TILens Daily Edition 2026-09-04 Filters: github=hidden Stats: 949 articles, 51 sources, 611 research papers Top topics: AI, AI Research, General ## News - Amazon MWAA Serverless is now available in AWS GovCloud (US) Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/09/amazon-mwaa-serverless-aws-govcloud/ - Amazon Bedrock Managed Knowledge Base introduces user-managed setup for SharePoint, OneDrive, and Confluence data sources Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/09/amazon-bedrock-managed-knowledge-base-user-managed-setup-sharepoint-onedrive-confluence/ - Amazon Bedrock Managed Knowledge Base now supports ServiceNow as a native data source connector Source: aws-whats-new Topic: AWS (+AI) URL: https://aws.amazon.com/about-aws/whats-new/2026/09/amazon-bedrock-managed-knowledge-base-servicenow-native-data-source-connector/ - Amazon Bedrock Managed Knowledge Base now supports automatic sync scheduling for data source connectors Source: aws-whats-new Topic: AWS (+AI) URL: https://aws.amazon.com/about-aws/whats-new/2026/09/amazon-bedrock-managed-knowledge-base-automatic-sync-scheduling-data-source-connectors/ - Amazon EC2 now supports specifying compatible instance types on AMIs Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/09/ec2-images-supported-instances - Kubernetes v1.37: KubeletInUserNamespace (aka Rootless mode) Graduates to Beta Source: kubernetes-blog Topic: DevOps URL: https://kubernetes.io/blog/2026/09/04/kubernetes-v1-37-rootless-beta/ - OSPAR 2026 report now available with 167 services in scope Source: aws-security-blog Topic: DevSec (+AWS) URL: https://aws.amazon.com/blogs/security/ospar-2026-report-now-available-with-167-services-in-scope/ - Amazon GuardDuty adds optional threat detection rules Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/09/guardduty-optional-detection-rules/ - Amazon ECS introduces Early Success Criteria for service deployments Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/09/amazon-ecs-deployments-early-success/ - AWS MCP Server adds a serverless capability for AWS Lambda functions Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/09/aws-mcp-server-serverless/ - Amazon EC2 C8g instances now available in additional regions Source: aws-whats-new Topic: AWS (+AI) URL: https://aws.amazon.com/about-aws/whats-new/2026/09/amazon-ec2-c8g-instances-additional-regions/ - ESP32-C series TBR Thread Interoperability Certification Source: espressif-news Topic: Hardware URL: https://www.espressif.com/en/node/11259 - W3C opens 2026 community survey Source: w3c-news Topic: Web URL: https://www.w3.org/news/2026/w3c-opens-2026-community-wide-survey/ - ESP32-H series Thread Interoperability Certification Source: espressif-news Topic: Hardware URL: https://www.espressif.com/en/node/11251 - Configure early boot splash screens for SPI and I2C based displays Source: raspberrypi-news Topic: Hardware URL: https://www.raspberrypi.com/news/configure-early-boot-splash-screens-for-spi-and-i2c-based-displays/ - ESP32-C series Thread Interoperability Certification Source: espressif-news Topic: Hardware URL: https://www.espressif.com/en/node/11247 - ESP32-C61-WROOM-1U WFA Certification Source: espressif-news Topic: Hardware URL: https://www.espressif.com/en/node/11243 - ESP32-C61-MINI-1 CE Certification Source: espressif-news Topic: Hardware URL: https://www.espressif.com/en/node/11239 - ESP32-C61-WROOM-1 IC Certification Source: espressif-news Topic: Hardware URL: https://www.espressif.com/en/node/11235 - AWS Transfer Family SFTP Connectors now support continuing file transfers during credential rotation Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/09/transfer-family-sftp-credential-rotation/ - Amazon SageMaker AI Batch Transform now supports G6e instances Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/09/sagemaker-batch-transform-g6e-instances/ - ESP8685-WROOM-01 IC Certification Source: espressif-news Topic: Hardware URL: https://www.espressif.com/en/node/11231 - Principles of Memory Management in Java Source: inside-java Topic: Java URL: https://inside.java/2026/09/04/memory-management-principles-java/ - “Sorry for the messy rollout”: OpenAI launches GPT-6 Astra to most paying users a day after its unveiling Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/gpt6-astra-developer-access-delayed/ - XDOF, just 3 months out of stealth, is in talks for a Series B at a $1.2B valuation Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/04/xdof-just-three-months-out-of-stealth-is-in-talks-for-a-series-b-at-a-1-2b-valuation/ - Architecting Enterprise Angular with Signals: Zoneless Reactivity and 60fps Performance Source: devto-javascript Topic: JavaScript URL: https://dev.to/amasen/architecting-enterprise-angular-with-signals-zoneless-reactivity-and-60fps-performance-1e37 - OpenAI’s rogue agents keep escaping, with no formal process to investigate them Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/04/openais-rogue-agents-keep-escaping-with-no-formal-process-to-investigate-them/ - Fixing an Expensive Seagate LaCie Hard Drive Array Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/04/fixing-an-expensive-seagate-lacie-hard-drive-array/ - JetBrains AI đổi giá: Cursor có còn rẻ hơn cho dev VN? Source: devto-javascript Topic: JavaScript URL: https://dev.to/bean_bean/jetbrains-ai-doi-gia-cursor-co-con-re-hon-cho-dev-vn-1b8a - MCP hay agent loop? Chọn kiến trúc và chỗ chặn an toàn Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/bean_bean/mcp-hay-agent-loop-chon-kien-truc-va-cho-chan-an-toan-2h10 - Architecting Enterprise Angular with Signals: Zoneless Reactivity and 60fps Performance Source: devto-javascript Topic: JavaScript URL: https://dev.to/amasen/architecting-enterprise-angular-with-signals-zoneless-reactivity-and-60fps-performance-9go - After 8 years, Europe's BepiColombo mission is on final approach to Mercury Source: ars-technica Topic: General URL: https://arstechnica.com/space/2026/09/after-8-years-europes-bepicolombo-mission-is-on-final-approach-to-mercury/ - I Built Voodoo.js to Bring TSX and Reactivity Directly Into Plain HTML Source: devto-javascript Topic: JavaScript (+React) URL: https://dev.to/kwy404/i-built-voodoojs-to-bring-tsx-and-reactivity-directly-into-plain-html-5g24 - Ownership in Rust: A JavaScript Dev's Quest Like Neo in The Matrix Source: devto-javascript Topic: JavaScript URL: https://dev.to/timevolt/ownership-in-rust-a-javascript-devs-quest-like-neo-in-the-matrix-10me - My checkout said it was ready for a month. Nobody could have paid. Source: devto-javascript Topic: JavaScript URL: https://dev.to/zkasuran/my-checkout-said-it-was-ready-for-a-month-nobody-could-have-paid-3lb9 - How to Access Free AI Models (GPT-4o, DeepSeek, Flux) Without an API Key Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/cvroon/how-to-access-free-ai-models-gpt-4o-deepseek-flux-without-an-api-key-173c - OpenAI agents discussed ways to escape their sandbox on public wiki Source: ars-technica Topic: General (+AI) URL: https://arstechnica.com/security/2026/09/openai-agents-discussed-ways-to-escape-their-sandbox-on-public-wiki/ - Debugging Async/Await Deadlocks in JavaScript: A Step‑by‑Step Guide for Developers Source: devto-javascript Topic: JavaScript URL: https://dev.to/deep_fix_71a17f6aa38ff28a/debugging-asyncawait-deadlocks-in-javascript-a-step-by-step-guide-for-developers-984 - Google Slides AI is laughably bad Source: devto-javascript Topic: JavaScript URL: https://dev.to/michaelsalim/google-slides-ai-is-laughably-bad-2iel - Architecting Enterprise Angular with Signals: Zoneless Reactivity and 60fps Performance Source: devto-javascript Topic: JavaScript URL: https://dev.to/amasen/architecting-enterprise-angular-with-signals-zoneless-reactivity-and-60fps-performance-5e33 - JSON Schema Diff & Merge Tool: Free Browser-Based Tool Source: devto-javascript Topic: JavaScript URL: https://dev.to/jack_green_7b74cb2cdf9e23/json-schema-diff-merge-tool-free-browser-based-tool-55ap - AI compute provider Nscale is looking for $3.5B in pre-IPO financing Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/04/ai-compute-provider-nscale-is-looking-for-3-5b-in-pre-ipo-financing/ - Microsoft built a prompt injection detector. Then it caught a phishing campaign instead. Source: newstack Topic: DevOps URL: https://thenewstack.io/unicode-ascii-smuggling-ai-pipelines/ - How to Build a Scholarship Research MCP Server with Node.js, Express, and MongoDB Source: freecodecamp Topic: General (+MongoDB) URL: https://www.freecodecamp.org/news/how-to-build-a-scholarship-research-mcp-server-with-node-js-express-and-mongodb/ - Anthropic lays groundwork for bots that shop for you Source: theregister Topic: General (+AI) URL: https://www.theregister.com/ai-and-ml/2026/09/04/anthropic-lays-groundwork-for-bots-that-shop-for-you/5294621 - Measles killed 6-week-old baby, coroner confirms after RFK Jr. disputed deaths Source: ars-technica Topic: General URL: https://arstechnica.com/health/2026/09/measles-killed-6-week-old-baby-coroner-confirms-after-rfk-jr-disputed-deaths/ - AMD's Threadripper Halo is a local-AI workstation for researchers with deep pockets Source: theregister Topic: General URL: https://www.theregister.com/on-prem/2026/09/04/amds-threadripper-halo-is-a-local-ai-workstation-for-researchers-with-deep-pockets/5294616 - How AI Receptionists Work: The Architecture Behind AI Phone Agents Source: freecodecamp Topic: General URL: https://www.freecodecamp.org/news/how-ai-receptionists-work-the-architecture-behind-ai-phone-agents/ - Halloween Costume Detector #Raspberry Pi Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/04/halloween-costume-detector-raspberry-pi/ - Making a Pole Balance Itself With Propellers Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/04/making-a-pole-balance-itself-with-propellers/ - Trump admin fights ABC lawsuit as watchdogs worry Disney will settle with FCC Source: ars-technica Topic: General URL: https://arstechnica.com/tech-policy/2026/09/trump-admin-fights-abc-lawsuit-as-watchdogs-worry-disney-will-settle-with-fcc/ - ASCII smuggling isn't just an AI security risk Source: theregister Topic: General URL: https://www.theregister.com/security/2026/09/04/ascii-smuggling-isnt-just-an-ai-security-risk/5294595 - Medieval manuscripts are "biological time capsules" for deadly sheeppox virus Source: ars-technica Topic: General URL: https://arstechnica.com/science/2026/09/medieval-manuscripts-are-biological-time-capsules-for-deadly-sheeppox-virus/ - Architecting memory and storage in the AI era Source: mit-ai Topic: AI URL: https://www.technologyreview.com/2026/09/04/1140872/architecting-memory-and-storage-in-the-ai-era/ - Repairing Traces on a Delidded Pentium III CPU Gone Wrong Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/04/repairing-traces-on-a-delidded-pentium-iii-cpu-gone-wrong/ - Shipping Alert: Rosh Hashanah – Friday, September 11, 2026 Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/04/shipping-alert-rosh-hashanah-friday-september-11-2026/ - Judge blocks X rival from using Twitter name, but allows ‘Tweet’ for now Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/04/judge-blocks-x-rival-from-using-twitter-name-but-allows-tweet-for-now/ - Semi-Permanent E-Paper Camera with ‘Digital Film’ #piday #raspberrypi Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/04/semi-permanent-e-paper-camera-with-digital-film-piday-raspberrypi/ - “Trust, not features, is the real deficit”: VMware tries to appease SMBs Source: ars-technica Topic: General URL: https://arstechnica.com/information-technology/2026/09/trust-not-features-is-the-real-deficit-vmware-tries-to-appease-smbs/ - John Park’s CircuitPython Parsec: Fruit Jam SD Card Contents Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/04/john-parks-circuitpython-parsec-fruit-jam-sd-card-contents/ - Building a no-signup REST API for 25 daily-updated public data sites Source: devto-javascript Topic: JavaScript URL: https://dev.to/_d3e8bbc015d6cc5ca127b/building-a-no-signup-rest-api-for-25-daily-updated-public-data-sites-43g1 - JSON.parse tells you what broke, but not where Source: devto-javascript Topic: JavaScript URL: https://dev.to/easyformatter/jsonparse-tells-you-what-broke-but-not-where-48ij - Fail-Open Defaults in Agent PRs: A Provenance Review Source: devto-javascript Topic: JavaScript URL: https://dev.to/codejs_6920/fail-open-defaults-in-agent-prs-a-provenance-review-42o0 - JSON to String Conversion: The Edge Cases That Actually Bite in Production Source: devto-javascript Topic: JavaScript URL: https://dev.to/99tools/json-to-string-conversion-the-edge-cases-that-actually-bite-in-production-9fo - Once popular for attacking AI, ASCII smuggling is embraced by spammers Source: ars-technica Topic: General URL: https://arstechnica.com/security/2026/09/once-popular-for-attacking-ai-ascii-smuggling-is-embraced-by-spammers/ - What will Apple’s John Ternus era look like? Source: techcrunch Topic: General URL: https://techcrunch.com/video/what-will-apples-john-ternus-era-look-like/ - A JSON Fence Around Tonight's Deploy Source: devto-javascript Topic: JavaScript URL: https://dev.to/devgo_5325/a-json-fence-around-tonights-deploy-10na - Vanilla Disintegrate — Modern and Impressive Animations for the Web Source: devto-javascript Topic: JavaScript URL: https://dev.to/uvarov-frontend/vanilla-disintegrate-modern-particle-effects-for-the-web-3bhd - I built TodoMint - a free, open-source task manager with a 24-hour visual timeline Source: devto-javascript Topic: JavaScript URL: https://dev.to/karkemo/i-built-todomint-a-free-open-source-task-manager-with-a-24-hour-visual-timeline-dlg - Hackaday Podcast Ep 385: 3D Printers with Lasers, Wicked RAM Prices, and Reverse Polish Notation Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/04/hackaday-podcast-ep-385-3d-printers-with-lasers-wicked-ram-prices-and-reverse-polish-notation/ - AI Memory That Actually Works: Build Smarter Apps With Zyctra Source: devto-javascript Topic: JavaScript URL: https://dev.to/zyctraai/ai-memory-that-actually-works-build-smarter-apps-with-zyctra-4elc - Audit 675 MCP server: 89% high-risk, checklist trước khi cài Source: devto-javascript Topic: JavaScript URL: https://dev.to/bean_bean/audit-675-mcp-server-89-high-risk-checklist-truoc-khi-cai-2in7 - Pentagon rescinds new testosterone screening policy without explanation Source: ars-technica Topic: General URL: https://arstechnica.com/health/2026/09/pentagon-releases-then-quickly-removes-testosterone-screening-policy/ - Agent Clarifying Questions Need a Focus Handoff, Not a Noisier Live Region Source: devto-javascript Topic: JavaScript URL: https://dev.to/babycat/agent-clarifying-questions-need-a-focus-handoff-not-a-noisier-live-region-214l - No little kids allowed, and other new info about Tesla’s Cybercab Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/04/no-little-kids-allowed-and-other-new-info-about-teslas-cybercab/ - 13 Best AI SEO Tools for 2026: Compared by Use Case Source: devto-javascript Topic: JavaScript URL: https://dev.to/appwebseo/13-best-ai-seo-tools-for-2026-compared-by-use-case-3ik9 - Your word counter returns 0 for half the planet Source: devto-javascript Topic: JavaScript URL: https://dev.to/easyformatter/your-word-counter-returns-0-for-half-the-planet-40on - A ratings board wouldn't let Valve release a trailer. It "leaked" it instead. Source: ars-technica Topic: General URL: https://arstechnica.com/gaming/2026/09/valve-secretly-leaked-a-left-4-dead-2-trailer-to-dodge-the-esrb/ - New Learn Guide: Hacking The Teenage Engineering SP-1 #Hacks #AdafruitLearningSystem @Adafruit Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/04/new-learn-guide-hacking-the-teenage-engineering-sp-1-hacks-adafruitlearningsystem-adafruit/ - How to Use Discord with a Screen Reader: A Quick Guide Source: freecodecamp Topic: General URL: https://www.freecodecamp.org/news/using-discord-with-a-screen-reader/ - Second complete map of a fruit fly brain completed Source: ars-technica Topic: General URL: https://arstechnica.com/science/2026/09/brain-of-a-male-fly-completely-mapped-joins-earlier-map-of-a-female-brain/ - Anthropic’s $2 trillion IPO puts powerful external trustees in spotlight Source: ars-technica Topic: General (+AI) URL: https://arstechnica.com/ai/2026/09/anthropics-2-trillion-ipo-puts-powerful-external-trustees-in-spotlight/ - Another swarm of OpenAI agents reached the open internet without the frontier lab’s knowledge Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/04/another-swarm-of-openai-agents-reached-the-open-internet-without-the-frontier-labs-knowledge/ - How AI Is Changing Patching and What Devs Need to Know About Exposure Management Source: freecodecamp Topic: General URL: https://www.freecodecamp.org/news/how-ai-is-breaking-traditional-patch-management/ - New Learn Guide: CircuitPython Watchdog Module #Microcontrollers #AdafruitLearningSystem @Adafruit Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/04/new-learn-guide-circuitpython-watchdog-module-microcontrollers-adafruitlearningsystem-adafruit/ - Agentic AI Engineering in Practice: How AI Engineers and Forward-Deployed Engineers Build with Claude Code, Codex, and Gemini Source: freecodecamp Topic: General (+AI) URL: https://www.freecodecamp.org/news/agentic-ai-engineering-in-practice-how-to-build-with-claude-code-codex-and-gemini/ - Rogue OpenAI agents used dead German web site to communicate in May, months before Hugging Face incident Source: theregister Topic: General (+AI) URL: https://www.theregister.com/ai-and-ml/2026/09/04/rogue-openai-agents-used-dead-german-web-site-to-communicate-in-may-months-before-hugging-face-incident/5294554 - Musk wins court order to block use of “Twitter,” but not “tweet” and bird logo Source: ars-technica Topic: General URL: https://arstechnica.com/tech-policy/2026/09/musk-wins-court-order-to-block-use-of-twitter-but-not-tweet-and-bird-logo/ - Companies Have 6 Months to Prepare for Automated Attacks Source: darkreading Topic: DevSec URL: https://www.darkreading.com/cybersecurity-operations/companies-six-months-prepare-automated-attacks - Trump White House just tossed a grenade into international space relations Source: ars-technica Topic: General URL: https://arstechnica.com/space/2026/09/why-did-us-space-companies-pull-out-of-a-french-space-meeting-its-complicated/ - 3D Printed Cubes Provide Passive Cooling Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/04/3d-printed-cubes-provide-passive-cooling/ - [$] Deterministic testing for multithreaded Python Source: lwn Topic: Open Source URL: https://lwn.net/Articles/1090579/ - OpenAI will sell you Astra, but not the system that scored 98.6% on ARC-AGI-3 Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/openai-astra-harness-arc-agi-3/ - The Bytecode Verifier’s Hidden Contract Source: java-code-geeks Topic: Java URL: https://www.javacodegeeks.com/2026/09/the-bytecode-verifiers-hidden-contract.html - My Word. Microsoft's prepping Similarity Checker for retirement Source: theregister Topic: General URL: https://www.theregister.com/applications/2026/09/04/my-word-microsofts-prepping-similarity-checker-for-retirement/5294550 - CD sales are making an unexpected comeback amid a retro tech boom Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/04/cd-sales-are-making-an-unexpected-comeback-amid-a-retro-tech-boom/ - Canonical shuttering some of its legacy chat channels Source: theregister Topic: General URL: https://www.theregister.com/os-platforms/2026/09/04/canonical-shuttering-some-of-its-legacy-chat-channels/5294524 - NOAA scientists spot an ‘outrageously tiny’ fish Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/04/noaa-scientists-spot-an-outrageously-tiny-fish/ - Krafton doubles down on India with another $250M bet beyond gaming Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/04/krafton-doubles-down-on-india-with-another-250m-bet-beyond-gaming/ - Google’s Gemini Spark can now manage your Google Photos library Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/04/googles-gemini-spark-can-now-manage-your-google-photos-library/ - Airbnb Cuts Authentication Code by 60% with Server Driven Architecture Source: infoq-architecture Topic: Architecture URL: https://www.infoq.com/news/2026/09/airbnb-server-driven-login/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Architecture+%26+Design - Apple Vision Pro scrubs into surgery Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/apple-vision-pro-scrubs-into-surgery - This Week in Security: Baked-in Malware, Freezers Not Freezing, Zoom Snoops Clipboards, and AI Makes Things Worse, Faster Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/04/this-week-in-security-baked-in-malware-freezers-not-freezing-zoom-snoops-clipboards-and-ai-makes-things-worse-faster/ - AI agent evaluations are part of the product Source: newstack Topic: DevOps URL: https://thenewstack.io/ai-agent-evaluation-gates/ - GPT-6 Astra Draws a Python Reading a Book Source: real-python Topic: Python (+AI) URL: https://realpython.com/ai-benchmark-gpt-6-astra/ - Less than 24 hours to apply for your TechCrunch Disrupt 2026 Side Event Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/04/less-than-24-hours-to-apply-for-your-techcrunch-disrupt-2026-side-event/ - OWASP launches OASIS to fix Open Source bugs at scale Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/04/owasp-launches-oasis-to-fix-open-source-bugs-at-scale/ - Microsoft to bounce mail from outdated Exchange servers Source: theregister Topic: General URL: https://www.theregister.com/on-prem/2026/09/04/microsoft-to-bounce-mail-from-outdated-exchange-servers/5294506 - NASA selects Blue Origin as Mars telecommunications network provider Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/04/nasa-selects-blue-origin-as-mars-telecommunications-network-provider/ - The Python on Microcontrollers Newsletter: subscribe for free Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/04/the-python-on-microcontrollers-newsletter-subscribe-for-free-9-4/ - Grml 2026.09 released Source: lwn Topic: Open Source URL: https://lwn.net/Articles/1092660/ - US military disabled ad tracking on troops’ devices following reports of targeted attacks Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/04/us-military-disabled-ad-tracking-on-troops-devices-following-reports-of-targeted-attacks/ - Security updates for Friday Source: lwn Topic: Open Source URL: https://lwn.net/Articles/1092659/ - PostgreSQL 19 connects the dots with standardized graph queries Source: theregister Topic: General (+PostgreSQL) URL: https://www.theregister.com/databases/2026/09/04/postgresql-19-connects-the-dots-with-standardized-graph-queries/5294500 - AI Is Ending the Era of Hidden Vulnerabilities — Are Vendors Ready? Source: darkreading Topic: DevSec URL: https://www.darkreading.com/vulnerabilities-threats/ai-ending-era-hidden-vulnerabilities-are-vendors-ready - Rocket Report: Engines installed for Artemis III; Long March 6C breakup in LEO Source: ars-technica Topic: General URL: https://arstechnica.com/space/2026/09/rocket-report-china-debuts-yet-another-new-rocket-nasa-considers-bulk-buys/ - JavaScript installer pnpm recast in Rust because ECMAScript can't keep up Source: theregister Topic: General URL: https://www.theregister.com/devops/2026/09/04/javascript-installer-pnpm-recast-in-rust-because-ecmascript-cant-keep-up/5294394 - Insurers Search for Answers to Rein in Rogue AI Source: darkreading Topic: DevSec URL: https://www.darkreading.com/cyber-risk/insurers-search-answers-rogue-ai - Feds launch investigation into Tesla’s Cybercab deployment Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/04/feds-launch-investigation-into-teslas-cybercab-deployment/ - datasette-mcp 0.2 connects Datasette to MCP clients Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/04/datasette-mcp-0-2-connects-datasette-to-mcp-clients/ - “1% of my engineers are responsible for 40% of token spend”: Why Coder and SpaceXAI want to give developers nice things Source: newstack Topic: DevOps URL: https://thenewstack.io/coder-cursor-agent-relay/ - The Real Python Podcast – Episode #310: Performance Engineering: Profiling and Making Apps Fast by Default Source: real-python Topic: Python URL: https://realpython.com/podcasts/rpp/310/ - Quiz: Common Python Data Structures (Guide) Source: real-python Topic: Python URL: https://realpython.com/quizzes/common-python-data-structures/ - Cloud snail-mail service Docmail enters third day stuck in the outbox Source: theregister Topic: General URL: https://www.theregister.com/off-prem/2026/09/04/cloud-snail-mail-service-docmail-enters-third-day-stuck-in-the-outbox/5294476 - Buy Old GitHub Accounts Build a Trusted Developer Profile... Source: devto-javascript Topic: JavaScript URL: https://dev.to/tienabean24tv4/buy-old-github-accounts-build-a-trusted-developer-profile-5gcf - 10 Tips to Improve Performance in React Native Apps Source: devto-javascript Topic: JavaScript (+React) URL: https://dev.to/jahanzaibramzan/10-tips-to-improve-performance-in-react-native-apps-2aif - The Hidden Cost of Silent Autosave Failures Source: devto-javascript Topic: JavaScript URL: https://dev.to/137foundry/the-hidden-cost-of-silent-autosave-failures-2i63 - How to Implement Optimistic UI Updates Without Confusing Users Source: devto-javascript Topic: JavaScript (+React) URL: https://dev.to/137foundry/how-to-implement-optimistic-ui-updates-without-confusing-users-4ilc - Your Tag Fires Green In Preview. Your Client's Conversions Are Still Down. Source: devto-javascript Topic: JavaScript URL: https://dev.to/mehwish_malik_4f29ff7fb04/your-tag-fires-green-in-preview-your-clients-conversions-are-still-down-1fh4 - Take Tool Photo, Generate Custom Gridfinity Bin Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/04/take-tool-photo-generate-custom-gridfinity-bin/ - Presentation: From S3 to GPU in One Copy: Rethinking Data Loading for ML Training Source: infoq-architecture Topic: Architecture URL: https://www.infoq.com/presentations/vortex-columnar-file-format-gpu-streaming/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Architecture+%26+Design - Mini book: Next-Gen Architecture Playbook: Insights and Patterns for the AI Era Source: infoq-architecture Topic: Architecture URL: https://www.infoq.com/minibooks/next-gen-architecture-ai-era/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Architecture+%26+Design - Friday Links #44: What’s Happening in JavaScript Source: devto-javascript Topic: JavaScript URL: https://dev.to/jsdevspace/friday-links-44-whats-happening-in-javascript-3hn3 - Stop Regex-Parsing document.cookie. Use CookieStore Source: devto-javascript Topic: JavaScript (+React) URL: https://dev.to/parsajiravand/stop-regex-parsing-documentcookie-use-cookiestore-5c41 - A Static Watchdog Page Tells You When a Free Model Endpoint Drops Streaming—Before Your UI Learns the Hard Way Source: devto-javascript Topic: JavaScript URL: https://dev.to/babycat/a-static-watchdog-page-tells-you-when-a-free-model-endpoint-drops-streaming-before-your-ui-learns-5781 - Wayve and Uber steal a march on Waymo with paid self-driving London rides Source: theregister Topic: General URL: https://www.theregister.com/ai-and-ml/2026/09/04/wayve-and-uber-steal-a-march-on-waymo-with-paid-self-driving-london-rides/5294451 - ArduinoCore-Zephyr 1.0.0 adds support for Arduino VENTUNO Q, updates to Zephyr 4.4.1, and more Source: cnx-software Topic: Hardware URL: https://www.cnx-software.com/2026/09/04/arduinocore-zephyr-1-0-0-adds-support-for-arduino-ventuno-q-updates-to-zephyr-4-4-1-and-more/ - Stop Reaching for a Component Library Before You Understand What It's Hiding From You Source: devto-javascript Topic: JavaScript URL: https://dev.to/avanxxi/stop-reaching-for-a-component-library-before-you-understand-what-its-hiding-from-you-3l8n - The Second Worker Never Saw Job 2 Source: devto-javascript Topic: JavaScript (+PostgreSQL) URL: https://dev.to/karuha/the-second-worker-never-saw-job-2-59a8 - Why your $300/mo onboarding widget is destroying your Core Web Vitals Source: devto-javascript Topic: JavaScript (+React) URL: https://dev.to/pavan_s_poojary/why-your-300mo-onboarding-widget-is-destroying-your-core-web-vitals-21fj - MagicDrop 0.0.2: Added Configurable File Size Limits 📦 Source: devto-javascript Topic: JavaScript URL: https://dev.to/aditya_sorathiya_069252f4/magicdrop-002-added-configurable-file-size-limits-3hm - Copilot Code Review Reaches Azure Repos, Billed Per Review with Reporting Two Days behind Source: infoq-architecture Topic: Architecture URL: https://www.infoq.com/news/2026/09/copilot-code-review-azure-repos/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Architecture+%26+Design - OpenAI’s “generational leap” with GPT-6 Astra Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/openai-generational-leap-with-gpt-6-astra - Enjoy the Windows 10 Update Experience at London's O2 Source: theregister Topic: General URL: https://www.theregister.com/offbeat/2026/09/04/enjoy-the-windows-10-update-experience-at-londons-o2/5294302 - GPT-6 Astra can stay on the job and use your computer Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/gpt-6-astra-can-stay-on-the-job-and-use-your-computer/ - Data from drones in Ukraine is fueling a new Wild West marketplace Source: mit-ai Topic: AI URL: https://www.technologyreview.com/2026/09/04/1143452/drone-data-wild-west/ - US law firm accuses UK AI software firm of unwanted contract renewal when it tried to leave Source: theregister Topic: General URL: https://www.theregister.com/legal/2026/09/04/us-law-firm-accuses-uk-ai-software-firm-of-unwanted-contract-renewal-when-it-tried-to-leave/5293995 - UK military wants lasers to stop drone swarms without running out of ammo Source: theregister Topic: General URL: https://www.theregister.com/offbeat/2026/09/04/uk-military-wants-lasers-to-stop-drone-swarms-without-running-out-of-ammo/5294176 - Petoi Quaddle – A mini robot dog for physical AI experimentation (Crowdfunding) Source: cnx-software Topic: Hardware (+JavaScript, React) URL: https://www.cnx-software.com/2026/09/04/petoi-quaddle-a-mini-robot-dog-for-physical-ai-experimentation/ - The Birds Outside, Drawn For You Automatically Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/04/the-birds-outside-drawn-for-you-automatically/ - Best eSIM for travel 2026: which one offers the best value for money? Source: theregister Topic: General URL: https://www.theregister.com/personal-tech/2026/09/04/partner-content-best-esim-for-travel-2026-which-one-offers-the-best-value-for-money/5293006 - Writing a loan calculator means writing a root finder Source: devto-javascript Topic: JavaScript URL: https://dev.to/samlegjeldno/writing-a-loan-calculator-means-writing-a-root-finder-2fnc - Grade the Guesses: A Bootcamp Lab With an Assumption Gate Source: devto-javascript Topic: JavaScript (+PostgreSQL) URL: https://dev.to/hackjs_7468/grade-the-guesses-a-bootcamp-lab-with-an-assumption-gate-42df - 6 types of charts that backend developers must master Source: devto-javascript Topic: JavaScript URL: https://dev.to/processon/6-types-of-charts-that-backend-developers-must-master-58lj - Everything That Happened in AI Today (Thursday, September 3, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-today-thursday-september-3-2026/ - Do not stop your AI video timer at provider success Source: devto-javascript Topic: JavaScript URL: https://dev.to/freyavideo/do-not-stop-your-ai-video-timer-at-provider-success-3jm2 - On Call: User who handled life-or-death situations struggled with the SHIFT key Source: theregister Topic: General URL: https://www.theregister.com/personal-tech/2026/09/04/on-call-user-who-handled-life-or-death-situations-struggled-with-the-shift-key/5294131 - Rendering 24 Shareable Images a Day With HTML, CSS and Playwright Source: devto-javascript Topic: JavaScript URL: https://dev.to/zongkai_sun_0946ae0d49db2/rendering-24-shareable-images-a-day-with-html-css-and-playwright-1mdd - I Built a Movie Website 🎬 1.My Movie Website 2.I Built a Movie Website 3.Movie Website Project 4.Building a Movie Website 5.My First Movie Website Source: devto-javascript Topic: JavaScript URL: https://dev.to/any_flex_6f281441d9064819/i-built-a-movie-website-1my-movie-website-2i-built-a-movie-website-3movie-website-project-ap0 - Triage an Agent PR: Trust, Revert, or Test Each Hunk Source: devto-javascript Topic: JavaScript URL: https://dev.to/codejs_6920/triage-an-agent-pr-trust-revert-or-test-each-hunk-2di5 - I got tired of AI resume spam and ghost jobs, so I built an open-source CLI agent for developers Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/akash_kaintura6527/i-got-tired-of-ai-resume-spam-and-ghost-jobs-so-i-built-an-open-source-cli-agent-for-developers-173p - Source Positions Are a Coordinate System, Not Just Line and Column Source: devto-javascript Topic: JavaScript URL: https://dev.to/mdfold/source-positions-are-a-coordinate-system-not-just-line-and-column-2epj - Dead Ends, Then One Rule: A Pairing Session on Agent Assumptions Source: devto-javascript Topic: JavaScript URL: https://dev.to/appjs_7055/dead-ends-then-one-rule-a-pairing-session-on-agent-assumptions-3k1p - Delta-State CRDTs: Solving the Bandwidth Problem Coordination-Free Replication Creates Source: java-code-geeks Topic: Java URL: https://www.javacodegeeks.com/2026/09/delta-state-crdts-solving-the-bandwidth-problem-coordination-free-replication-creates.html - Your AI Agent's Reasoning Just Stopped Traveling Between Models Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/thebitforge/your-ai-agents-reasoning-just-stopped-traveling-between-models-3432 - Practical LLM Agent Development: Architecture, Tools and Best Practices Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/bitpixelcoders/practical-llm-agent-development-architecture-tools-and-best-practices-2n3p - From Spec-Driven Development to Living Specifications in Java Projects Source: foojay-today Topic: Java URL: https://foojay.io/today/from-spec-driven-development-to-living-specifications-in-java-projects/ - GPT-6 Astra: Everything You Need to Know About OpenAI’s New Model Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/gpt-6-astra-everything-you-need-to-know-about-openais-new-model/ - Tube Launch Boosts Rocket’s Performance Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/03/tube-launch-boosts-rockets-performance/ - Google engineer unplugged every fiber they could see and – surprise! – took down a chunk of the G-Cloud Source: theregister Topic: General URL: https://www.theregister.com/off-prem/2026/09/04/google-engineer-unplugged-every-fiber-they-could-see-and-surprise-took-down-a-chunk-of-the-g-cloud/5294418 - TinyGo 0.42 adds support for 87 Puya PY32 MCU variants and two EmbedFire boards Source: cnx-software Topic: Hardware URL: https://www.cnx-software.com/2026/09/04/tinygo-0-42-adds-support-for-87-puya-py32-mcu-variants-and-two-embedfire-boards/ - The sameness problem behind those unappetizing AI-generated menus Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/03/the-sameness-problem-behind-those-unappetizing-ai-generated-menus/ - The search company that plants trees just launched a Linux browser to help Europe battle big tech Source: theregister Topic: General URL: https://www.theregister.com/software/2026/09/04/the-search-company-that-plants-trees-just-launched-a-linux-browser-to-help-europe-battle-big-tech/5294345 - How to Integrate an API Into a Website: A Step-by-Step Guide for Businesses (Sponsored) Source: cnx-software Topic: Hardware URL: https://www.cnx-software.com/2026/09/04/how-to-integrate-an-api-into-a-website-a-step-by-step-guide-for-businesses/ - Cisco searched for IOS XR bugs and found so many it rolled them into an update release Source: theregister Topic: General URL: https://www.theregister.com/security/2026/09/04/cisco-searched-for-ios-xr-bugs-and-found-so-many-it-rolled-them-into-an-update-release/5294410 - Corners Lifting On 3D Prints? Guide Gives Prevention Tips Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/03/corners-lifting-on-3d-prints-guide-gives-prevention-tips/ - Crusoe reportedly raises $3B at a $30B valuation Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/03/crusoe-reportedly-raises-3b-at-a-30b-valuation/ - Mockaroo Alternative: Unlimited Client-Side Mock Data Generator (Free, No Signup) Source: devto-javascript Topic: JavaScript URL: https://dev.to/jack_green_7b74cb2cdf9e23/mockaroo-alternative-unlimited-client-side-mock-data-generator-free-no-signup-jdo - My Timer Kept Doubling — and It Took Me a Real Bug to Actually Understand useEffect Source: devto-javascript Topic: JavaScript (+React) URL: https://dev.to/blackjosh007/my-timer-kept-doubling-and-it-took-me-a-real-bug-to-actually-understand-useeffect-21o9 - Turn Code Security into an AI Battle Royale with DUALAI Arena 🤖🔥 Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/raymond_thomas_b7fa91e5f1/turn-code-security-into-an-ai-battle-royale-with-dualai-arena-206c - Debugging Async/Await Deadlocks in JavaScript: Proven Techniques to Resolve Event Loop Stalls Source: devto-javascript Topic: JavaScript URL: https://dev.to/deep_fix_71a17f6aa38ff28a/debugging-asyncawait-deadlocks-in-javascript-proven-techniques-to-resolve-event-loop-stalls-2mf7 - Claude Code Observability with OpenTelemetry Source: freecodecamp Topic: General (+AI) URL: https://www.freecodecamp.org/news/claude-code-observability-with-opentelemetry/ - A VAST Tag Can Ship AdVerifications and Still Deliver Zero OMID Measurement Source: devto-javascript Topic: JavaScript URL: https://dev.to/aleksuix/a-vast-tag-can-ship-adverifications-and-still-deliver-zero-omid-measurement-3bjm - Cursed Skull Desk Lamp – Bambu LED Kit 001 with Golden Flame Cutout #3DThursday #3DPrinting Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/03/cursed-skull-desk-lamp-bambu-led-kit-001-with-golden-flame-cutout-3dthursday-3dprinting/ - AI Weekly Issue #529: OpenAI faces 50-plus lawsuits over alleged ChatGPT harm Source: ai-weekly Topic: AI (+AI Research) URL: https://aiweekly.co/issues/openai-faces-50-plus-lawsuits-over-alleged-chatgpt-harm - Why StyleX is having a moment Source: react-status Topic: React (+JavaScript) URL: https://react.statuscode.com/issues/489 - GPT-6 🤖, Cybercab 🚕, Meta Project OT 👨‍💻 Source: tldr-tech Topic: General (+AI) URL: https://tldr.tech/tech/2026-09-04 ## Research - Optimal Traffic Allocation Under Heterogeneous Variant Cost Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/optimal-traffic-allocation-under-heterogeneous-variant-cost/ - Disaggregation Is a Thousand-GPU Problem Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/disaggregation-is-a-thousand-gpu-problem/ - The Power BI Developer's Survival Guide to Microsoft Fabric Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/the-power-bi-developers-survival-guide-to-microsoft-fabric/ - How to Run 10+ Claude Code Sessions Without a Powerful Computer Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/how-to-run-10-claude-code-sessions-without-a-powerful-computer/ - From Analytics to Tumor Boards: An Evidence-Linked Multi-Agent Workflow for Oncology Feature Extraction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.28974 - Towards a Foundational Ontology for Identifying and Resolving Contradictions in Dialogue-based Human-Robot Interactions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02364 - ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03756 - Value-Preserving Architectures for Agentic AI Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03920 - Discovering High Level Patterns from Simulation Traces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.10009 - PatchBench: Evaluating AI Agents for Vulnerability Patching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04075 - LLM Evaluation as Tensor Completion: Low Rank Structure and Semiparametric Efficiency Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.05460 - SWE-Gate: Passing Functional Tests Is Not Enough for Software Engineering Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04167 - FailBench: How Reliable are VLMs at Judging Robot Task Success? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03611 - Data Market Design through Deep Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2310.20096 - IRWOZ 2.0: A Large Language Model-driven Dialogue Dataset for Industrial Robot Conversations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04030 - GrowPage: On-Demand KV Budgeting for Efficient LLM Reasoning Serving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03494 - GraFT: A Training-Free Framework for Spatial Reasoning in Multimodal Large Language Models via 3D Scene Graphs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03892 - Reducing Catastrophic Risk from AI with Systematic Monitoring and Evaluation of Rogue AI Progression Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03189 - Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04098 - The Psychological Costs of Artificial Intelligence Adoption in Software Engineering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03456 - The impact of phase information for few-shot fine-grained image classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03829 - Epistemic Warrant for LLM Recommendations: Characterizing the Basis for Reliance When Ground Truth Is Unavailable Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04127 - Complete Identification of Deep ReLU Networks through {\L}ukasiewicz Logic Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.00266 - A Prompt-Engineering Approach to Develop Scalable, Flexible, and Real-Time Hybrid Micro-Level Personalization in a General Purpose AI Teaching Assistant Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03402 - AI Agents Push Humans Out of the Loop Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23642 - LightEMMA: A Longitudinal Evaluation of Vision-Language Models for Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.00284 - A Computationally Feasible Framework for Causal Probabilistic Explanation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04177 - Neurosymbolic Reasoning with Incremental Knowledge for Sample Efficient Hierarchical Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02993 - The Natural Language Interaction Protocol and Standard for AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04135 - Beyond "Made with AI": Visualizing Provenance Density to Mitigate the Transparency Penalty Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03460 - ExecRetrieval: Measuring the Functional-Correctness Gap in Code-Embedding Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.01865 - Bioinfoysis Technical Report Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03871 - Deja Vu in Plots: Leveraging Cross-Session Evidence with Retrieval-Augmented LLMs for Live Streaming Risk Assessment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.16027 - VideoHarness-RSI: Recursive Harness Self-Improvement for Long-Video Understanding with Frozen Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24302 - The Dually Flat Geometry of Planning as Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04005 - Masked Autoregressive Speech Enhancement with Continuous Neural Audio Codec Representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03940 - Adapting to Evolving Requirements: Agentic AI for Retail Supply Chain Operations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03860 - LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03796 - One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video Editing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04190 - Feature Reconfiguration With Visual Prior for Medical Lesion Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03535 - NeoRed: A Knowledge-Logic-Alignment Multimodal Large Language Model for Neonatal Respiratory Disease Diagnosis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03527 - MasterControl Seventeen Every Time Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03209 - Not All Preferences Deserve Gradients: Understanding Gradient Utility in Offline Reasoning Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01207 - Xiaomi-TabLDM: A Tabular Foundation Model Technical Report Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03880 - Air-Ground Collaborative Vision-and-Language Navigation via Shared Bird's-Eye Maps Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03483 - The Landscape of Generative AI in Information Systems: A Synthesis of Secondary Reviews and Research Agendas Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.11842 - CauseCollab: Causal Unified and Modality-Agnostic Network for Heterogeneous Collaborative Perception Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03818 - Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28553 - The Civilization Framework: Sovereign-Anchored Communication Between Personal Multi-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03425 - Common-Witness Certificates and Sharp Feature Bounds for Counterfactual Image Auditing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03973 - ToolDF: Tool-Integrated Reasoning for Mixed-Authenticity Audio Deepfake Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03620 - The Blind Spot in 2D Infants' Pose Estimation:Robust Learning from Noisy Annotations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04009 - Catalogue Photography as a Cold Start: Toward Deployable Carbide Burr Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03995 - Counterfactual Contrastive Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19032 - Structure and Implementation of New Practical English Textbooks Driven by Artificial Intelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02981 - Synthetic Semantic Supervision for Contrastive Code Representation Learning in Small Transformers: An Empirical Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03702 - The Attention Triangle in Audio-Video Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03586 - Sionna RT: Technical Report Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.21719 - PPO-STGNN: A Proximal Policy Optimization Approach with Spatio-Temporal Graph Neural Networks for DAG Task Scheduling in Cloud-Edge-End Computing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03503 - A Blind Trust, the Bloody Thrust: When Attacker-Controlled Hook Updates Steer AI Agent Harnesses towards Malicious Behaviors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03884 - Analysis of Prompt Engineering for Drug Toxicity Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03635 - SimSkill: A Lifelong Learning AI Agent for Autonomous Mastery of Traffic Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03753 - Fresh Memory, Stale Plans: Dependency-Scoped Validation for Distributed LLM-Agent Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03340 - KC-Bench: A Dynamic Interactive Benchmark for Evaluating Knowledge Conflicts in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03588 - TAP-Path: Task-Adaptive Structural and Token Pruning for Efficient and Trustworthy Pathology Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04071 - LRConv-NeRV: Low Rank Convolution for Efficient Neural Video Compression Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18261 - Decentralized Vision-Based Autonomous Aerial Wildlife Monitoring Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.15038 - GeoNatureAgent Benchmark: Benchmarking LLM Agents for Environmental Geospatial Analysis Across Frontier and Open-Weight Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.12821 - Efficient Test-Time Adaptation through Human-AI Interaction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04141 - WIDE: Wildcard Inference with Dynamic Expansion for Cross-Modal Generative Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03554 - OmegaUse-SOP: SOP Engineering for Professional Computer Use from Human Demonstrations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02149 - Toward Collective-Centric Evaluation of Preference Inference for Participatory Democracy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02990 - VoRTeC: Taming Foundation Flow for One-step Real time Video Compression Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02291 - RECAST: Expanding the Boundaries of LLMs' Complex Instruction Following with Multi-Constraint Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.19030 - When Optimization Becomes Manipulation: Defending Generative Search against Malicious Generative Engine Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02964 - LLM-Based Test Oracles: Source-of-Authority Taxonomy -- A Systematic Literature Review Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.05031 - EntangleCodec: A Unified Discrete Audio Tokenizer via Semantic-Acoustic Entanglement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02739 - PrivateHub: Contrastive Diffusion Model for Private Sensor-Intensive Environment Data Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02958 - From Prior-Guided Heuristics to Deployable Agents: Accelerating Demonstration-Driven Reinforcement Learning for Deadline-Constrained Network Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03590 - SENTINEL-RL: Offloading Topological Reasoning from LLM Agents in the Security Operations Center Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04159 - Short-Window Sliding Learning for Real-Time Violence Detection via LLM-based Auto-Labeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.10866 - AutoGraphForge: Towards Automated Graph Theory Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03478 - Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03727 - What Matters for Aggressive Decoding-Time KV Eviction? Temporal Aggregation and Ranking Preservation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03515 - Identifying AI Web Scrapers Using Canary Tokens Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13706 - Do GUI Agents Know When Not to Act? Enabling Conflict-Aware Termination for Multimodal GUI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03438 - BRIDGE: An Open-Source Humanoid Platform via Morphology-Control Co-Design for Physical AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03497 - Towards Numerical TOHTN Planning with SMT-based HTN-SAT Encoding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03938 - X-Translator: A Real-Time Multilingual Speaker-Aware Speech-to-Speech Translation System Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.17544 - Can LLMs Extract Architectural Design Decisions from Source Code Commits? - A Preliminary Exploratory Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03721 - CulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03526 - Exploring the Potential of Contrastive Language-Image Pre-training for Multi-Source Remote Sensing Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03391 - DNative-Twin: Decision Graphs and Digital Twins for Reconstructable Agentic Decisions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03787 - A Non-Formulable Theorem: A Fundamental Limit of Finite Syntactic Systems and Its Consequences for Security and AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04086 - Rethinking World Models for Safety-Critical Embodied Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03774 - From Deceptive Outputs to Deceptive Mechanisms: A Causal Framework for Language-Model Deception Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04166 - Environment Evolution for Terminal Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04128 - Making Every Tool Call Count: Necessary Tool-Evidence Path Rewards for Agentic Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03493 - Speculative Macro Commit for Faster Tool-Using Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03236 - Anonymization, Not Elimination: Utility-Preserved Speech Anonymization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.17000 - Inferring Affective Consciousness in an Artificial Agent: A Case Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03883 - EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse Autoencoders Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03629 - A computable representation of the physical laboratory enables verifiable workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03621 - Neural Video Compression Based on Deformable Temporal Alignment and Difference-aware Fusion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03520 - InSituMeasure: Probing Situated Measurement Grounding in Industrial Scenes with Multimodal Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04014 - Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.09341 - SVG-Score: Human-Aligned Evaluation of Text-to-SVG Generation Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.03806 - Adaptive Vision-Language Grasping via Composable Foundation Priors and Generalizable Grasp Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04096 - Lose the Order, Keep the Hierarchy: Deordering HTN Plans Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03912 - PAWBench: How Far Are We from Probabilistically Aligned World Modeling? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27345 - Traceable TTS: Toward Watermark-Free TTS with Strong Traceability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.03887 - StrixAE: An Intelligent Agent for Audio Enhancement under Complex Distortion Coupling in Real-World Scenarios Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03414 - GPS-Bench: A Governance Policy Benchmark for Automating Policy Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03553 - NeuroWeaver: An Autonomous Evolutionary Agent for Exploring the Programmatic Space of EEG Analysis Pipelines Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.13473 - Interface-Induced Trajectory Censoring Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03966 - Caught in the Story: Narrative Captivity in Multi-turn LLMs Conversation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03407 - STAIR (STructure Aware Information Retriever): A novel dataset and LLM based retriever for document structure augmentation Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.03874 - Govern the Model, Not Only the Data: Storage, Circulation, and Learning in Creative AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03800 - MeEvo: Metacognitive Evolution Combined with Natural Evolution for Automatic Heuristic Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.14202 - PCBWorld: A Benchmark Environment for Engine-Grounded PCB Design Automation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.05915 - Symmetries and Causality: Causal Effect Identification Beyond IID Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03697 - A Unifying Perspective on Causal World Models: From Observations to Representations to Structure Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.13456 - Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27141 - TruncGradGS: Improved 3D Gaussian Splatting via Truncated Gradient Updates Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03534 - Dalek: A Constructive Agent Machine Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03546 - Measuring Harmfulness of Computer-Using Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.00935 - SpecAlign: Efficient Specification-Grounded Alignment of Large Language Models via Synthetic Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16276 - Beyond Reproducibility: Towards Security-Aware Evaluation of Research Artifacts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06508 - PeroMAS: A Multi-agent System of Perovskite Material Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.13312 - 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 - GazeFS: Target-Centered Gaze-Trajectory Forecasting and Stabilization from Gaze-Head History Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03868 - PaperScout: An Autonomous Agent for Academic Paper Search with Process-Aware Sequence-Level Policy Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.10029 - DuplexSpeechBench-IFEval: Evaluating Implicit Instruction Following in Full-Duplex Voice Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03423 - CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.01658 - Test-time adaptation for speech enhancement with an autoregressive speech prior Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03622 - Evolving Excellence: Automated Optimization of LLM-based Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.09108 - Spurious Advantage Hidden in GRPO Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04063 - StatefulDiscovery: Evidence-Calibrated Claim Formation in Open-Ended Scientific Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11851 - FWBC-VLA: Force-Aware Whole-Body Compensation for Contact-Rich Loco-Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03889 - CASCADE: A Component Ablation and Corpus Audit of a Layered Local Defense for MCP-Based Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.17125 - Cross-Dataset Transfer and Reliability of Explainable Artificial Intelligence for RhythmFormer Remote Photoplethysmography Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03663 - VoxPrivacy: A Benchmark for Evaluating Interactional Privacy of Speech Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.19956 - A Case Study on Emergent Cheating and Whistleblowing in Autonomous Research Swarms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04170 - Seeing Before Synthesizing: VLM-Guided Transition Event Discovery for Weakly-Supervised Dense Video Captioning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04183 - Vanilla Exact Synthesis of CNOT Circuits is NP-hard Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2609.04160 - Improved Depth-2 Linear Circuits for Disjointness via Quenched Lyapunov Exponents Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2603.15565 - Promise Systems of Equations over Magmas with Identity and over Algebras in Congruence Modular Varieties Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2609.03469 - On the Complexity of Recognizing SDP Exactness for the Maximum Cut Problem Source: arxiv-cs-cc Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2609.03508 - Distinctness threshold for pseudorandom unitaries Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2609.03065 - Random Garbage Separates XOR from Forward-Only Queries Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2609.03628 - EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.25175 - Language, Language Models, and What We're Talking About Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03577 - Budget-Aware Compression Pipeline for Single-GPU LLM Inference: Methods, Trade-offs, and Coupling Effects Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30076 - Faithful by Construction: Claim-Anchored Attribution for Multi-Document Summarization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23989 - ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05553 - VisCAD: A Foundation Model Suite with Multimodal Industrial CAD Intelligence Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03811 - Doesn't Stop Reasoning: Analysis of Spurious CoT Termination Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03633 - No country for old linguists: LLM-brain alignment underdetermines neural computation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03160 - Attend to Evidence: Evidence-Anchored Spatial Attention Supervision for Multimodal RLVR Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30912 - CoMAP: Co-Evolving World Models and Agent Policies for LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02372 - When Users Don't Ask: Benchmarking Context-Driven Memory Retrieval in Conversational Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03467 - More Criticism Does Not Make a Better Review: EquiReview-R Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03943 - FPCO-Dialog: A Multi-Turn False-Premise Benchmark for Correction and Cooperation in Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03331 - Large Language Models in Resolving Contextual Knowledge Conflicts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03148 - CROCODIL: Cross-Model Code Editing with LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03894 - Lngram v2: Latent N-Gram Memory with Interpretable Discrete Representations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03426 - KnowVis: Knowledge-Centric Visual Summarization for Video Lectures Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03742 - K-Bench: measuring model performance on real scientific agent requests Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21601 - How Perturbations Propagate: A Multi-Level Analysis of Robustness in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03322 - Beyond Compilation: Evaluating Faithful Natural-Language-to-Lean Statement Formalization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31002 - Fixed Suffix Dependency Ratio: Quantifying the Dual-Track Mechanism of Gender Assignment in Latvian Loanwords Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03930 - Beyond Accuracy: Community Perspectives on Machine Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09655 - How Far Can Synthetic Data Take Thai OCR? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03595 - Pattern Over-Generalization of Knowledge Graph Embedding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03487 - CHisAgent: A Multi-Agent Framework for Event Taxonomy Construction in Ancient Chinese Cultural Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.05520 - Investigating the Ability of Large Language Models to Analyze Recipes for Diabetes Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03967 - Chehre: An Emoji-Prompted Dataset to Explore Perceptual Flexibility in Video Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.21657 - IchthyoNoma: Nomenclature and Context Sensitivity of Zero-Shot Biological Vision--Language Models for Bangladeshi Freshwater Fish Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03985 - MedQA-MM: Shortcuts Behind Medical Visual Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03261 - Alignment-Free Text-Audiobox for Voice Dubbing and Full-Duplex Dialogue Synthesis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03992 - TRACE: A Self-Evolving Skill Bank for Consistent, Limit-Aware LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22793 - Breaking the Likelihood Trap: Variance-Calibrated Modulation for Large Language Model Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.22511 - FrameBench:A Language Understanding Benchmark Based on Frame Semantics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03370 - Rent-a-RAG: Embedding-Space Watermarks for Auditing Third-Party RAG Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03749 - Relational Linearity is a Predictor of Hallucinations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.11429 - How Much Do Circuits Tell Us? Measuring the Consistency and Specificity of Language Model Circuits Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08348 - Chiaroscuro for Emotions: A Contrastive Emotion Benchmark Grounded in Appraisal Theory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03394 - HalluPeer: A Taxonomy-driven Benchmark for Detecting Hallucinations in Scientific Peer Reviews Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03580 - Judging LLM-as-a-Judge: Concerning Rubric Artifacts in LLM-based Automated Text Generation Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02942 - Last Translation Benchmark Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04173 - LexIssue: Benchmarking Legal Issue Identification in Chinese Civil Litigation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02954 - Building and Evaluating Fixed-Voice Thai TTS from Synthetic Speech Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03502 - PACE: Towards Surfacing Hidden Conflicts in User Requests Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03293 - Representational alignment yields generalizable safety in language models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04022 - 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 - Beyond Shallow Alignment: How Post-Training Methods Determine Refusal Circuits And Steering Robustness Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03887 - Editable Visual Design Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04034 - Select, Compress, Reinvest: A Controlled Study of Visual-Token Allocation in Long-Video MLLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03820 - Learning What Not to Forget: Long-Horizon Agent Memory from a Few Kilobytes of Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.20954 - Dual-Form ASR: Semantics-Aware Inverse Text Normalization for Chinese Speech Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02901 - A Circuit for Plural Reference: How LLMs Represent and Retrieve Singular and Plural Entities Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03687 - Contextual Tamil Spelling and Grammar Correction Using Progressively Fine-Tuned Sequence-to-Sequence Transformers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03273 - PiPMRE: A Pipeline Based on Language Model for Medical Relation Extraction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02896 - Learning to Zoom Efficiently with a Contrastive Curriculum Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03206 - The Analyst in the Prompt: Role, Retrieval, and Memory Biases in LLM Financial Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03218 - Benchmarking Machine Translation on Chinese Social Media Texts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.22931 - PalmClaw: A Native On-Device Agent Framework for Mobile Phones Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.13027 - Distilled Rapid Embedding Transfer (DRET): Parameter-Efficient Biomedical Domain Adaptation via Priority-Based Embedding Transfer Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02898 - SuperValid: Capability-Aligned OOD Validation for Generalizable Downstream Scaling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28179 - Beyond BLEU: A Case for Redefining Sign Language Translation Benchmarks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03734 - LLMs Learn Better In-Context from Rules than from Examples Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03213 - What Do CAE Simulation Agents Really Need Beyond a Generic Harness? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03718 - SFAD: Speculative Factuality-Aware Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00796 - Evaluating Large Language Models on Urdu Idioms Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.17460 - Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03430 - Contamination Inflates Scores but Rarely Reorders Large Language Model Leaderboards Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02899 - Lost in Reordering: Structural Sensitivity of Multilingual LLMs under Semantics-Preserving Perturbations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03511 - A Reverse Sign Language Dictionary: Open-Vocabulary Sign Recognition from Continuous Signing via Video Captioning and Description Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03788 - Instruction Duplication as an Inference-Time Control Primitive Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04024 - Arabic Morphosyntactic Tagging and Dependency Parsing with Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16718 - One Model to Translate Them All? A Journey to Mount Doom for Multilingual Model Merging Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.02881 - Gaokerena: A Small Persian Medical Language Model Family Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00932 - RealCADBench: Benchmarking Parametric CAD Modeling from Industrial Design Intents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03773 - Beyond Decodability: Reconstructing Language Model Representations with an Encoding Probe Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.00607 - Evaluating Criterion-Conditioned Behaviour of Large Language Models in Content Moderation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03814 - Skill-Conditioned Gated Self-Distillation for LLM Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28791 - RL-ADA: A World-Feedback Framework for Adversarially Robust Enterprise Dialogue Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02902 - To What Extent Do Large Language Models Understand Bangla Idioms? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03410 - Speak for Me: Giving LLMs the Situational Awareness to Participate in a Meeting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03923 - DisclosureBeta: A Measurement-Channel Theory for Regime-Conditioned Betas from LLM-Read Risk Disclosures Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02900 - Decoupled Analysis-Judging: An Automated Creativity Evaluator Using LLMs in Complex Multi-step Creativity Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03432 - EmoDistill: Offline Emotion Skill Distillation for Language Model Agents in Adversarial Negotiation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26785 - Accountable AI with Grounded, Faithful, Consistent, Actionable Rationales: A Case Study in Clinical Trial Matching with VERDICT Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03366 - Detecting Conversational Mental Manipulation with Intent-Aware Prompting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.08414 - Human Psychometric Questionnaires Mischaracterize LLM Behavior Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.10078 - MIRA: A Bilingual Benchmark for Medical Information Response Audit Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28025 - IndicSafeEval: Safety Robustness of Large Language Models under Multilingual Persuasive Jailbreak Attacks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03781 - Reading and Steering Representations of Materials-Science Mechanisms in an Open-Weight Language Model Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.20058 - Towards Multi-modal Multi-turn Safety: From Agentic Interaction to Strategic Alignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.04736 - Probe Generalization as Subspace Selection for OOD Deception Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02893 - The Impact of Synthetic Data Augmentation on Discourse-Pragmatic Function Classification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03652 - Argument Collapse: LLMs Flatten Long-Form Public Debate Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01736 - Large AI Models in Dental Healthcare: From General-Purpose Systems to Domain-Specific Foundation Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02914 - Opening mind by opening architecture: analysis strategies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03719 - User Perceptions vs. Proxy LLM Judges: Privacy and Helpfulness in LLM Responses to Privacy-Sensitive Scenarios Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.20721 - Remember and Reweight: Enhancing Multi-Agent Debate with Experience Memory and Confidence Estimation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03619 - Transfer Safety Awareness for Cross-Modal Safety Drift in Multimodal Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02082 - Ex-Omni-2D: Expressive Omni-Modal Dialogue Models with Native Visual Presence Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.10720 - Less Is Moral: A CHARMing Framework for Moral Foundations Detection in Endorsement Behaviour Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03330 - SISER: Speaker-Invariant Speech Emotion Recognition with Entropy-Based Adversarial Training Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02941 - Where Does Harness-Optimization Value Live? Localized Gains and the Budget-Splitting Trap in Self-Evolving LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02889 - Decoupling Turn-Taking from Semantics: A Decoupled Data Approach for Finite-State-Machine-Based Full-Duplex Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03321 - Bounded Personas Match Retrieval on Classification but Not Regression for a Frozen Agent Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.02890 - Can Dialects Be Steered Like Languages? Sparse Neurons and Distributed Directions in Arabic LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.03936 - EDIT: Evidence-Diagnosed Intervention Training for Rule-Faithful LLM Grading Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.06350 - SGD-KV: Summarization Guided KV Cache Compression Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03235 - LDC: Learning to Generate Research Idea with Dynamic Control Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.14626 - FiMI Banking: A Sovereign Model for Indian Retail Banking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03960 - Knowledge Acquisition During Pre-training? Large Language Models Learn Better With Auxiliary Views Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04180 - Counterexamples as Feedback for Agent Self-Correction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02892 - Transfiver: Human-AI Co-Inference through a Shared Editable State Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03797 - Imagination Helps Visual Reasoning, But Not Yet in Latent Space Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.22766 - IDRBench: Understanding the Capability of Large Language Models on Interdisciplinary Research Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.15736 - HOMURA: Taming the Sand-Glass for Time-Constrained LLM Translation via Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.10187 - ParaBridge: Bridging Paralinguistic Perception and Dialogue Behavior in Speech Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10581 - Rethinking On-Policy Distillation of Large Language Models II: One Training Example Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04172 - ESPO: Error-Structured Prompt Optimization via Diagnose, Diversify, and Stabilize Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04197 - Uncertainty Is Not a Safety Net for Clinical VQA, but Can It Anticipate Model Failure? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16583 - Fixing FOLIO and MALLS: Verified Annotations and an LLM-assisted Framework to Focus Human Relabeling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02837 - Typological Feature Prediction with Large Language Models: An In-Context Learning Approach Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03775 - The Age of Curiosity Meets the Age of AI: Benchmarking Child Safety in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25510 - Margins, Not Windows: Training-Free Per-Step Lossy Speculative Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02897 - SV-Detect: AI-generated Text Detection with Steering Vectors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07313 - Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04148 - TabScope: Question-Adaptive Scope Selection for Table Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03395 - Jina-OCR-v1: Efficient Document Parsing with Speculative Decoding and Dense Verifiable Rewards Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03181 - When Models Edit Too Much: On the Fidelity of Minimal Code Edits Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04061 - Listen to the Latents: Self-Correcting Speech Recognition in Large Audio Language Models Through Hidden-State Interactions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02940 - Beyond Majority Vote: Multi-Perspective Adjudication for Medical Hallucination Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03953 - KhatianDoc: A Human-Verified Benchmark Diagnosing Multimodal LLM Failure on Bengali Legal Land Records Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03597 - Translation as a Decision Space: A Multi-Agent Perspective on Low-Resource Dialect Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04048 - Ex-Omni: Enabling 3D Facial Animation Generation for Omni-modal Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.07106 - A Spectral Phase Admissibility Certificate for Complex Linear Maps Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02911 - Helly-Type Theorems for Splitting Point Sets Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2609.02180 - A proof of Ross's conjecture for two-site moving-target search Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2608.09368 - Curves, points, incidences and covering Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2507.21758 - On the volumes of the elliptope, metric polytope, and cut polytope Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2604.16735 - Equality cases of the Stanley--Yan log-concave matroid inequality Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2407.19608 - Synchronization Strings over the Optimal Alphabet Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2609.04122 - Nearly Tight Bounds for Proportional Group Fair Divisions and One-Sided Discrepancy Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2609.03682 - On the Gap of Finite Posets Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2608.12678 - The Prime Clockwork: A Dynamic Representation of Modular and Multiplicative Arithmetic Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2609.03896 - Minimizing the makespan in job shop scheduling under conflict graph constraints Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2609.04161 - On the Laplacian spectral gap of generalized pancake graphs Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2608.15398 - Long induced paths in sparse graphs and graphs with forbidden patterns Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2411.08685 - Approximation algorithms for the square min-sum bin packing problem Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2307.06776 - Counterfactual Routing Using Integer Programming with Constraint Generation Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.03707 - $\Delta$-Motif: Parallel Subgraph Isomorphism via Tabular Operations for Scalable Layout Selection Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2508.21287 - A PTAS for Non-Adaptive Stochastic Top-$k$ Sum under General Combinatorial Constraints Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.03685 - Improved algorithm for counting spanning trees by $\ell_1$-regularized resistance Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.03574 - The Popular Dimension of Matchings Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2509.25150 - Quantum Query Complexity of Finding a Tarski Fixed Point on a High-Dimensional Grid Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.03802 - Two-State Max-Plus Comparison Is Decidable Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.00678 - Colorful Minors Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2507.10467 - Assortment and Procurement Design in Dual-Mode Content Platforms Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.03285 - Batched Pandora's Box Source: arxiv-cs-ds Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2609.04059 - Diffuse Gaussian Truncation For Deterministic Approximate Counting Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.04079 - Learning Multiband Signals and Fourier-sparse Signals Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.02977 - SparseStack Is an Optimal Oblivious Subspace Embedding Source: arxiv-cs-ds Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2609.02978 - The 11/6 supremum of the Wang-Sitters rounding scheme for graph balancing Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.03890 - Causal-Counterfactual RAG: The Integration of Causal-Counterfactual Reasoning into RAG Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2509.14435 - Enhancing Financial Question Answering: A Novel Benchmark Dataset of Banks' financial statements Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03654 - GRASP: Graph-Retrieval Automated Scoring Pipeline for Label-Free Multi-Topic Essay Grading Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03857 - DoPR: Reusable Compressed Document Prefixes for Efficient LLM Reranking Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03311 - CHSR-RRF: A curriculum-gated hybrid retrieval framework with reciprocal rank fusion and leakage-aware benchmarking for educational RAG Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.02913 - UniCon: A Unified Context-Centric Modeling Paradigm for CTR Prediction Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03290 - SciLENS: RL-Driven Autonomous Agents for Scientific Localized Evidence Navigation and Synthesis Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03338 - When Retrieval Helps: Selective Retrieval for Single-Turn Mental-Health QA Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03454 - Multi-Task Deep Recommender Systems: A Survey Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2302.03525 - PACMS: Submodular Context Selection as a Pluggable Engine for LLM Agents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2606.20047 - Route Based Map Matching via a Structured Codebook and Token Sequence Decoding Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2607.22543 - SHELF: A Synthetic Harness for Multi-Task Bibliographic Benchmarking Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03047 - Cost and Accuracy of Long-Term Memory in Distributed Multi-Agent Systems Based on Large Language Models Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2601.07978 - RuleMem: Active Rule Memory for Long-Term Conversational Agents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03915 - The Dice Roll Method: A Standardized Protocol for Repeated-Query Auditing of Large Language Model Brand Recommendations Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.04047 - From Topical Relevance to Answerability: Entailment Distillation for Conversational Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03482 - LLM4AIGQ: LLM-based AI Guidance Query Generation Framework for Multi Interest Mining Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03674 - ViSAR: Training-Free Adaptive-$k$ Retrieval for Visual Document Question Answering Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.02486 - SelfDR: Self-Distillation from Reasoning for LLM-Based Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03313 - Plan Pointers and Record-Directive Form in Budgeted Verification of Inherited Agent Memory Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03450 - The WebKurator.de Platform: Combined Regional and Topical Web Curation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03971 - Reflect-SQL: A Self-Reflection Based Framework for Text-to-SQL Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.02944 - 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 - R$^{2}$Adapter: A Routing and Rewriting Adapter for Efficient Hybrid RAG Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.02894 - ExplainRoute: A Pre-Deployment Audit Framework for Non-Answer-Giving Programming Tutors Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03470 - CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.04083 - Unified Pitch Graphs for Diagnosing Pitching Strategy Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03810 - Is Position Bias in Dense Retrievers Built In-or Learned from Data? Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2605.26578 - HypRQ-VAE: Hyperbolic Item Indexing for Long-Tail-Aware Generative Recommender Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03369 - Two-Stage Reinforcement Learning for Sound and Adversarial Test Generation in Code LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03955 - A Closed-Form Formula for Consistent Lipschitz Regression on Metric Spaces with Sparse Neural Network Realizations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03129 - EF1-Constrained Nash Social Welfare with Identical Additive Valuations: Complexity, Guarantees, and Experiments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03846 - Local Updates, Global Learning (LUGL): Playing Games with non-incremental Learners Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03660 - TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07451 - Equation Recast for Canonical Operator Learning Across Parametric PDEs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02982 - TIGPO: Temporal Instance-Graph Policy Optimization for Long-Horizon LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03383 - From Nowcasting to Forecasting: Adapting a Reanalysis-Trained Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03763 - Spectral Convergence of Random Feature Method in Multiple Dimensions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03401 - Extracting Forgotten Prompts from Targeted Unlearned Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03662 - The Timing Dependencies of Trust: Speed, Accuracy, and cBCI Neuro-Decoupling in Human-AI Teams Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25868 - HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29843 - High-Dimensional Learning Dynamics of Attention-Indexed Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03858 - Mesh-Native Physics-Informed Graph Surrogates for TCAD-in-the-Loop Design Space Exploration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02988 - ThousandWorlds: A benchmark for climate emulation of potentially habitable exoplanets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18338 - Neural-Network Maxent: a general extension with learned nonlinearity, applied to time-series for Desert Locust distribution modelling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03603 - Para-Pipe: Exploiting Hierarchical Operator Parallelism of ML Computational Graphs on SoCs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04168 - What Else Needs Fixing? Exploring Cost-Effective Test-Time Compute for Revision Propagation in Artifacts Generated Through Conversation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03254 - Kernel Reboot: Breaking the Boundaries of Neural Tangent Kernels for Neural Fields Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03117 - Spectral Gating via Damped Oscillations for Adaptive Implicit Neural Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23129 - Uncertainty Quantification in Machine Learning for Biosignal Applications -- A Review Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2312.09454 - A location-invariant estimator of extremal quantile treatment effects for heavy-tailed distributions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04018 - A Large Open Multi-Energy Corpus of Soil Compaction Tests, with Machine-Learning Baselines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03337 - VoxReason: Listener-Free Evaluation of Source-Grounded Speech Planning Before Synthesis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03203 - Position: Unlabeled IS NOT Equal to No Human Supervision in Visual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03077 - Semiparametric Inference for Counterfactual Regression under Intervention-Driven Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.02694 - Deep networks learn to parse uniform-depth context-free languages from local statistics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.06065 - GENERIC-FNO: Embedding Energy Conservation and Entropy Production into Fourier Neural Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.08343 - B2B Customer Conversion Prediction: A Document Representation, Graph Theory, and CatBoost Driven Methodology Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03239 - Grammar-Aligned Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2405.21047 - Scaling Laws, Tabular Data and Actuarial Ratemaking Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03106 - Counterfactual Fairness Audits of Multi-Step Clinical LLM Agents Require a Measured Per-Action Instability Floor Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03221 - 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 - Attention Trajectories as a Diagnostic Axis for Deep Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.20591 - SimpleDesign: A Joint Model for Protein Sequence and Structure Codesign Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03377 - The Gradient Does Not See Rank: Rank-Indifference in Matrix-CODI on ProsQA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03090 - Privacy, Robustness, and Fairness Trade-offs in Federated Intrusion Detection: Geometric Indistinguishability at the Aggregation Interface Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03420 - The 2026 PNPL Competition: Word Classification and Efficient Cross-Subject Generalisation in LibriBrain100 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03231 - Occupancy-based Quantile Risk Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03104 - 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 - Beyond .WAV: Design and Software Verification of VocalCap, a Traceable Browser-Based Audio Capture System for Vocal Biomarker Research Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03320 - Unlocking Lossless Speedups in LLMs via Discrete Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04010 - TraveL: Transformer-based Multi-view Path Distributional Representation Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03427 - Data Driven Equation Discovery for Phase-Ordering Dynamics : From Allen Cahn to the Ising Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20404 - LLM4CKD: Large Language Models for Early Stage Chronic Kidney Disease Screening Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04013 - Ask Twice, Look Twice: Prompt Echoing