TILens Daily Edition 2026-09-25 Filters: github=hidden Stats: 1095 articles, 54 sources, 751 research papers Top topics: AI, AI Research, General ## News - Amazon Transcribe adds customer-managed KMS keys for custom resources Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/09/amazon-transcribe/ - Proaction boosts sales 60% and saves 75+ hours with Codex Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/proaction - Amazon EC2 M8i and M8i-flex instances are now available in additional regions Source: aws-whats-new Topic: AWS (+AI, PostgreSQL) URL: https://aws.amazon.com/about-aws/whats-new/2026/09/amazon-ec2-m8i-m8i-flex-thf/ - Amazon EC2 R8i and R8i-flex instances are now available in additional regions Source: aws-whats-new Topic: AWS (+AI, PostgreSQL) URL: https://aws.amazon.com/about-aws/whats-new/2026/09/ec2-r8i-r8i-flex-thf/ - Amazon EC2 C8i and C8i-flex instances are now available in additional regions Source: aws-whats-new Topic: AWS (+AI) URL: https://aws.amazon.com/about-aws/whats-new/2026/09/c8i-c8i-flex-thf-september-2026/ - GitHub Copilot app for Beginners: How to build custom workflows with canvases Source: github-blog Topic: Open Source URL: https://github.blog/ai-and-ml/github-copilot/github-copilot-app-for-beginners-how-to-build-custom-workflows-with-canvases/ - AWS IAM outbound identity federation now supports interface VPC endpoints for OIDC discovery Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/09/aws-sts-vpc-oidc/ - Same Query, Same Score: Consistent Ranking with StableTfl in Atlas Search Source: mongodb-blog Topic: MongoDB (+AI, Information Retrieval) URL: https://www.mongodb.com/company/blog/engineering/same-query-same-score-consistent-ranking-with-stabletfl-atlas-search - How to stream PostgreSQL changes to Amazon S3 with AWS Fargate Source: aws-database-blog Topic: AWS (+PostgreSQL) URL: https://aws.amazon.com/blogs/database/how-to-stream-postgresql-changes-to-amazon-s3-with-aws-fargate/ - Trading a Cloud Identity for Your Own: Workload Attestation on Managed Compute Source: netflix-techblog Topic: Architecture URL: https://netflixtechblog.com/trading-a-cloud-identity-for-your-own-workload-attestation-on-managed-compute-516d5a29b252?source=rss----2615bd06b42e---4 - Sensea underwater camera — Raspberry Pi Official Magazine #170 Source: raspberrypi-news Topic: Hardware URL: https://www.raspberrypi.com/news/sensea-underwater-camera-raspberry-pi-official-magazine-170/ - AWS DataSync launches a monitoring dashboard for tracking task executions across your account Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/09/datasync-monitoring-dashboard - Improving site performance by shipping more CSS Source: github-blog Topic: Open Source URL: https://github.blog/engineering/architecture-optimization/improving-site-performance-by-shipping-more-css/ - AWS Elastic Disaster Recovery now supports AWS Graviton-based source servers Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/09/elastic-disaster-recovery-graviton/ - AWS End User Messaging now supports voice calling on WhatsApp Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/09/aws-end-user-messaging-voice-calling-whatsapp - AWS End User Messaging and Amazon SES now offer AI agent skills for the AWS MCP Server Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/09/aws-messaging-ses-ai-skills-mcp-server/ - Lowe’s answers millions of home improvement questions with OpenAI Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/lowes - AWS Billing and Cost Management now provides billing context for your account through a new API Source: aws-whats-new Topic: AWS URL: https://aws.amazon.com/about-aws/whats-new/2026/09/aws-billing-and-cost-management-billing-context-api/ - The Limitations of Running a Workload Generator In the Same JVM as the System-Under-Test Source: inside-java Topic: Java URL: https://inside.java/2026/09/25/limitations-of-running-a-workload-generator-in-the-same-jvm/ - Wayfair boosts catalog accuracy and support speed with OpenAI Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/wayfair - Spring Boot 4.2.0-M2 available now Source: spring-blog Topic: Java URL: