapture Source: planet-python Topic: Python URL: https://grahamdumpleton.me/posts/2026/09/unit-testing-with-wrapture/ - deforester - Logging for Janet Source: lobsters Topic: General URL: https://codeberg.org/veqq/deforester - METR Report on OpenAI / Hugging Face Hacking Incident Source: hacker-news Topic: General (+AI) URL: https://metr.org/blog/2026-08-26-openai-hugging-face-incident-investigation/#core-takeaways-about-this-incident - Justice Dept. Sides with OpenAI in New York Times Copyright Suit Source: hacker-news Topic: General (+AI) URL: https://www.nytimes.com/2026/09/02/technology/justice-department-openai-copyright-suit.html - M6 Mac Mini vs. M1 Mac Mini: original Apple Silicon versus the new Source: hacker-news Topic: General URL: https://appleinsider.com/inside/mac-mini/vs/m6-mac-mini-vs-m1-mac-mini-five-year-gap-hardware-compared - USPS Built an Untested, Undocumented Ballot-Blocking System Despite Injunction Source: hacker-news Topic: General URL: https://www.techdirt.com/2026/09/02/whistleblower-usps-defied-a-court-injunction-to-build-an-untested-undocumented-ballot-blocking-system-its-own-staff-call-the-process-a-shit-show/ - Maybe We Shouldn't Be Reviewing All This Code Source: hacker-news Topic: General URL: https://martinfowler.com/rachels-ramblings/code-review.html - Launch HN: RonanRX (YC S26) – Personalized Peptides and GLP-1s Source: hacker-news Topic: General (+AI) URL: https://news.ycombinator.com/item?id=49543530 - I Think the Military Commissary Freezers Were Hacked Source: lobsters Topic: General URL: https://signalandsilence.substack.com/p/i-think-someone-hacked-the-commissary - CHC5: Open Camera System – Image Sensor Specification Comparison Source: hacker-news Topic: General URL: https://www.circuitvalley.com/2026/08/chc5-open-camera-sensor-comparison-specification.html - VC isn't VC anymore Source: hacker-news Topic: General URL: https://www.anildash.com/2026/09/02/cancer-capital/ - Show HN: Open source ML programming language playground Source: hacker-news Topic: General (+AI) URL: https://sw-ml-study.github.io/sw-mlpl/ - Reasons robotics is hard Source: hacker-news Topic: General URL: https://secondthoughts.ai/p/14-reasons-robotics-is-hard - Pushdown automata in statistical machine translation (2014) Source: hacker-news Topic: General URL: https://dl.acm.org/doi/abs/10.1162/coli_a_00197 - Uber shuts operations in Nigeria and Uganda with immediate effect Source: hacker-news Topic: General URL: https://www.bbc.com/news/articles/c86xpv8l9y9o - Security Incident – BGP Hijacking Source: lobsters Topic: General URL: https://www.virtualizor.com/blog/security-incident-bgp-hijacking/ - Is There I/O After Death? What Happens to Io_uring When a Process Dies Source: hacker-news Topic: General URL: https://blog.ydb.tech/is-there-i-o-after-death-what-happens-to-io-uring-when-a-process-dies-92c65354873f?postPublishedType=repub - Mamdani Bans AI in NYC Schools Source: hacker-news Topic: General URL: https://www.nytimes.com/2026/09/01/nyregion/ai-ban-schools-nyc.html - asciiQuake Source: lobsters Topic: General URL: https://asciiquake.wtf/ - I rented a car, and within hours my driver's license was for sale Source: hacker-news Topic: General URL: https://arstechnica.com/security/2026/09/my-drivers-license-is-one-of-153-million-for-sale-on-a-new-dark-website/ - Vidact – a compiler that turns React into direct DOM operations Source: hacker-news Topic: General (+JavaScript, React) URL: https://www.vidact.dev/ - Music Theory for Programmers Source: hacker-news Topic: General URL: https://runjs.app/blog/music-theory-for-programmers - El Niño is now stronger than at any point in the last 1k years Source: hacker-news Topic: General URL: https://arstechnica.com/science/2026/08/el-nino-is-now-stronger-than-at-any-point-in-the-last-1000-years-study-finds/ - Altair Basic Interpreter Source Code (1975) [pdf] Source: hacker-news Topic: General URL: https://images.gatesnotes.com/12514eb8-7b51-008e-41a9-512542cf683b/34d561c8-cf5c-4e69-af47-3782ea11482e/Original-Microsoft-Source-Code.pdf - The Silo · interactive 3D cutaway Source: hacker-news Topic: General URL: https://3dscenes.qualityf2p.workers.dev/silo - Z: Local-first search layer for humans and agents Source: hacker-news Topic: General URL: https://github.com/zvec-ai/zvec-grep - I wanna live an NPC life Source: hacker-news Topic: General URL: https://signalundefied.bearblog.dev/i-wanna-live-an-npc-life/ - Fable 5.1 World Modeling Source: hacker-news Topic: General URL: https://github.com/PhiloLabs/fable51-worlds - Muse Spark 1.3 Source: hacker-news Topic: General URL: https://developer.meta.com/ai/models/muse-spark/ - Digital Sovereignty Is Written in PHP Source: hacker-news Topic: General URL: https://thephp.foundation/blog/2026/09/02/digital-sovereignty-is-written-in-php/ - The Death of Physical Media Source: hacker-news Topic: General URL: https://seerofthe.net/the-death-of-physical-media/ - Selling Software Worldwide from Europe Source: hacker-news Topic: General URL: https://holtwick.de/blog/sell-from-europe - Unified Arabic Source: hacker-news Topic: General URL: https://worksthatwork.com/6/unified-arabic - Humanity has built the records of FATE by accident Source: hacker-news Topic: General URL: https://ariadne.space/2026/09/01/humanity-has-built-the-records.html - Black Hole of Los Alamos: Seller of surplus nuclear research materials (2011) Source: hacker-news Topic: General URL: https://www.atlasobscura.com/places/black-hole-of-los-alamos - Using Cloudflare Workers and reCAPTCHA v3 for a Static Site Contact Form Source: hacker-news Topic: General URL: https://nooshu.com/blog/2026/03/09/using-cloudflare-workers-and-recaptcha-v3-for-a-static-site-contact-form/ - Qantas Airbus A380 engine failure in 2010 (2023) Source: hacker-news Topic: General URL: https://admiralcloudberg.medium.com/a-matter-of-millimeters-the-story-of-qantas-flight-32-bdaa62dc98e7 - Async Rust vs RTOS showdown (2022) Source: hacker-news Topic: General URL: https://tweedegolf.nl/en/blog/65/async-rust-vs-rtos-showdown/ - Firefox's AI Switch Is Off. Telemetry Isn't Source: hacker-news Topic: General URL: https://marius.blog/firefox-155-ai-kill-switch-retest/ - CFTC moots rules to stop prediction markets from giving affiliates advantages [pdf] Source: hacker-news Topic: General URL: https://www.govinfo.gov/content/pkg/FR-2026-08-06/pdf/2026-15948.pdf - Why do so many tools have JSON config files? Source: hacker-news Topic: General URL: https://textlog.cc/post/895 - A Million Falcons Went Missing. Here’s How They Were Found Source: hacker-news Topic: General URL: https://www.nationalgeographic.com/animals/article/falcons-migration-angola-falcopolis - This Fence Has No Farmer (Chesterton's Fence and AI-Generated Code) Source: hacker-news Topic: General URL: https://adamgreenough.net/blog/this-fence-has-no-farmer/ - The Overton Window of Food Source: hacker-news Topic: General URL: https://think-twice.me/?p=116 - Electronic skin for prosthetics to sense temperature and pressure Source: hacker-news Topic: General URL: https://news.wsu.edu/press-release/2026/08/20/researchers-develop-electronic-skin-for-prosthetics-to-sense-temperature-and-pressure/ - AI is stopping startups from completing puberty Source: hacker-news Topic: General URL: https://ashley.rolfmore.com/ai-is-stopping-startups-from-completing-puberty/ - I don't have a smartphone or at least I wish I didn't Source: hacker-news Topic: General URL: https://ploum.net/2026-09-02-i_dont_have_a_smartphone.html - Earth's organisms developed via evolution. What if the cosmos did, too? Source: hacker-news Topic: General URL: https://www.smithsonianmag.com/science-nature/earths-organisms-developed-via-evolution-some-theorists-wonder-what-if-the-entire-cosmos-did-too-180989338/ - OpenBSD Stories: Strange Medieval Devices Source: hacker-news Topic: General URL: http://miod.online.fr/software/openbsd/stories/smd.html - Reverse Engineering Unknown File Formats with ImHex Source: lobsters Topic: General URL: https://werwolv.net/posts/file_format_reverse_engineering/ - Static Allocation, Constant Work Source: hacker-news Topic: General URL: https://matklad.github.io/2026/09/02/static-allocation-constant-work.html - Paint.net 5.2 alpha now runs on Linux Source: hacker-news Topic: General URL: https://forums.paint.net/topic/134562-paintnet-52-alpha-build-9739/ - Oh-my-pi – The Harness Playbook Source: hacker-news Topic: General URL: https://stencil.so/blog/harness-playbook - Delidded Intel I9-14900KS CT Scan Source: hacker-news Topic: General URL: https://www.lttlabs.com/articles/2026/09/02/delidded-intel-i9-14900ks - How Railroad Crossings Work (2024) Source: hacker-news Topic: General URL: https://practical.engineering/blog/2023/12/29/how-railroad-crossings-work - Tangle – Visual ML Pipeline Editor Source: hacker-news Topic: General URL: https://tangleml.com/ - Implementing FMA and finding bugs in C and Rust standard libraries Source: hacker-news Topic: General URL: https://shnatsel.github.io/implementing-fma-finding-bugs-in-std/ - CTTI is Exponential, RTTI is Linear Source: lobsters Topic: General URL: https://www.gingerbill.org/article/2026/09/02/ctti-is-exponential-rtti-is-linear/ - How to debloat your Xiaomi 15 Ultra without root access Source: hacker-news Topic: General URL: https://trackerninja.codeberg.page/post/how-to-debloat-your-xiaomi-15-ultra-without-rooting-and-connecting-it-to-the-computer/ - Study Math with Kusama Source: hacker-news Topic: General URL: https://medium.com/counterarts/study-math-with-kusama-6008df7c2abd - The race to engineer new knobs for the human brain Source: hacker-news Topic: General URL: https://www.neuroai.science/p/the-race-to-engineer-new-knobs-for - Show HN: FrontierHarness Eval – 9 harness, same model, cost per pass varies 17x Source: hacker-news Topic: General URL: https://frontierharness.org - Unusual Suspects Source: hacker-news Topic: General URL: https://neal.fun/unusual-suspects/ - Saving money on Google Photos with Immich: Your own personal photo storage Source: hacker-news Topic: General URL: https://www.markpitblado.me/blog/saving-on-google-photos-with-immich-your-own-personal-photo-storage/ - SteamdDB Joins Nexus Mods Source: hacker-news Topic: General URL: https://www.nexusmods.com/news/15597 - The true horror of Edgar Allan Poe’s stories lies in their confessions Source: hacker-news Topic: General URL: https://yalereview.org/article/emily-ogden-edgar-allan-poe - Gemini 3.8 Flash and 3.8 Flash Cyber Source: hacker-news Topic: General (+AI) URL: https://blog.google/innovation-and-ai/models-and-research/gemini-models/3-8-flash-and-3-8-flash-cyber/ - The Highest Point in the Netherlands Source: hacker-news Topic: General URL: https://ipv6.hanazo.no/posts/anniversary-personal/ - Let's build a compressor from scratch Source: lobsters Topic: General (+Rust) URL: https://ochagavia.nl/blog/lets-build-a-compressor-from-scratch/ - Show HN: Think Turing Complete, but you write the circuits in TypeScript (WIP) Source: hacker-news Topic: General URL: https://play.simten.dev - Google avoids a breakup of its ad tech business Source: hacker-news Topic: General URL: https://www.nytimes.com/2026/09/02/technology/google-ad-tech-remedies.html - Check if a file was made with Claude Source: lobsters Topic: General URL: https://www.claude.com/check-content - The holy grail of nixpkgs: version ranges Source: lobsters Topic: General URL: https://fzakaria.com/2026/09/01/the-holy-grail-of-nixpkgs-version-ranges - Exit the Cave Source: hacker-news Topic: General URL: https://turtlespace.blog/p/exit-the-cave - WebLLM: high-performance in-browser LLM inference engine Source: hacker-news Topic: General (+AI) URL: https://github.com/mlc-ai/web-llm - GrapheneOS says Pixel 11 has MTE support after all Source: hacker-news Topic: General URL: https://grapheneos.social/@GrapheneOS/117194007157499435 - Three sites made 215,128 “best software” pages for AI. Perplexity cites them Source: hacker-news Topic: General URL: https://trellner.com/reports/manufactured-sources-behind-ai-recommendations/ - Goroutine Leak Profiles Source: lobsters Topic: General (+Go) URL: https://go.dev/blog/goroutine-leak-profiles - A third of Perplexity's citations don't contain the number they're cited for Source: hacker-news Topic: General URL: https://hausresearch.com/reports/perplexity-citation-audit/ - My practical approach to surfing the web safely Source: hacker-news Topic: General URL: https://molily.de/safe-websurfing/ - Poisson Disk Sampling Source: hacker-news Topic: General URL: https://stripeacross.com/posts/poisson-disk-sampling/ - Six curl CVEs after OpenAI and Anthropic came back with zero Source: hacker-news Topic: General (+AI) URL: https://aisle.com/blog/aisle-discovered-six-curl-cves-after-openai-and-anthropic-found-zero - Biggest dark matter detector spots a single weird particle Source: hacker-news Topic: General URL: https://www.science.org/content/article/world-s-biggest-dark-matter-detector-spots-single-weird-particle - Singapore subway (mrt) information display types Source: hacker-news Topic: General URL: https://www.sgtrains.com/technology-infosys.html - A note on subscription prices from LWN Source: hacker-news Topic: General URL: https://lwn.net/Articles/1090585/ - Watch the 'Eclipse of the Century' Next Year When Spain, Egypt and More Go Dark Source: hacker-news Topic: General URL: https://www.nytimes.com/2026/08/13/travel/solar-eclipse-2027-morocco-egypt.html - LLMs: Intelligence vs. Cost Source: hacker-news Topic: General (+AI) URL: https://openteams.com/intelligence-vs-cost/ - The Cables That Connect the World Source: hacker-news Topic: General URL: https://xn--gckvb8fzb.com/the-cables-that-connect-the-world/ - Aging brains blend memories together instead of just forgetting them Source: hacker-news Topic: General URL: https://studyfinds.com/aging-brains-blend-memories-together-instead-of-forgetting-them-study-finds/ - Dutch central bank moves share of gold from U.S., Canada to London Source: hacker-news Topic: General URL: https://nltimes.nl/2026/09/02/dutch-central-bank-moves-share-gold-us-canada-london-cites-instability - Dependent if expressions without dependent types Source: lobsters Topic: General URL: https://haskellforall.com/2026/09/dependent-if-expressions - Academia as a d-index measuring contest Source: hacker-news Topic: General URL: https://kevinmunger.substack.com/p/introducing-the-k-index - Ask HN: 30, burnt out, with 6-10 months of runway. What would you do? Source: hacker-news Topic: General URL: https://news.ycombinator.com/item?id=49535363 - Using jq to format JSON on the clipboard Source: hacker-news Topic: General URL: https://chris48s.github.io/blogmarks/posts/2021/jsontidy/ - Can I opt out of my input or output data being used for training? Source: hacker-news Topic: General URL: https://help.mistral.ai/en/articles/455207-can-i-opt-out-of-my-input-or-output-data-being-used-for-training - Uber is laying off 10% of staff Source: hacker-news Topic: General URL: https://www.uber.com/us/en/newsroom/simplerfasteruber/ - Check if a file was made with Claude Source: hacker-news Topic: General URL: https://claude.com/check-content - The Empire of Information Source: hacker-news Topic: General URL: https://lareviewofbooks.org/article/data-empire-roopika-risam-information-organize-control-dominate/ - Revisiting Joel's Test Source: lobsters Topic: General URL: https://blog.exe.dev/revisiting-joel - Pointing at the error: compiler-style diagnostics in uutils coreutils Source: hacker-news Topic: General URL: https://uutils.org/blog/2026-08-error-diagnostics/ - The Two Abstractions of System Design: Hide or Reduce Source: hacker-news Topic: General URL: http://muratbuffalo.blogspot.com/2026/05/the-two-abstractions-of-system-design.html - Old Directions: Reviving the spirit of revival Source: hacker-news Topic: General URL: https://www.nplusonemag.com/issue-54/the-intellectual-situation/old-directions/ - Dextroproporphan: An Analogue for a Better Dextromethorphan? Source: hacker-news Topic: General URL: https://monfak.top/blog/posts/dextroproporphan - It's OK to hardcode feature flags (2025) Source: hacker-news Topic: General URL: https://code.mendhak.com/hardcode-feature-flags/ - Why are there no flow batteries with symmetric ferrocyanide electrolytes? Source: hacker-news Topic: General URL: https://chemisting.com/2026/09/02/why-are-there-no-flow-batteries-with-symmetric-ferrocyanide-electrolytes/ - Quasar 438B: Europe's Leading AI Model Source: hacker-news Topic: General URL: https://multiversecomputing.com/resources/introducing-quasar-438b-europe-s-leading-ai-model - Banca Etica Suspends A/I's Account While Condemning the Sanctions Behind It Source: hacker-news Topic: General URL: https://sabot.media/post/banca-etica-statement-english - Fomu An FPGA board that fits inside your USB port Source: hacker-news Topic: General URL: https://www.crowdsupply.com/sutajio-kosagi/fomu - TinyGo 0.42 - Recover Is Real Source: lobsters Topic: General (+Go) URL: https://tinygo.org/blog/2026/tinygo-0.42-recover-is-real/ - ESP32 as counter-surveillance platform Source: lobsters Topic: General (+Hardware) URL: https://www.youtube.com/watch?v=PcK-TDmzshc - Ask HN: Resources to get good at soldering? Source: hacker-news Topic: General URL: https://news.ycombinator.com/item?id=49533840 - Sweden pauses Denmark power cable over EU grid rules Source: hacker-news Topic: General URL: https://www.nordiskpost.com/2026/05/08/sweden-power-cable-dispute-freezes-link-to-denmark/ - What will you do after tech? Source: lobsters Topic: General URL: https://lobste.rs/s/oieyk7/what_will_you_do_after_tech - Commodore 64 released September 1, 1982 Source: hacker-news Topic: General URL: https://dfarq.homeip.net/commodore-64-released-september-1-1982/ - New things for regular expressions in PostgreSQL (pg_tre and pg_re2) Source: lobsters Topic: General (+Databases, PostgreSQL) URL: https://www.depesz.com/2026/08/25/new-things-for-regular-expressions-in-postgresql-pg_tre-and-pg_re2/ - Bye Bye Perspective API: Lessons for Measurement Infrastructure in NLP, CSS and LLM Evaluation Source: lobsters Topic: General (+AI) URL: https://arxiv.org/abs/2604.25580 - Who's Hiring? Q4 2026 Source: lobsters Topic: General URL: https://lobste.rs/s/8mwdf1/who_s_hiring_q4_2026 - ITA Controlled English (CE) Source: hacker-news Topic: General URL: https://github.com/ce-store/ce-store - Read your own writes, off the primary Source: lobsters Topic: General (+Databases) URL: https://boringsql.com/posts/read-your-own-writes/ - Solving the Flat Cube Source: lobsters Topic: General URL: https://mathenchant.wordpress.com/2026/08/19/solving-the-flat-cube/ - The Emergent Symbolic Structure of Artificial Neural Networks Source: hacker-news Topic: General URL: https://arxiv.org/abs/2608.29530 - M-DISC – DVD/Blu-ray compatible discs that may last up to 1000 years Source: hacker-news Topic: General URL: https://en.wikipedia.org/wiki/M-DISC - WebFPGA (2019) Source: hacker-news Topic: General URL: https://webfpga.io/ - A Switch-Level Simulation Model for Integrated Logic Circuits (1981) [pdf] Source: hacker-news Topic: General URL: https://www.cs.cmu.edu/~bryant/pubdir/MIT-LCS-TR-259.pdf - True Rate of Unemployment Source: hacker-news Topic: General URL: https://www.lisep.org/tru - New type of dice guarantees no tie when deciding who goes first Source: hacker-news Topic: General URL: https://www.cbc.ca/radio/asithappens/dice-mystery-board-game-9.7328614 - Normalized Fascism in Open Source: $12 Million Given to DHH Source: lobsters Topic: General URL: https://brennan.day/normalized-fascism-in-open-source-12-million-given-to-dhh/ - Bluefin is a capability system Source: lobsters Topic: General URL: https://h2.jaguarpaw.co.uk/posts/bluefin-capability-system/ - LLMs and self-referentiality Source: hacker-news Topic: General (+AI) URL: https://scottaaronson.blog/?p=10046 ## Media - End-to-end agentic development with Google Gemini, Antigravity, and GitLab Source: youtube-googlecloud Topic: AWS (+AI, Cloud, General) URL: https://www.youtube.com/watch?v=IXc9d_EN4ts - He built a voice controlled drone to avoid using a remote! 🤯✈️ Source: youtube-googlecloud Topic: AWS (+AI, Cloud, General) URL: https://www.youtube.com/shorts/afUQpY5oYcw - Don't wait to graduate: A student’s AI ancestry storyteller Source: youtube-googlecloud Topic: AWS (+AI, Cloud, General) URL: https://www.youtube.com/shorts/2TQuelvaWMo - SIG Contribex Meeting for 2026-09-02 Source: youtube-kubernetescommunity Topic: DevOps URL: https://www.youtube.com/watch?v=yb1-cJcgZzc - SIG Node Meeting for 2026-09-02 Source: youtube-kubernetescommunity Topic: DevOps URL: https://www.youtube.com/watch?v=ZveGhE8xL2k - Kubernetes SIG Release for 2026-09-02T16:28:50Z.mp4 Source: youtube-kubernetescommunity Topic: DevOps URL: https://www.youtube.com/watch?v=deXXMo3J-fo - Why Community is the True Strength of Open Source Source: youtube-cncf Topic: DevOps (+Open Source) URL: https://www.youtube.com/shorts/z8vRJmA79LY - Kubernetes SIG Release for 2026-09-02T15:57:42Z.mp4 Source: youtube-kubernetescommunity Topic: DevOps URL: https://www.youtube.com/watch?v=62hJE8rd73o - WG Workload Aware Scheduling Meeting for 2026-09-02 Source: youtube-kubernetescommunity Topic: DevOps URL: https://www.youtube.com/watch?v=k7PA_tDjpR8 - Merge Forward Meeting - September 2026 Source: youtube-cncf Topic: DevOps (+Open Source) URL: https://www.youtube.com/watch?v=4l0TLT3WAkA - IT'S FINALS TIME 🤯 Source: youtube-docker Topic: DevOps URL: https://www.youtube.com/shorts/vuHCTUVJ_GQ - The most interesting hack in history just got weirder... Source: youtube-fireship Topic: Web (+AI, General, JavaScript) URL: https://www.youtube.com/watch?v=0Rp9KJCEIvg - Demystifying AI terms: loop engineering, squads, and harness | S02E02 | The GitHub Podcast Source: youtube-github Topic: Open Source (+AI, General) URL: https://www.youtube.com/watch?v=7oqYIRbB6Rc - What's it like to be a maintainer of OpenClaw, the fastest growing project in GitHub history? 🦞 Source: youtube-github Topic: Open Source (+General) URL: https://www.youtube.com/shorts/k2fgD6JbB54 - Are you ready for Freo Finals 😤 Source: youtube-docker Topic: DevOps URL: https://www.youtube.com/watch?v=InSUUWydGIo - Jordan Clark | 150 Games Source: youtube-docker Topic: DevOps URL: https://www.youtube.com/watch?v=C-xuR1eA7TY