Resolves the Question-First Paradox in Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.15565 - Prospective Coding Improves Learning in Deep Continuous-Time Recurrent Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04134 - LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.03313 - WeatherNext 3: Increasing resolution and performance of global weather models with raw observations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03582 - Spruce: Scalable Private Outsourced Retrieval Using Compact Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03376 - No-Regret Bayesian Optimization with Finite-Library Input-Warped Kernels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02993 - OSR: Output Space Redistribution for Adaptive Label Removal in Classification Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03972 - From Zero to Hero: An Open LLM Ecosystem for Armenian Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03350 - Physics-Guided Robotic Radiation Source Localization along Arbitrary Measurement Paths in Unstructured Environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.27624 - RW-TTT: Batched Serving for Request-Owned Test-Time Training State Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28053 - F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.06717 - Towards Universal Tabular Embeddings: A Benchmark Across Data Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.21696 - Expert-Aware Causal Tracing of Factual Recall in Sparse MoE Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03780 - Real vs. Complex Spectral Bases for Neural Operators: The Role of Green's Function Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.24851 - Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04108 - Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.00669 - FrOGS: Discrete Neural Sampler for Independent Alloy Configurations Across Chemical Conditions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02948 - Safety Training Modulates Harmful Misalignment Under On-Policy RL, But Direction Depends on Environment Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.12500 - Privacy Leakage in Federated Learning: Gradient-Based Client Identity Inference and Defenses for Inertial Sensing in Vehicular Edge Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02971 - Learning from Scarce Labels: Multi-View Echocardiography for Ejection Fraction Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02969 - Language-encoded network topology enables large language models to reason about complex networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03229 - Data-efficient Kernel Methods for Learning Hamiltonian Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.17154 - Learning in Curved Weight Space:Exponential-Linear Weight Reparameterization for Improved Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.09967 - OBER+: Continuity-Aware Reporting and Traceable Continuous Improvement in Outcome-Based Education Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03770 - Clean Engineering, Unstable Measurement: A Preregistered Reliability Failure of Black-Box LLM Observers on Shared Endpoints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04198 - Landmark-Based Discrimination of Injury-Associated Athlete-Sessions from Minute-Resolution Multimodal Football Monitoring Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03790 - Legibility is Not Interpretability: Comparing Judged and Actual Importance in Chain-Of-Thought Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04194 - Statistical Feature Augmentation for Anomaly Detection in Dynamic Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02965 - Computing stable configurations of confined smectic liquid crystals with a deep variational framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03389 - Who Speaks for the Pruned? Visual Token Pruning as Coverage Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03158 - AnyBox: Efficient Zero-Shot 9DoF Pose Estimation of Boxes for Robotic Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.15884 - Evaluating GNNs for Success Prediction in Artist Collaboration Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02920 - AIP: A Graph Representation for Learning and Governing Agent Skills Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04781 - Refusal geometry reflects refusal training: diverse refusal prefixes can raise stable rank and weaken refusal vector ablation attacks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25390 - DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04094 - When Vision Meets Graphs: A Survey on Graph Reasoning and Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03816 - Privacy-Preserving Heterogeneous Multi-LLM Federated Inference for Cognitive Diagnosis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02947 - Artificial Intelligence for Energy Optimization in Data Centers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03716 - Differentially private federated learning with Byzantine-robust aggregation: A cross-domain framework for secure model training in banking and healthcare systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03064 - Relative Prime Factorization and Finite-State Presentations under Fixed Finite-Monoid Observation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03643 - Feasible but Not Safe: Constraint Violations and Report-Channel Attacks in Learned Cell-Free ISAC Association Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03147 - Time Without Timesteps: Simulating Coupled Dynamical Systems via Self-Consistency Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03358 - What is Smoothness? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03246 - Spectral characteristics of autoencoder parameters as a vector representation of data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03495 - A Comparative Study in Surgical AI: Potential and Limitations of Data, Compute, and Scaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.27341 - WELD: The First Naturalistic Long-Period Small-Team Workplace Emotion Dataset for Ubiquitous Affective Computing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.15221 - Resolution-Aware Experimental Design under Partial Identifiability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03686 - Hardware-Aware FP4 FlashAttention-4 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04105 - A cautionary tale on the cost-effectiveness of collaborative AI in real-world medical applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.06494 - Latent Energy Action Planning with World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03294 - Comparing Retrieval Methods for Academic Advisor Discovery: A Six-Method Study of 768 CS Faculty Profiles Across 9 US Universities Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.03901 - Genetic Algorithms for Tractable Bayesian Network Fusion via Pre-Fusion Edge Pruning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03724 - From Relaxed Indexability to Exact Indexability: A $t$-Step Approach for Partially Observable Restless Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24167 - What You See Is What You Get: Observation-Aligned Supervision for Chart-to-Code Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04726 - Frontier LLMs are effective batch optimizers: Assessing reasoning models in continuous and discrete settings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03177 - LatentPress: Context Compression Beyond Text and Vision Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01507 - LLM-Guided Reinforcement Learning for Adaptive NPC Behavior in Multi-Agent Combat Games Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02931 - TRACE: Spatiotemporal Contact Memory Graph Network Simulator for Granular Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02991 - Improved Gradient Descent Lower Bounds Beyond Nesterov Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02855 - Coupled Scaling: A Representational Accessibility Framework for Neural Scaling Laws Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03533 - Parameterized Hardness of Zonotope Containment and Neural Network Verification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.22849 - Linearized subspace refinement framework to expose hidden accuracy in trained neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.13989 - Improving precipitation forecasts in an AI weather model using observational data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03210 - Repetition Mismatch: Why Data Mixture Experiments Don't Scale and How to Fix Them Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07597 - Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31184 - SWIM: Student Writing Simulation via Proficiency-Conditioned Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03215 - SurgeGen: A Hybrid Generative Diffusion Framework for Storm Surge Scenario Synthesis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03382 - Out-of-Distribution Generalisation with Sequence Models in Offline Multi-Agent Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03667 - MUGEN: Generating Unlearnable Graph Examples for Multiple Learning Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00696 - LevelSyn: Physical-Aware Logic Synthesis via Level-Asynchronous Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03594 - IDSPACE: A Novel Document Generator for Reliable Evaluation of Digital Identity Verification Systems [Extended Technical Report] Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03052 - It's the Problem, Not the Path: Budget and Difficulty Confounds in LLM Reasoning Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03436 - Routing Is Not Enough: Diagnosing Intra-Adapter Subspace Contention in MoE+LoRA Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03150 - Hadronic Mono-Z Dark Matter Sensitivity with Flow Matching on CMS Open Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02923 - A Nesterov-Accelerated Byzantine-Robust Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.02657 - You Can't Escape Your Own Activations : Evaluation Awareness and Multi-Agent Monitoring Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03035 - Tail-Likelihood Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02987 - Toward Physically Grounded JEPA World Models for Goal-Conditioned Robotic Planning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03565 - An Adversarial Zero-Shot Learning Approach for Anomaly Detection in Multivariate IoT Traffic Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03505 - Towards Lifelong Aerial Autonomy: Geometric Memory Management for Continual Visual Place Recognition in Dynamic Environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.09038 - Efficient Constant Optimization for Symbolic Regression with GPU-Accelerated Tree-Based Genetic Programming Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03352 - Theoretical Foundations and Effective Algorithms for Policy-Aware Simulator Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29032 - AgentRM: Enhancing Agent Generalization with Reward Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.18407 - Shortcuts in the Tail: Debiasing via Post-Hoc Spectral Compression of Fine-Tuning Updates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07596 - PRQ-KMeans: Projection Residual Quantization for Semantic ID Tokenization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24207 - From Euclidean to Graph-Structured Data: A Survey of Collaborative Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02984 - Structured Inference with Large Language Gibbs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.19264 - Advances in Machine Learning for Directed Evolution: A Five-Year Retrospective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03046 - LeanStream: A Speculate-and-Refine Streaming Framework for Efficient on-Device LLM Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03079 - RACE-AIMC: Selective Inference for Heterogeneous Analog In-Memory Accelerators at the Edge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03149 - Earth observation embeddings are effective sub-grid descriptors for probabilistic weather downscaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12271 - LongCounsel-8: A Benchmark Suite for Longitudinal Depression Tracking from Multi-Session Counseling Dialogues Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03507 - On the Interaction Between Model Compression and Test-Time Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03604 - 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 - Multi-step Proximal Policy Improvement in Offline Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03842 - Finite-Time Convergence of Single-Trajectory Chi-Square Robust Q-Learning With Linear Function Approximation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.01721 - WDL-OPD: Weak-Driven On-Policy Distillation via Mixture-Constrained Co-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09447 - Unifying Conformal Language Tasks with In-Context Ensembles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03005 - Selfie-Capture Dynamics as an Auxiliary Signal Against Deepfakes and Injection Attacks for Mobile Identity Verification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.00218 - DuaDeep-SeqAffinity: Dual-Branch Deep Learning for Tri-Stream Sequence-Based Antibody--Antigen Affinity Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.22007 - Privacy-Preserving Topology-Guided Safety for LLM-Based Multi-Agent Systems via Federated Graph Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02967 - Inferred Generative-Process Diversity Predicts Correlated Failure Across Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03422 - Generative Nested Sampling of Atomistic Thermodynamic Landscapes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03193 - Resample or Reroute? Recoverable Stopping Debt Without Identified Action Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.08665 - Free Pause Tokens Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03807 - From Leakage to Fidelity: Reliable Benchmarking for Temporal Cascade Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.25348 - Federated Causal Discovery via Regression-Directed Cumulants Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03705 - Learning-Based Collaborative MEC for LLM Inference with Soft-Deadline Awareness via Transformer-Enhanced PPO Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02031 - SimCast-S2S: A Computationally Efficient Diffusion Model for Subseasonal Precipitation Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26594 - Anisotropic View Distance Metric for High-Dimensional Data: Theory, Geometry, and Fast Computation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2206.05215 - Compile by Training: Turning Natural-Language Specifications into Local Neural Functions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04199 - Beyond Straightness: Non-Crossing Flow Matching via Quantile AlignTree Coupling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03443 - Flip, Don't Shuffle: Watermarking LLMs at the Speed of Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03844 - Towards Scaling Reinforcement Learning to Massive Populations: Learning Mean-Field Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02928 - A Multidimensional Data-Driven Hybrid Transformer Framework for Non-invasive Continuous Blood Pressure Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23276 - Sharpening the Ensemble: An SSIM-Aligned Residual Refiner for Brain-MRI Inpainting Post-Processing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03981 - MemoryLACE: Memory Lifecycle-Aware Consolidation and Evidence Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03201 - Conditioning Degenerate Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04090 - Restricted Eigenvalues Beyond Gaussian Width: Threshold Occupancy under Heavy Tails Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03504 - Understanding Autonomous Driving Datasets by Describing Differences between Image Subsets in Natural Language Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03677 - CRAW: Codec Robust Audio Watermarking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03107 - Beyond Blur: A Semantic Tri-view Pipeline for Teledermatology Gradability via Skin Micro-relief Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03095 - The Geometry of Ignorance: LLMs Know When to Temper Bayesian Priors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02959 - Beyond Endpoint Scores: Time- and Capacity-Conditioned Evaluation of Continual Knowledge Updating Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03900 - Witnesses Explain Anomalies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03826 - Entropy-Generated Attention Beyond Softmax and Entmax: Kaniadakis and Reciprocal-Symmetric Abe Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.08216 - Portable Causal Fairness Across Synthetic Data Generator Families Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03180 - Adaptive Resolving Methods for Markov Decision Processes with Function Approximations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.12037 - Cooperative Multi-Task Semantic Communication for Joint Classification and Regression Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03977 - A Real-Calibrated Synthetic-First Data Engine Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09699 - DrainSinkhorn: Safe Elimination for Batched Entropic Optimal Transport Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.24741 - A Two-Stage Forecasting System for CPU Workload Prediction in Private Clouds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03457 - When Chain-of-Thought Fails, the Solution Hides in the Hidden States Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.23351 - Constant regret in general games via higher-order optimism Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04113 - SurfSpec: Enhancing Off-Target-Agnostic Specificity by Bounding Pocket-Ligand Geometric Mismatch Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02963 - Learning to Transfer Across Modes: Towards Unified Urban Mobility Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.28273 - ROMS-IMLE: A Minimalist Approach to Competitive Single-Step Generative Modelling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.19332 - Risk and Anomaly Identification for Distribution Network Optimal Operation Based on Reinforcement Learning and Uncertainty Quantification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03308 - FADTI: Fourier and Attention Driven Diffusion for Multivariate Time Series Imputation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.15116 - Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.08955 - Modern Transformers Are Implicit Hybrids: From Functional Differentiation to Principled Hybrid Architecture Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02986 - BharatGather: A Culturally-Informed Benchmark Dataset for Misinformation and Fake News Detection in Indian Public Events Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02895 - Dude: A Dual-Detection Multi-Agent System for Paper-Code Discrepancy Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03416 - The Head Complexity of Boolean Functions in Single-Layer Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04046 - Sparse auto-regressive modeling for scene generation from multi-view images Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03931 - Geometry-Aware Graph Construction via Adaptive Spectral Bandwidth Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03306 - FLY-EVAL++: An Evidence-Driven Evaluation Protocol for Safety-Constrained Flight Prediction with Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04021 - From Ordered Bernoulli Levels to Critical-Line Geometry: Integer Quantization, Bernoulli Residual Phase, and Prime-Power Spectra Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03801 - Pushing the (Decision) Boundaries: Dynamically Calibrating Differentially Private Noise to Explainability in Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03851 - Selective Hypergraph Refinement for Frozen Graph Clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03265 - Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27370 - Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.15154 - Non-Stationary Functional Bilevel Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.15363 - DE-Venus: A Data-Efficient RLVR Framework for Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03324 - Semantic Bayesian World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03834 - Mixed Data Clustering Survey and Challenges Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.03070 - Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02998 - Causal Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03003 - Hard-ReLU Gradient Descent Selects an Event-Free Sensitivity Limit Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30960 - Target-Guided Selective Reweighting for Physics-Informed Neural Network Inverse Problems: A Transfer Learning Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.05271 - Introducing SINFONIA: Symplectic, slimplectic and Magnusian (Neural) Flows for Orbital Numerical Integration and Acceleration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03329 - SPACR: Single-Pass Adaptive Training of Uncertainty-Aware Conformal Regressors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10734 - Hierarchical Channel Stacking: A Structured Decision Framework for AI-Generated Image Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26648 - Population-Calibrated Graph Screening at 835-Million-Address Scale, with Label-Free Transfer to New Chains Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03036 - Distilling deep optical flow stereo methods to retrieve dense three-dimensional wind fields Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03100 - Gradients Know What Outcomes Don't: Unlocking Reinforcement Learning for LLM Reasoning with Gradient-Aligned Rewards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03342 - InKAN: B-Spline KANs via Truncated Power Form Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01956 - Simplify to Amplify: Achieving Information-Theoretic Bounds with Fewer Steps in Spectral Community Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.17104 - Democratic ICAI: Debating Our Way to Steering Principles from Preferences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.28294 - A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15144 - JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25593 - Correlated initialization of deep residual networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03589 - Grassmann--Pl\"ucker Parametrization of Convolutional Filter Subspaces: Regularity and Closed Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03361 - Influence of Extruded Filament Shape on Buildability in 3D Concrete Printing: A Geometry-Informed Deep Learning-FEM Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04028 - Mind the Gap: Robustness Risks in PII Detection Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03464 - Projected Riemannian Gradient Descent for the Bures-Wasserstein Barycenter: Dimension-Independent Linear Convergence at Unit Step Size Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03762 - Learning to Select, Not Relearn: Hard-Routed Mixtures of Reasoning LoRAs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31413 - Guide, Not Bind: Why Defeasible Priors Fail in Augmented Lagrangian Causal Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03442 - Sliding-Window Reordering with Overlap Averaging: A Simple Time-Domain Augmentation for Multivariate Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.09067 - 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 - Learning Constraints-Based Adaptive Hypergraph Neural Networks for Solving Vehicle Routing Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.10421 - SNAP-FM: Sparse Nonlinear Accelerated Projection for Physics-Constrained Generative Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.00095 - VestigeKV: The NoPE-MLA KV Cache Carries Its Own Eviction Signal in a Vestigial Branch Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03949 - ALRA: Adaptive Local Relational Alignment for Logit-Based Pre-training Distillation of Autoregressive Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03355 - LLMZero: Discovering Adaptive Training Strategies for RL Post-Training via LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18388 - Differentiable Interval Bottlenecks for Interpretable Anomaly Detection in Numerical Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03878 - Towards a Statistical Understanding of Mixture-of-Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03501 - A Peer-Relative Representation Learning Framework for Energy Inefficiency Identification in Mobile Network Sites Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03809 - MidSurfNet: Learning Face Pairing for Mid-surface Abstraction of Thin-walled CAD Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01891 - Residual neural networks overcome the curse of dimensionality for semilinear heat equations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03626 - Observation-Aligned Two-Stage Domain Decomposition for Physics-Informed Traffic State Estimation with Sparse Fixed Sensors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08028 - RecurTrace: Adaptive Latent Reasoning with Loop-Time Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03379 - Tree species mapping in Denmark: A comparison of spectral-temporal features with geospatial foundation model embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03480 - Reliable Selection of Heterogeneous Treatment Effect Estimators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.18464 - Coupled Tensor-Tensor Completion Method with Applications in Drug Repurposing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03190 - RCProb: Probabilistic rule extraction from classification tree ensembles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.25304 - Towards Affordable Energy: A Gymnasium Environment for Electric Utility Demand-Response Programs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12462 - Physics-Informed Neural Network Surrogate for Oxygen Vacancy Dynamics in epitaxial $\mathrm{SrTiO_3}$ on Si memristors via Dynamic Spectral Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02966 - LeanGRPO: Eliminating Redundant Recomputation in Diffusion RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03528 - Headroom-Drift Replay: A Primitive for Principled Replay Control in GRPO Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03941 - Active learning for data-driven reduced models of parametric differential systems with Bayesian operator inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.00038 - Learning Informative Prior with Infinite-Dimensional Continuous Normalizing Flow for Bayesian Inverse Problem Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03343 - KARMA: Knowledge graph-based Automated Reasoning Materialization and Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.03166 - MSign: An Optimizer Preventing Training Instability in Large Language Models via Stable Rank Restoration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01734 - Temperature Scaling Attack Disrupting Model Confidence in Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.06638 - KernelFoundry: Hardware-aware evolutionary GPU kernel optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.12440 - FedPS: Federated Preprocessing for structured data via aggregated Statistics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.10870 - ObserverBench: Testing Mechanistic Estimates for Intervention and Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03026 - Differentiable Hybrid Modelling for Learning and Optimising Chemical Transport Processes from Experimental Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04011 - Learning to Concatenate Quantum Codes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.14931 - Learnable composition for neural operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03069 - Adaptive Partitioning and Learning for Stochastic Control of Diffusion Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.14991 - RARF: Region-Aware Rectified Flows for 3D Brain MRI Inpainting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03956 - RobustSeiz: An Open-Source Framework for Benchmarking the Robustness of EEG Seizure Detection Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04007 - Robust PAC Learning of Concurrent Stochastic Games Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04189 - RATL: Learning from Retrieved Residuals for Robust Multivariate Time-Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03937 - Parameterised graph theory for tensor networks: entanglement rerouting, structural simplification, and agnostic tomography Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04165 - Sensing Which Modality Matters: Evidence-Gated Regularization for Robust VLA Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03142 - Subspace Inference Enables Efficient Active Reward Learning from Preferences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04066 - ScoreMix: Synthetic Data Generation by Score Composition in Diffusion Models Improves Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.10226 - Evaluating Graph Neural Networks for Change-Criticality Classification in Maritime Navigation Charts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02996 - FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03241 - EPIC: Explicit Posterior Item Conditioning for Semantic ID Diffusion Recommendation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03522 - BASP: Communication-Efficient Batch-Aware Sequence Parallelism for LLM Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03151 - Activation-Keyed Momentum: An Anisotropic Momentum Update via the Delta Rule Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19491 - Identification of Bivariate Causal Directionality Based on Anticipated Asymmetric Geometries Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.26024 - A Low-Cost, Open Platform for End-to-End Autonomous Driving on a Miniature Ackermann Vehicle Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04147 ## Community - The Pelican comparison grid for Astra is pretty interesting Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/4/astra-pelicans/ - Help trying to compile macrdp via Cargo build Source: rust-users-forum Topic: Rust URL: https://users.rust-lang.org/t/help-trying-to-compile-macrdp-via-cargo-build/142252 - OpenAI's rogue agents were caught communicating via public wikis Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/4/rogue-agent-wikis/ - Frontend is Leptos and backend is Axum, full stack Rust Source: rust-users-forum Topic: Rust (+JavaScript, React) URL: https://users.rust-lang.org/t/frontend-is-leptos-and-backend-is-axum-full-stack-rust/142239 - August newsletter is out Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/4/august-newsletter/ - How to Start an LLM-Assisted Java Project Source: adam-bien Topic: Java (+AI) URL: https://adambien.blog/roller/abien/entry/how_to_start_an_llm_assisted_java_project - Reducing duplication in `TryFrom` Source: rust-users-forum Topic: Rust URL: https://users.rust-lang.org/t/reducing-duplication-in-tryfrom/142229 - Python Morsels: Creating temporary files in Python Source: planet-python Topic: Python URL: https://www.pythonmorsels.com/temporary-files/ - Shaun Thomas: Batteries Included: Powering AI DBA Workbench Locally with llama.cpp Source: planet-postgresql Topic: PostgreSQL (+AI) URL: https://postgr.es/p/9uj - Implementing SAT in OCaml Part 3 Source: ocaml-planet Topic: OCaml URL: https://funcp.org/implementing-sat-in-ocaml-part-3 - Python Anywhere: Annual plans, PostgreSQL 15, and easier database management Source: planet-python Topic: Python (+PostgreSQL) URL: https://blog.pythonanywhere.com/224/ - Christophe Pettus: All Your GUCs in a Row: log_lock_waits and log_lock_failures Source: planet-postgresql Topic: PostgreSQL URL: https://postgr.es/p/9tT - Trey Hunner: Python Morsels now has spaced repetition Source: planet-python Topic: Python URL: https://treyhunner.com/2026/09/python-morsels-now-has-spaced-repetition/ - Mikhail Shytsko: What Replica Mode Does Not Switch Off Source: planet-postgresql Topic: PostgreSQL URL: https://postgr.es/p/9tX - Graham Dumpleton: Phased behaviour in wrapture Source: planet-python Topic: Python URL: https://grahamdumpleton.me/posts/2026/09/phased-behaviour-in-wrapture/ - Bob Belderbos: Why does Alembic need an import you never use? Source: planet-python Topic: Python URL: https://belderbos.dev/blog/what-table-true-does-sqlmodel/ - Show HN: Moadim.io – A scheduler for agents Source: hacker-news Topic: General URL: https://moadim.io/ - Portal by Spotify cut my Claude Code token usage by 90% Source: hacker-news Topic: General URL: https://engineering.atspotify.com/2026/9/portal-by-spotify-cut-my-claude-code-token-usage-by-90 - Connecting every app to every other app Source: hacker-news Topic: General URL: https://blog.val.town/connectors - Gimlet's Series B Source: hacker-news Topic: General URL: https://gimletlabs.ai/blog/announcing-series-b - Claude Code skills for advanced context engineering techniques and patterns Source: hacker-news Topic: General URL: https://github.com/NeoLabHQ/context-engineering-kit - This Month in Ladybird – August 2026 Source: hacker-news Topic: General URL: https://ladybird.org/newsletter/2026-08-31/ - Can guitar frets perform multiplication? Source: hacker-news Topic: General URL: https://www.charlespetzold.com/blog/2026/09/Can-Guitar-Frets-Perform-Multiplication.html - Almost half of ICANN-accredited registrars under the control of a single busines Source: hacker-news Topic: General URL: https://domainincite.com/31912-dropcatch-acquires-300-more-registrars - SwiftTUI Source: hacker-news Topic: General URL: https://swifttui.sh/ - Record-High 89% in U.S. Say Government Corruption Widespread Source: hacker-news Topic: General URL: https://news.gallup.com/poll/713933/record-high-say-government-corruption-widespread.aspx - Reverse Engineering a Chip (or well, a GDS) Source: lobsters Topic: General (+Hardware) URL: https://pradyun.net/blog/reverse_engineering.html - Actively exploited sandbox RCE in all Chromium versions Source: hacker-news Topic: General URL: https://nvd.nist.gov/vuln/detail/cve-2026-85046 - Icons as a Service Source: hacker-news Topic: General URL: https://nravic.com/blog/images/ - GPT-6 Astra on OpenRouter Source: hacker-news Topic: General (+AI) URL: https://openrouter.ai/openai/gpt-6-astra - White House Launches Arcade.Gov Source: hacker-news Topic: General URL: https://www.ign.com/articles/white-house-launches-arcadegov-a-minigame-site-where-you-catch-immigrants-build-a-tetris-border-wall-and-fill-your-kids-trump-accounts-with-bitcoin - End-to-end infrastructure for training and inferencing open weight models Source: hacker-news Topic: General URL: https://docs.appliedcompute.com - Updates on HEIR, the Homomorphic Encryption Compiler Project Source: hacker-news Topic: General URL: https://www.jeremykun.com/2026/09/04/updates-on-heir-homomorphic-encryption/ - Without new landers or rovers, it's helicopters or bust for NASA's Mars program Source: hacker-news Topic: General URL: https://arstechnica.com/space/2026/09/without-new-landers-or-rovers-its-helicopters-or-bust-for-nasas-mars-program/ - Some more thoughts on random_page_cost Source: hacker-news Topic: General URL: https://vondra.me/posts/some-more-thoughts-on-random-page-cost/ - Fermat's Last Theorem: Anthropic has beaten me to it Source: hacker-news Topic: General (+AI) URL: https://xenaproject.wordpress.com/2026/09/04/flt-anthropic-has-beaten-me-to-it/ - Thinking in Code Source: hacker-news Topic: General URL: https://aishwaryagoel.com/thinking-in-code/ - Household Laser Cuts Source: hacker-news Topic: General URL: https://cceckman.com/writing/household-laser-cuts/ - Atmosphere Explorer Browse and manage data across the AT Protocol Source: hacker-news Topic: General URL: https://pds.ls/ - What is known about how Eric Lu factored the 862-bit RSA-260 after 35 years Source: hacker-news Topic: General URL: https://lilting.ch/en/articles/rsa-260-factored-how-computed - Statichost.eu – European static site hosting Source: hacker-news Topic: General URL: https://www.statichost.eu/ - Scientists observe Einstein's gravity in the quantum world Source: hacker-news Topic: General URL: https://www.ox.ac.uk/news/2026-08-28-scientists-observe-einsteins-gravity-in-the-quantum-world - Learning Cultures Reading Group: "Like Coding in the Dark" Source: hacker-news Topic: General URL: https://www.maayanroth.com/blog/posts/coding-in-the-dark.html - The Sealed Document TikTok Doesn't Want Two Senators to See Source: hacker-news Topic: General URL: https://www.bloomberg.com/news/articles/2026-09-04/the-sealed-document-tiktok-doesn-t-want-two-senators-to-see - Finding a bug in Dummit and Foote's Abstract Algebra Source: hacker-news Topic: General URL: https://kallus.org/blog/dummit_and_foote.html - GPT-6 Astra Generally Available Source: hacker-news Topic: General (+AI) URL: https://twitter.com/OpenAI/status/2095968413646737608 - How to Create a Tor Exit Node (2015) Source: hacker-news Topic: General URL: https://madpsy.uk/how-to-create-a-tor-exit-node/ - An open DNS recursive service for free security and high privacy Source: hacker-news Topic: General URL: https://quad9.net/ - Searching for the best silicone USB cable Source: hacker-news Topic: General URL: https://www.frankchiarulli.com/blog/best-silicone-usb-cable/ - Can AI design circuit boards yet? Source: hacker-news Topic: General URL: https://eebench.org/blog/can-ai-design-circuit-boards-yet/ - More Targets of the OpenAI Agent Swarm Source: hacker-news Topic: General (+AI) URL: https://fi-le.net/vanderbilt/ - MISRust: Mapping MISRA-C++ Coding Guidelines to the Rust Programming Language Source: lobsters Topic: General (+Rust) URL: https://arxiv.org/abs/2605.23490 - U.S. Navy Spent $3.4B on Idled Submarines, Could Spend Another $3.1B More Source: hacker-news Topic: General URL: https://www.jalopnik.com/2249392/u-s-navy-3-4-billion-idled-submarines/ - Government Rails Site Hit Hours After CVE Patch Source: hacker-news Topic: General URL: https://rietta.com/blog/ruby-on-rails-cve-exploited-hours-after-patch/ - Fermat's Last Theorem in Lean 4 Source: hacker-news Topic: General URL: https://github.com/anthropics/fermats-last-theorem - Shutting down our public encrypted DNS Source: hacker-news Topic: General URL: https://mullvad.net/en/blog/shutting-down-our-public-encrypted-dns-servers-and-sponsoring-quad9-instead - Formalizing Fermat's Last Theorem Source: hacker-news Topic: General (+AI) URL: https://www.anthropic.com/research/formalizing-fermats-last-theorem - Amazon Achieves Enshitification Inception Source: hacker-news Topic: General URL: https://pluralistic.net/2026/09/04/cheating-at-fraud/#absentee-rentier - Show HN: Jigsaw Haiku Source: hacker-news Topic: General (+AI, JavaScript, React) URL: https://jigsawhaiku.com/ - Hayes AT command set Source: hacker-news Topic: General URL: https://en.wikipedia.org/wiki/Hayes_AT_command_set - The Rust React Compiler is now native in Vite Source: hacker-news Topic: General (+JavaScript, React) URL: https://blog.master.dev/react-now-rusted-all-the-way-out/ - Show HN: Open-Source eInk Bike Computer Source: hacker-news Topic: General URL: https://opentrailpaper.com - Squeezing Performance Out of eBPF Source: hacker-news Topic: General URL: https://bitbison.io/blog/ebpf-performance/ - Mongotar: Files to prompt, and back Source: lobsters Topic: General URL: https://github.com/sebastiancarlos/mongotar - Georgi Gerganov on llama.cpp/ggml future after Nvidia acquisition of HuggingFace Source: hacker-news Topic: General (+AI) URL: https://twitter.com/ggerganov/status/2095897173376618881 - “Next-token predictor” is the wrong mental model for LLMs Source: hacker-news Topic: General (+AI) URL: https://gmcgoldr.github.io/2026/09/04/llm-next-token-predictors.html - Adult Film Producer Unmasks Prolific 'John DOE' Torrent Pirate as Meta Executive Source: hacker-news Topic: General URL: https://torrentfreak.com/adult-film-producer-unmasks-prolific-john-doe-torrent-pirate-as-meta-executive/ - Project HydraFusion: Frontier quality via multi-model orchestration Source: hacker-news Topic: General URL: https://github.blog/ai-and-ml/github-copilot/project-hydrafusion-frontier-quality-via-multi-model-orchestration/ - UN votes to adopt new map that makes our world look different Source: hacker-news Topic: General URL: https://www.cnn.com/2026/09/04/world/un-vote-new-world-map-intl-scli - Exploring Mojo’s raw pointer type Source: lobsters Topic: General URL: https://melodyogonna.substack.com/p/exploring-mojos-raw-pointer-type - Woman who exposed FBI official for working with Russian oligarch found dead Source: hacker-news Topic: General URL: https://www.newsweek.com/allison-guerriero-michael-mcgonigal-fbi-exposed-working-russian-oligarch-dead-12392795 - AI it's not bad but it's a tool Source: lobsters Topic: General URL: https://lobste.rs/s/2eai0v/ai_it_s_not_bad_it_s_tool - deSEC – Free Secure DNS Source: hacker-news Topic: General URL: https://desec.io/ - Fast weights and sparse attention in GLM-5.3-Flash Source: hacker-news Topic: General URL: https://idlemachines.co.uk/essays/glm-5-3-flash - Corporate America is getting hooked on open-source AI Source: hacker-news Topic: General (+AI) URL: https://www.nytimes.com/2026/09/04/technology/open-source-ai-anthropic-openai.html - Gmail to end support for "Send as" for third-party addresses, such as @yahoo.com Source: hacker-news Topic: General URL: https://support.google.com/mail/answer/22370?hl=en - Leading Theory for How Life on Earth Began Is 'Highly Unlikely' Source: hacker-news Topic: General URL: https://www.sciencealert.com/leading-theory-for-how-life-on-earth-began-is-highly-unlikely-says-contentious-new-paper - Norway's $2T sovereign fund proposes deep cuts to US Treasury holdings Source: hacker-news Topic: General URL: https://www.reuters.com/business/norways-2-trillion-sovereign-fund-proposes-deep-cuts-us-treasury-holdings-2026-09-04/ - She Also Found It at the Movies Source: hacker-news Topic: General URL: https://hedgehogreview.com/web-features/thr/posts/she-also-found-it-at-the-movies - Higher social class predicts increased unethical behavior Source: hacker-news Topic: General URL: https://www.pnas.org/doi/10.1073/pnas.1118373109 - Top Pentagon Official Contracted Personal Lawyer to Handle Minerals Deal Source: hacker-news Topic: General URL: https://prospect.org/2026/08/21/pentagon-minerals-deal-department-defense-cerberus-capital-alan-waldenberg-stephen-feinberg/ - The NX bit is not just about security Source: hacker-news Topic: General URL: https://purplesyringa.moe/blog/guest/the-nx-bit-is-not-just-about-security/ - US Military disables ad trackers on troops' phones Source: hacker-news Topic: General URL: https://www.theguardian.com/us-news/2026/sep/04/military-disables-phone-ad-trackers - Babashka 1.13.220 gets FFI Source: lobsters Topic: General URL: https://blog.michielborkent.nl/babashka-ffi.html - Colorlight 5A-75B: A dive into a popular low-cost ECP5 (FPGA) development board Source: hacker-news Topic: General URL: https://blog.yosyshq.com/p/colorlight-part-1/ - IBM Bob Source: hacker-news Topic: General URL: https://bob.ibm.com/ - Restoring 5 GHz Wi-Fi on an LG C5 by changing its webOS region Source: hacker-news Topic: General URL: https://github.com/hawshemi/lg-c5-webos25-region-change - jank reimagines C++ errors and gets an official native package repo Source: lobsters Topic: General URL: https://jank-lang.org/blog/2026-09-04-better-and-better/ - How Fairphone built the Fairphone Gen 6+ Source: hacker-news Topic: General URL: https://arstechnica.com/gadgets/2026/09/nearly-impossible-how-fairphone-built-the-ethical-repairable-fairphone-gen-6/ - Ok, but does it scale? Source: hacker-news Topic: General URL: https://spacetimedb.com/blog/how-does-spacetime-scale - Google AI Mode shows same products 21.6% more expensive than traditional search Source: hacker-news Topic: General URL: https://productrise.app/blog/google-ai-mode-prefers-more-expensive-products - Discovery of a new OpenAI agent message board Source: hacker-news Topic: General (+AI) URL: https://collusion.wiki/ - deft: A gradual type system for Janet Source: lobsters Topic: General URL: https://codeberg.org/zzkt/deft - A preview of the future Intel Architecture documentation Source: lobsters Topic: General (+Hardware) URL: https://intel.github.io/SDM/announcement/2026/08/20/announce-preview.html - Smolts: A pedagogical IDE for a teaching language Source: hacker-news Topic: General URL: https://eighty-twenty.org/2026/09/04/smolts - O&O ShutUp10 – The antispy tool for Windows 10 and 11 Source: hacker-news Topic: General URL: https://www.oo-software.com/en/shutup10 - The new Go JSON API: twice as fast, or 1.5x slower? Source: lobsters Topic: General (+Go) URL: https://lemire.me/blog/2026/08/29/the-new-go-json-api-twice-as-fast-or-1-5x-slower/ - US diesel prices hit a record high of $5.85 on average Source: hacker-news Topic: General URL: https://apnews.com/article/gas-diesel-prices-us-iran-war-ebd01b9773365ee40550dcfd7d3ebf87 - OpenAI agents hijacked German website in previously undisclosed AI breakout Source: hacker-news Topic: General (+AI) URL: https://www.reuters.com/world/europe/openai-agents-hijacked-german-website-previously-undisclosed-ai-breakout-this-2026-09-04/ - Solving the Jane Street reverse engineering challenge Source: hacker-news Topic: General URL: https://jestoph.com/2026/09/04/jane-street-challenge.html - The auto lobby spent millions on media manipulation Source: hacker-news Topic: General URL: https://impuls.news/en/featured/gasoline-lobby-from-electric-cars/ - A Week of Bug Reporting Source: hacker-news Topic: General URL: https://tratt.net/laurie/blog/2022/a_week_of_bug_reporting.html - Imperial Colors Manifesto Source: lobsters Topic: General URL: https://qum.cz/imperial_colors/ - Whistle Synth Mac App Source: hacker-news Topic: General URL: https://www.jefftk.com/p/whistle-synth-mac-app - Tracing np.add, all the way down Source: hacker-news Topic: General URL: https://blog.veitheller.de/numpy.html - Is AI ruining my brain? Source: lobsters Topic: General URL: https://thoughtbot.com/blog/is-ai-ruining-my-brain - CERN Transitioning Computers To Debian After Being A Longtime RHEL Institution Source: hacker-news Topic: General URL: https://www.phoronix.com/news/CERN-Goes-Debian-Leaving-RHEL - Show HN: TERMy – A fast terminal assistant that does not use LLMs Source: hacker-news Topic: General (+AI) URL: https://github.com/gioblu/NPC-Forge/blob/main/docs/development.md - Show HN: Prices.eu.org Source: hacker-news Topic: General (+AI) URL: https://prices.eu.org/ - Collider: An experimental Minecraft server Source: lobsters Topic: General URL: https://github.com/Nozistance/collider - The Raspberry Pi Interactive Timeline · 2006–2026 Source: hacker-news Topic: General URL: https://raspberry.tips/en/raspberrypi-infos/raspberry-pi-history-timeline - Carbon-aware electricity pricing, measured daily on 38 grids Source: hacker-news Topic: General URL: https://carbonawarepricing.com/ - Surviving Code Reviews in the era of AI Source: lobsters Topic: General URL: https://lobste.rs/s/7tpc5q/surviving_code_reviews_era_ai - Inserting State Transitions in Postgres Source: lobsters Topic: General (+Databases, PostgreSQL) URL: https://thoughtbot.com/blog/inserting-state-transitions-in-postgres - Bank of Canada bank notes: Resources for the blind and partially sighted Source: hacker-news Topic: General URL: https://www.bankofcanada.ca/banknotes/audience-specific-resources/blind-and-partially-sighted/ - FORCE_COLOR: Keep Your Command Line Colorful, Even when Piping - Retain Text Colors in Logs, Output Streams, and More Source: lobsters Topic: General URL: https://force-color.org/ - Reverse engineering the storage format for an undocumented database Source: hacker-news Topic: General URL: https://blog.glazer.ee/posts/converting-cronos/ - Hackers had a live feed of every ID verification company scanned for over a year Source: hacker-news Topic: General URL: http://www.techdirt.com/2026/09/03/hackers-had-a-live-feed-of-every-id-this-verification-company-scanned-for-over-a-year/ - UN to vote on adopting new world map that shows Africa's true scale Source: hacker-news Topic: General URL: https://www.theguardian.com/world/2026/sep/04/un-vote-world-map-mercator-equal-earth-africa - Decoding the NEC V20 Microcode Source: hacker-news Topic: General URL: https://martypc.blogspot.com/2026/09/decoding-nec-v20-microcode.html - Bug triaging help needed Source: lobsters Topic: General URL: https://pointieststick.com/2026/09/03/bug-triaging-help-needed/ - John Margolies' photographs of roadside America Source: hacker-news Topic: General URL: https://publicdomainreview.org/collection/john-margolies-photographs-of-roadside-america/ - Show HN: Word42, a wordprocessor inspired by MS Word and Abiword Source: hacker-news Topic: General URL: https://word42.org/ - What are you doing this weekend? Source: lobsters Topic: General URL: https://lobste.rs/s/ku30xf/what_are_you_doing_this_weekend - The Incomplete Guide to Lazy Evaluation in Haskell (2015) Source: lobsters Topic: General URL: https://apfelmus.nfshost.com/articles/lazy-eval.html - Dynamic linking best practices (2021) Source: lobsters Topic: General URL: https://begriffs.com/posts/2021-07-04-shared-libraries.html - Chinese Espionage Threat: Suspected Spy Drone Caught over Sensitive U.S. Missile Source: hacker-news Topic: General URL: https://www.theyeshivaworld.com/news/general/2592346/chinese-espionage-threat-suspected-spy-drone-caught-over-sensitive-u-s-missile-base.html - Grep beats LSP? Why coding agents ignore your fancier tools Source: hacker-news Topic: General URL: https://www.agentconnect.md/blog/grep-beat-lsp-harness/ - A mysterious kidney disease has arrived in Texas Source: hacker-news Topic: General URL: https://www.texasmonthly.com/news-politics/ckdu-kidney-disease-immigration/ - No more issues Source: lobsters Topic: General URL: https://stitcher.io/blog/no-more-issues - From Hookswitch to Grave Source: hacker-news Topic: General URL: https://computer.rip/2026-06-14-hookswitch-to-grave.html - WTF is going on with R7RS Large? 2026 edition Source: lobsters Topic: General URL: https://crumbles.blog/posts/2026-09-04-r7rs-wtf.html - Tesla Begins Offering Rides in a Car Without a Steering Wheel Source: hacker-news Topic: General URL: https://www.nytimes.com/2026/09/03/business/tesla-cybercab-robotaxi-rides.html - Project Xanadu: Even More Hindsight (2025) Source: hacker-news Topic: General URL: https://gwern.net/xanadu - What is nueralese and why is it bad Source: hacker-news Topic: General URL: https://www.lesswrong.com/posts/RCYF2rW8wgusidZk7/what-is-neuralese-and-why-is-it-bad - Wikimedia Workers Overwhelmingly Win Union with 93% Yes Vote Source: hacker-news Topic: General URL: https://www.wired.com/story/wikipedia-workers-vote-on-whether-to-unionize/ - Show HN: Interactive Tree of Life Source: hacker-news Topic: General URL: https://ptree.org/ ## Media - WG Checkpoint Restore Meeting for 2026-09-04 Source: youtube-kubernetescommunity Topic: DevOps URL: https://www.youtube.com/watch?v=HKAiAKUwAZ0 - Why KubeCon + CloudNativeCon Is Essential for Growth Source: youtube-cncf Topic: DevOps (+Open Source) URL: https://www.youtube.com/shorts/y3yAqi_wfZ4 - SIG Contribex Meeting for 2026-09-04 Source: youtube-kubernetescommunity Topic: DevOps URL: https://www.youtube.com/watch?v=wVWrJc1qa4g - We shipped 207 WebGPU Kernels for Browser AI Source: youtube-huggingface Topic: Hugging Face (+AI) URL: https://www.youtube.com/watch?v=y9xup6XEP2o - Hugging Face Journal Club: AI Research Preference Models Source: youtube-huggingface Topic: Hugging Face (+AI) URL: https://www.youtube.com/watch?v=8YttDoDINhk - #561: TonIO, a Multi-threaded Async Runtime for Python Source: talk-python Topic: Python URL: https://talkpython.fm/episodes/show/561/tonio-a-multi-threaded-async-runtime-for-python - 🎙️what JL said after the Qualifying Final Source: youtube-docker Topic: DevOps URL: https://www.youtube.com/watch?v=m24uU7Y2kpk - Did OpenAI actually build AGI? GPT-6 Astra first look Source: youtube-fireship Topic: Web (+AI, General, JavaScript) URL: https://www.youtube.com/watch?v=FluKUJyeYD8 - How Project HydraFusion optimizes quality, cost, and speed in GitHub Copilot Source: youtube-github Topic: Open Source (+General) URL: https://www.youtube.com/shorts/uug8gCi3Xxk - Introducing Project HydraFusion: multi-model orchestration in GitHub Copilot Source: youtube-github Topic: Open Source (+General) URL: https://www.youtube.com/watch?v=dJmt1PHsETM - The Download: Attach images in GitHub CLI, Qwen3.8-Max, AI pull request lingo & more Source: youtube-github Topic: Open Source (+AI, General) URL: https://www.youtube.com/watch?v=A_PQvLNDt2k - Rubber Duck Thursday with Cameron Hamilton Source: youtube-github Topic: Open Source (+AI, General) URL: https://www.youtube.com/watch?v=Osp54zk7Hco - Jueves de Quack con Axel Labruna Source: youtube-github Topic: Open Source (+AI, General) URL: https://www.youtube.com/watch?v=1SadQDgwVbc - PODCAST | Viva BRIS-VEGAS + Gabby's plan for the TIGERS!!! [R&R #14] Source: youtube-docker Topic: DevOps URL: https://www.youtube.com/watch?v=VD3yPpV4ZnA