https://spring.io/blog/2026/09/25/spring-boot-4-2-0-M2-available-now - Spring AI 2.1.0-M1 Available Now Source: spring-blog Topic: Java (+AI) URL: https://spring.io/blog/2026/09/25/spring-ai-2-1-0-M1-available-now - Unix Timestamps Explained: Seconds, Milliseconds, Time Zones and Common Mistakes Source: devto-javascript Topic: JavaScript URL: https://dev.to/julianhalden/unix-timestamps-explained-seconds-milliseconds-time-zones-and-common-mistakes-1p9c - i built a cookieless analytics tool (and deleted my cookie banner) Source: devto-javascript Topic: JavaScript URL: https://dev.to/omyvnss/i-built-a-cookieless-analytics-tool-and-deleted-my-cookie-banner-13ih - Crusoe abandons $1.25B plan to use Boom turbines at AI data centers Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/25/crusoe-abandons-1-25b-plan-to-use-boom-turbines-at-ai-data-centers/ - Everything That Happened in AI This Weekend So Far (Friday, September 25, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-this-weekend-so-far-friday-september-25-2026/ - Automattic has a new board after failed attempt to put CEO on leave Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/25/automattic-has-a-new-board-after-failed-attempt-to-put-ceo-on-leave/ - Can Trump ever be wrong? His pick to lead FDA refused to say. Source: ars-technica Topic: General URL: https://arstechnica.com/health/2026/09/can-trump-ever-be-wrong-his-pick-to-lead-fda-refused-to-say/ - Reviving the PoE++ Feature on a Ubiquiti Switch Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/25/reviving-the-poe-feature-on-a-ubiquiti-switch/ - Apple Intelligence for Home: cần gì để bật, giá bao nhiêu Source: devto-javascript Topic: JavaScript URL: https://dev.to/bean_bean/apple-intelligence-for-home-can-gi-de-bat-gia-bao-nhieu-54gn - Cổng CI cho code agent: reviewer sạch context và 3 chốt remote Source: devto-javascript Topic: JavaScript (+PostgreSQL) URL: https://dev.to/bean_bean/cong-ci-cho-code-agent-reviewer-sach-context-va-3-chot-remote-2nfl - Laya vs Jev: The Open-Source System 1 Decision Model Head-to-Head Source: devto-javascript Topic: JavaScript URL: https://dev.to/tekmag/laya-vs-jev-the-open-source-system-1-decision-model-head-to-head-5fm0 - Context Over MCP: Part V The Form Is the Tool. Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/wolfejam/context-over-mcp-part-v-the-form-is-the-tool-1cad - AI 2040 Plan A: What It Predicts and How the World Gets There Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/explainer-articles/ai-2040-plan-a-predictions-path-to-superintelligence/ - Unsecured OpenAI agents posted 53 user images on the internet without the lab’s knowledge Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/25/unsecured-openai-agents-posted-53-user-images-on-the-internet-without-the-labs-knowledge/ - John Park’s CircuitPython Parsec: Random Choice Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/25/john-parks-circuitpython-parsec-random-choice/ - How Fillable finds the blanks in a flat PDF form Source: devto-javascript Topic: JavaScript URL: https://dev.to/nobody_4fb7fd10637d3b88a3/how-fillable-finds-the-blanks-in-a-flat-pdf-form-68g - Court rules Pentagon can blacklist Anthropic for refusing to enable Claude features Source: ars-technica Topic: General (+AI) URL: https://arstechnica.com/tech-policy/2026/09/court-rules-trump-can-blacklist-anthropic-for-refusing-to-enable-claude-features/ - Tesla workers balk at training Optimus humanoid robots as replacements Source: ars-technica Topic: General URL: https://arstechnica.com/ai/2026/09/tesla-workers-balk-at-training-optimus-humanoid-robots-as-replacements/ - 1 porcja, 2 porcje, 5 porcji: Scaling Recipes and Handling Polish Plurals With Intl.PluralRules Source: devto-javascript Topic: JavaScript URL: https://dev.to/akbo_ichou_c41c249cc2783d/1-porcja-2-porcje-5-porcji-scaling-recipes-and-handling-polish-plurals-with-intlpluralrules-4mfa - Searching 10,000 Printable Pages Without a Search Server: A Prebuilt Index, Synonyms and Kid-Friendly Typos Source: devto-javascript Topic: JavaScript URL: https://dev.to/akbo_ichou_c41c249cc2783d/searching-10000-printable-pages-without-a-search-server-a-prebuilt-index-synonyms-and-1lcp - Meta opens early access program for new Muse features Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/25/meta-opens-early-access-program-for-new-muse-features/ - The hottest new hangout for middle schoolers is NPR’s comment section? Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/25/the-hottest-new-hangout-for-middle-schoolers-is-nprs-comment-section/ - Why the CISO-CFO Relationship Is a Key to Cybersecurity Success Source: darkreading Topic: DevSec URL: https://www.darkreading.com/cyber-risk/how-to-manage-ciso-cfo-relationship-cybersecurity-success - Building a Fair Trivia Quiz Engine: Unbiased Shuffling, Answer Position Balance and Team Scoring Source: devto-javascript Topic: JavaScript URL: https://dev.to/akbo_ichou_c41c249cc2783d/building-a-fair-trivia-quiz-engine-unbiased-shuffling-answer-position-balance-and-team-scoring-12o8 - Valen creator drives 'Golden Spike' to connect new languages with Rust Source: theregister Topic: General URL: https://www.theregister.com/devops/2026/09/25/valen-creator-drives-golden-spike-to-connect-new-languages-with-rust/5299273 - How I Built a Zero-API-Cost AI Agent That Runs 100% Locally — No Keys, No Cloud, No Bills Source: devto-javascript Topic: JavaScript (+React) URL: https://dev.to/scriptgather/how-i-built-a-zero-api-cost-ai-agent-that-runs-100-locally-no-keys-no-cloud-no-bills-3bi2 - Pi Pico Recreates The Heathkit Pocket Packet Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/25/pi-pico-recreates-the-heathkit-pocket-packet/ - Trustlines: Why XRPL Holder Counts Are Hard to Fake Source: devto-javascript Topic: JavaScript URL: https://dev.to/nyxagi/trustlines-why-xrpl-holder-counts-are-hard-to-fake-43gh - Raspberry Pi Security Camera Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/25/raspberry-pi-security-camera/ - Microsoft cells out, crams multiple values into Excel boxes Source: theregister Topic: General URL: https://www.theregister.com/applications/2026/09/25/microsoft-cells-out-crams-multiple-values-into-excel-boxes/5299294 - Building a Graffiti Text Generator With Canvas: FontFace Loading, Seeded Spray Effects and PNG Export Source: devto-javascript Topic: JavaScript URL: https://dev.to/akbo_ichou_c41c249cc2783d/building-a-graffiti-text-generator-with-canvas-fontface-loading-seeded-spray-effects-and-png-3j67 - Generating Printable Math Worksheets in JavaScript: Seeded Randomness, Constraints and Answer Keys Source: devto-javascript Topic: JavaScript URL: https://dev.to/akbo_ichou_c41c249cc2783d/generating-printable-math-worksheets-in-javascript-seeded-randomness-constraints-and-answer-keys-3d9i - Converting Video and Audio Entirely in the Browser With WebAssembly: Lessons From Building a Free Converter Source: devto-javascript Topic: JavaScript URL: https://dev.to/akbo_ichou_c41c249cc2783d/converting-video-and-audio-entirely-in-the-browser-with-webassembly-lessons-from-building-a-free-4fmn - LeveloJS Went Quiet. We Were Rebuilding the Foundation. Source: devto-javascript Topic: JavaScript URL: https://dev.to/motionmind2007/levelojs-went-quiet-we-were-rebuilding-the-foundation-4812 - Your uncle’s frozen Mac says it’s infected after viewing a Google ad. Now what? Source: ars-technica Topic: General URL: https://arstechnica.com/security/2026/09/google-ads-caught-delivering-convincing-scareware-ads-to-unsuspecting-users/ - Review: The iPhone 18 Pro is Apple's coolest smartphone (but only literally) Source: ars-technica Topic: General URL: https://arstechnica.com/apple/2026/09/review-the-iphone-18-pro-is-apples-coolest-smartphone-but-only-literally/ - We shipped a proxy extension for Firefox and Edge. Both browsers quietly reuse the old proxy tunnel, and that almost broke it. Source: devto-javascript Topic: JavaScript URL: https://dev.to/roamproxy/we-shipped-a-proxy-extension-for-firefox-and-edge-both-browsers-quietly-reuse-the-old-proxy-1g1i - Uncle Sam coughs up $1.9B for grid upgrades as datacenters hit a power wall Source: theregister Topic: General URL: https://www.theregister.com/systems/2026/09/25/uncle-sam-coughs-up-19b-for-grid-upgrades-as-datacenters-hit-a-power-wall/5299276 - A "Daily Challenge" That Resets at Midnight: Deterministic Picks Without a Backend Source: devto-javascript Topic: JavaScript URL: https://dev.to/akbo_ichou_c41c249cc2783d/a-daily-challenge-that-resets-at-midnight-deterministic-picks-without-a-backend-59ih - Building 24 Classroom Tools That Load Fast on a School Chromebook (No Login, No Student Data) Source: devto-javascript Topic: JavaScript URL: https://dev.to/akbo_ichou_c41c249cc2783d/building-24-classroom-tools-that-load-fast-on-a-school-chromebook-no-login-no-student-data-1gk4 - Anthropic to pay Akamai $11.6 billion over seven years in cloud deal Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/25/anthropic-to-pay-akamai-11-6-billion-over-seven-years-in-cloud-deal/ - Fake Google Security Team ad says 'no script reading' in voice phishing - then prints the script Source: theregister Topic: General URL: https://www.theregister.com/security/2026/09/25/fake-google-security-team-ad-says-no-script-reading-in-voice-phishing-then-prints-the-script/5299264 - AI was supposed to hit new grads hard. So far, unemployment data says otherwise. Source: ars-technica Topic: General URL: https://arstechnica.com/ai/2026/09/ai-was-supposed-to-hit-new-grads-hard-so-far-unemployment-data-says-otherwise/ - AI agents need continuity, not just context Source: pulumi-blog Topic: DevOps URL: https://www.pulumi.com/blog/neo-kopia-workspace-snapshots/ - New software dependency validation process increases speeds by 54x Source: theregister Topic: General URL: https://www.theregister.com/software/2026/09/25/new-software-dependency-validation-process-increases-speeds-by-54x/5299256 - Mark Wahlberg is coming to TechCrunch Disrupt 2026, and he wants to talk about your work, not his Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/25/mark-wahlberg-is-coming-to-techcrunch-disrupt-2026/ - Paramount/WBD merger conditions give the public "virtually nothing," judge is told Source: ars-technica Topic: General URL: https://arstechnica.com/tech-policy/2026/09/paramount-wbd-merger-conditions-give-the-public-virtually-nothing-judge-is-told/ - AI Sandbox Escapes: Why Forensic Readiness Matters More Than Containment Source: darkreading Topic: DevSec URL: https://www.darkreading.com/cyberattacks-data-breaches/ai-sandbox-escapes-forensic-readiness - “We Never Stand Still”: Ata Ul Haseeb Chaudhry’s 20 Years at EDB Source: edb-blog Topic: PostgreSQL URL: https://enterprisedb.com/blog/we-never-stand-still-ata-ul-haseeb-chaudhrys-20-years-edb - Ahead of US IPO, British AI neocloud Nscale secures $3.36B in convertible financing Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/25/ahead-of-u-s-ipo-british-ai-neocloud-nscale-secures-3-36b-in-convertible-finacing/ - Investigating a Rare Burnout 3 Beta Disc Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/25/investigating-a-rare-burnout-3-beta-disc/ - Subscribe to the Adafruit Youtube channel! #Youtube #AdafruitLearnSystem Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/25/subscribe-to-the-adafruit-youtube-channel-youtube-adafruitlearnsystem-226-4-3-2/ - Is solar's growth finally slowing in the US? Source: ars-technica Topic: General URL: https://arstechnica.com/science/2026/09/is-solars-growth-finally-slowing-in-the-us/ - ShinyHunters tells The Reg: We hacked the FBI to 'protect our business' Source: theregister Topic: General URL: https://www.theregister.com/cyber-crime/2026/09/25/shinyhunters-tells-the-reg-we-hacked-the-fbi-to-protect-our-business/5299250 - Google-backed energy outfit brings 33 MW of 4 GW geothermal potential online in Utah Source: theregister Topic: General URL: https://www.theregister.com/systems/2026/09/25/google-backed-energy-outfit-brings-33-mw-of-4-gw-geothermal-potential-online-in-utah/5299243 - Microsoft stops insisting you need a "Copilot+ PC" Source: ars-technica Topic: General URL: https://arstechnica.com/gadgets/2026/09/microsoft-stops-insisting-you-need-a-copilot-pc/ - What We Missed: Google Gemini Joins the AI Escape Party Source: darkreading Topic: DevSec (+AI) URL: https://www.darkreading.com/cyber-risk/what-we-missed-google-gemini-ai-escape-party - The Aeropod automates soil aeration without robotics — see it at TechCrunch Disrupt Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/25/the-aeropod-automates-soil-aeration-without-robotics-see-it-at-techcrunch-disrupt/ - Crooks use fake desktop apps to fool HR staff into giving them remote access Source: theregister Topic: General URL: https://www.theregister.com/security/2026/09/25/crooks-use-fake-desktop-apps-to-fool-hr-staff-into-giving-them-remote-access/5299226 - Some Supabase customers are publicly exposing reams of people’s data to the web Source: techcrunch Topic: General (+PostgreSQL) URL: https://techcrunch.com/2026/09/25/some-supabase-customers-are-publicly-exposing-reams-of-peoples-data-to-the-web/ - Astra and Opus just passed Turing’s other test Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/25/astra-and-opus-just-passed-turings-other-test/ - Microsoft’s new Copilot agents get their own email, calendar — and a place in the org chart Source: newstack Topic: DevOps URL: https://thenewstack.io/copilot-agents-identity-runtime/ - Bitget blames North Korea for $387.5M crypto wallet raid Source: theregister Topic: General URL: https://www.theregister.com/cyber-crime/2026/09/25/bitget-blames-north-korea-for-3875m-crypto-wallet-raid/5299218 - Hackaday Podcast Episode 388: RAM-Swapping on Raspberry Pi, Raindrops on Radar, and a Fine Mesh Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/25/hackaday-podcast-episode-388-ram-swapping-on-raspberry-pi-raindrops-on-radar-and-a-fine-mesh/ - OpenTelemetry and Prometheus are getting along. What’s still missing? Source: newstack Topic: DevOps URL: https://thenewstack.io/opentelemetry-prometheus-observability-interoperability/ - Meta is putting its muscle behind Muse as the AI app takes off Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/25/meta-is-putting-its-muscle-behind-muse-as-the-ai-app-takes-off/ - Adafruit LIS3DH Triple-Axis Accelerometer Breakout Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/25/adafruit-lis3dh-triple-axis-accelerometer-breakout/ - Meta’s AI Tamagotchi bet is…working? Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/video/will-metas-ai-tamagotchi-bet-isworking/ - [$] How KDE got funding to add enterprise features Source: lwn Topic: Open Source URL: https://lwn.net/Articles/1096245/ - Kiteworks urges customers to shut down their servers amid ‘imminent’ threat of cyberattack Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/25/kiteworks-urges-customers-to-shut-down-their-servers-amid-imminent-threat-of-cyberattack/ - For months, OpenAI’s agent swarms have been attacking online databases to find obscure facts Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/25/for-months-openais-agent-swarms-have-been-attacking-online-databases-to-find-obscure-facts/ - Anthropic’s founders seek voting control ahead of IPO Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/25/anthropics-founders-seek-voting-control-ahead-of-ipo/ - After seven years, a spacecraft company is releasing its Otters into the wild Source: ars-technica Topic: General URL: https://arstechnica.com/space/2026/09/after-seven-years-a-spacecraft-company-is-releasing-its-otters-into-the-wild/ - Did The BBC and Sir Clive Get it Right Twenty Years Ago? Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/25/did-the-bbc-and-sir-clive-get-it-right-twenty-years-ago/ - US being left behind in EV charging speeds as China goes sub-5 min to 70% Source: ars-technica Topic: General URL: https://arstechnica.com/cars/2026/09/us-being-left-behind-in-ev-charging-speeds-as-china-goes-sub-5-min-to-70/ - Two stable kernels for Friday Source: lwn Topic: Open Source URL: https://lwn.net/Articles/1096818/ - A summary from the 2026 Git Contributors' Summit Source: lwn Topic: Open Source (+AI) URL: https://lwn.net/Articles/1096819/ - LAST CALL FOR ENROLLMENT: Rebuild YouTube with AI Source: bytebytego Topic: Architecture URL: https://blog.bytebytego.com/p/last-call-for-enrollment-rebuild - Writing a .docx in the Browser With No Dependencies Source: devto-javascript Topic: JavaScript URL: https://dev.to/notepadneo/writing-a-docx-in-the-browser-with-no-dependencies-2fn - Office 2016 and 2019 holdouts blame update for license deactivation bug Source: theregister Topic: General URL: https://www.theregister.com/software/2026/09/25/office-2016-and-2019-holdouts-blame-update-for-license-deactivation-bug/5299186 - TechCrunch Disrupt 2026: Ricursive Intelligence’s Anna Goldie and Azalia Mirhoseini on when AI starts designing its own hardware Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/25/techcrunch-disrupt-2026-ricursive-intelligences-anna-goldie-and-azalia-mirhoseini-on-when-ai-starts-designing-its-own-hardware/ - Which copy of that file is the real one? Dinner, off the record, in Midtown Source: theregister Topic: General URL: https://www.theregister.com/storage/2026/09/25/sponsored/5299080 - Top 14 Platforms to Buy Aged Gmail Accounts in the USA ... Source: devto-javascript Topic: JavaScript URL: https://dev.to/ssk265336/top-14-platforms-to-buy-aged-gmail-accounts-in-the-usa--3lbm - Building a live network operations wall in one HTML file Source: devto-javascript Topic: JavaScript URL: https://dev.to/tonygoodchild/building-a-live-network-operations-wall-in-one-html-file-227h - The crypto Fear & Greed API: strings, midnight timestamps and a week that is six days long Source: devto-javascript Topic: JavaScript URL: https://dev.to/ethancole26/the-crypto-fear-greed-api-strings-midnight-timestamps-and-a-week-that-is-six-days-long-39hf - Stopping IT Worker Scams Requires Revamped HR Process Source: darkreading Topic: DevSec URL: https://www.darkreading.com/cyber-risk/stopping-it-worker-scams-revamped-hr-process - NitroIDE v25: I Security-Audited My Own Browser IDE — Here's Everything That Changed Source: devto-javascript Topic: JavaScript URL: https://dev.to/nitroide/nitroide-v25-i-security-audited-my-own-browser-ide-heres-everything-that-changed-48dn - Typed Email State for React Signups Source: devto-javascript Topic: JavaScript (+React) URL: https://dev.to/ryanlee91/typed-email-state-for-react-signups-5gp1 - LLM Streaming with Embabel Source: java-code-geeks Topic: Java (+AI) URL: https://www.javacodegeeks.com/llm-streaming-with-embabel.html - Raspberry Pi surfs memory crunch to record first half Source: theregister Topic: General URL: https://www.theregister.com/storage/2026/09/25/raspberry-pi-surfs-memory-crunch-to-record-first-half/5299155 - Running an Autonomous AI Agent Stack on Android with Termux — No Cloud, Just a Phone Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/sam_hiotis_117598dbfa3ac2/running-an-autonomous-ai-agent-stack-on-android-with-termux-no-cloud-just-a-phone-33dk - With PRIMA, NASA will try to build a billion-dollar space telescope in record time Source: ars-technica Topic: General URL: https://arstechnica.com/space/2026/09/nasa-green-lights-billion-dollar-infrared-observatory-for-launch-in-early-2030s/ - Meadow lets you leave your smartphone at home without sacrificing the essentials Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/25/meadow-lets-you-leave-your-smartphone-at-home-without-sacrificing-the-essentials/ - This Week in Security: FBI Gets Hacked, Muse Vulnerable to ClickFix, Popular Rust Developers at Risk, and New Attacks Against RSA Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/25/this-week-in-security-fbi-gets-hacked-muse-vulnerable-to-clickfix-popular-rust-developers-at-risk-and-new-attacks-against-rsa/ - Get Ready for Electronic Halloween with NeoPixel Jewel Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/25/get-ready-for-electronic-halloween-with-neopixel-jewel/ - Last 24 hours to save up to $200 on TechCrunch Disrupt 2026. Reason 5 of 5 to attend: Momentum Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/25/last-24-hours-to-save-up-to-200-on-techcrunch-disrupt-2026-reason-5-of-5-to-attend-momentum/ - Day 9: Learning JavaScript Variables, Operators & Functions 🚀 Source: devto-javascript Topic: JavaScript URL: https://dev.to/saravanan_cn_183fcba7cc7a/day-9-learning-javascript-variables-operators-functions-2gd8 - The pattern: Decoupling marketing copy from React components Source: devto-javascript Topic: JavaScript (+AI, PostgreSQL, React) URL: https://dev.to/pavan_s_poojary/the-pattern-decoupling-marketing-copy-from-react-components-5ain - Trump administration takes Musk’s side in fight over EU tech rules Source: ars-technica Topic: General URL: https://arstechnica.com/tech-policy/2026/09/trump-administration-takes-musks-side-in-fight-over-eu-tech-rules/ - Windows update leaves some virtual desktops staring into the void Source: theregister Topic: General URL: https://www.theregister.com/os-platforms/2026/09/25/windows-update-leaves-some-virtual-desktops-staring-into-the-void/5299106 - North Korean hackers suspected in $351M crypto theft, the largest so far this year Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/25/north-korean-hackers-suspected-in-351m-crypto-theft-the-largest-so-far-this-year/ - Security updates for Friday Source: lwn Topic: Open Source (+PostgreSQL) URL: https://lwn.net/Articles/1096637/ - The Next Big AI Model Can't Write a Single Sentence Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/renishb10/the-next-big-ai-model-cant-write-a-single-sentence-551p - Auto-saving extension data to the Downloads folder in Manifest V3: 8 things that broke Source: devto-javascript Topic: JavaScript URL: https://dev.to/elite_kid_4b64c2d2d87b228/auto-saving-extension-data-to-the-downloads-folder-in-manifest-v3-8-things-that-broke-3jc8 - Agents can now set up your website’s security with Turnstile Spin Source: cloudflare-blog Topic: General URL: https://blog.cloudflare.com/turnstile-spin/ - React PDF bbox Highlighting: Show RAG Citations on the Page Source: devto-javascript Topic: JavaScript (+AI, React) URL: https://dev.to/fangtanbamrung/react-pdf-bbox-highlighting-show-rag-citations-on-the-page-il9 - Stateless MCP Removes Session Affinity Requirements for AWS Server Deployments Source: infoq-architecture Topic: Architecture URL: https://www.infoq.com/news/2026/09/aws-stateless-mcp/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Architecture+%26+Design - Uncle Sam wants in on Musk's €120M fight with Brussels Source: theregister Topic: General URL: https://www.theregister.com/legal/2026/09/25/uncle-sam-wants-in-on-musks-120m-fight-with-brussels/5299123 - LAPL celebrates Latino Heritage Month #HispanicHeritageMonth Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/25/lapl-celebrates-latino-heritage-month-hispanicheritagemonth/ - OpenAI and Cursor agree on agent coordinators. They disagree on who runs them. Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/openai-cursor-coordinator-agents/ - Quiz: Jupyter Notebook: An Introduction Source: real-python Topic: Python URL: https://realpython.com/quizzes/jupyter-notebook-introduction/ - The Real Python Podcast – Episode #312: Navigating AI in Open Source: Insights From Wagtail Source: real-python Topic: Python URL: https://realpython.com/podcasts/rpp/312/ - Asahi fork embraces LLMs and lands Linux on the M4 Mac mini Source: theregister Topic: General (+AI) URL: https://www.theregister.com/os-platforms/2026/09/25/asahi-fork-embraces-llms-and-lands-linux-on-the-m4-mac-mini/5298931 - Amazon sellers watch as inventory vanishes into pending-order purgatory Source: theregister Topic: General URL: https://www.theregister.com/channel/2026/09/25/amazon-sellers-watch-as-inventory-vanishes-into-pending-order-purgatory/5298922 - Claude Spotted a DNA Pattern Scientists Had Overlooked Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/claude-dna-pattern-enzyme-discovery/ - BOFH: The Helldesk opens its third eye and ascends to a higher plane of troubleshooting Source: theregister Topic: General URL: https://www.theregister.com/bofh/2026/09/25/bofh-the-helldesk-opens-its-third-eye-and-ascends-to-a-higher-plane-of-troubleshooting/5298803 - Trump admin using AI to deny medical care for seniors in disastrous experiment Source: ars-technica Topic: General URL: https://arstechnica.com/health/2026/09/trump-admin-using-ai-to-deny-medical-care-for-seniors-in-disastrous-experiment/ - What Should Pine64 Build With Microcontrollers? Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/25/what-should-pine64-build-with-microcontrollers/ - Rocket Report: Era of cheap launch is over? Astra sets early 2027 target for return Source: ars-technica Topic: General URL: https://arstechnica.com/space/2026/09/rocket-report-era-of-cheap-launch-is-over-astra-sets-early-2027-target-for-return/ - From Agent Authorization to AI Production Evaluation: QCon AI New York 2026 Source: infoq-architecture Topic: Architecture URL: https://www.infoq.com/news/2026/09/qcon-ai-newyork-2026-sessions/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Architecture+%26+Design - Presentation: Spritely: Infrastructure for the Future of the Internet Source: infoq-architecture Topic: Architecture URL: https://www.infoq.com/presentations/spritely-decentralized-architecture/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Architecture+%26+Design - Dyfed-Powys Police cops to cyberattack, staff data potentially nicked Source: theregister Topic: General URL: https://www.theregister.com/cyber-crime/2026/09/25/dyfed-powys-police-cops-to-cyberattack-staff-data-potentially-nicked/5299112 - Another week, another data breach for Revolut customers Source: theregister Topic: General URL: https://www.theregister.com/cyber-crime/2026/09/25/another-week-another-data-breach-for-revolut-customers/5299092 - Compact Long-Wave Infrared camera pairs STM32N6 MCU with Lynred ATI320 thermal sensor Source: cnx-software Topic: Hardware URL: https://www.cnx-software.com/2026/09/25/compact-long-wave-infrared-camera-pairs-stm32n6-mcu-with-lynred-ati320-thermal-sensor/ - Meta's Connect turns into a Muse takeover Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/meta-connect-turns-into-a-muse-takeover - Spring AI RAG Tutorial with Spring Boot Source: java-code-geeks Topic: Java (+AI) URL: https://www.javacodegeeks.com/spring-ai-rag-tutorial-with-spring-boot.html - 😺 Meta unveiled Muse Charm, a pocket AI Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/meta-unveiled-muse-charm-a-pocket-ai/ - The Pentagon wants $30 million to build an AI-powered lie detector Source: mit-ai Topic: AI URL: https://www.technologyreview.com/2026/09/25/1145144/pentagon-ai-lie-detector/ - Judge uses electronic tag on Pokémon card tracker. It's super effective! Source: theregister Topic: General URL: https://www.theregister.com/offbeat/2026/09/25/judge-uses-electronic-tag-on-pokemon-card-tracker-its-super-effective/5298631 - How to Build Your First HTML Web Page: A Beginner-Friendly Step-by-Step Guide Source: devto-javascript Topic: JavaScript (+React) URL: https://dev.to/okoye_ndidiamaka_5e3b7d30/how-to-build-your-first-html-web-page-a-beginner-friendly-step-by-step-guide-3nik - 6 Git Signals That a Project Is About to Need a Refactor Source: devto-javascript Topic: JavaScript URL: https://dev.to/ke_jia_24bb2f9f84f14f728a/6-git-signals-that-a-project-is-about-to-need-a-refactor-db0 - Your files are in four places and nobody knows which one is right Source: theregister Topic: General URL: https://www.theregister.com/storage/2026/09/25/sponsored/5298972 - I Tried Every Snippet App for a Month. The Winner Was Not an App. Source: devto-javascript Topic: JavaScript URL: https://dev.to/ke_jia_24bb2f9f84f14f728a/i-tried-every-snippet-app-for-a-month-the-winner-was-not-an-app-l5b - 6 Git Signals That a Project Is About to Need a Refactor Source: devto-javascript Topic: JavaScript URL: https://dev.to/ke_jia_24bb2f9f84f14f728a/6-git-signals-that-a-project-is-about-to-need-a-refactor-el4 - UK wants more homes heated by waste heat from datacenters Source: theregister Topic: General URL: https://www.theregister.com/on-prem/2026/09/25/uk-wants-more-homes-heated-by-waste-heat-from-datacenters/5298827 - Show DEV: Building an Anonymous Instagram Profile & Story Viewer Without Logins Source: devto-javascript Topic: JavaScript URL: https://dev.to/x_z_e87b809fe996bc463fe4a/show-dev-building-an-anonymous-instagram-profile-story-viewer-without-logins-5fl2 - The .env File Is the Wrong Place to Think About Secrets Source: devto-javascript Topic: JavaScript URL: https://dev.to/ke_jia_24bb2f9f84f14f728a/the-env-file-is-the-wrong-place-to-think-about-secrets-54j4 - Scaffolded Dependencies Are Attack Surface: Auditing a New Project in 5 Minutes Source: devto-javascript Topic: JavaScript URL: https://dev.to/ke_jia_24bb2f9f84f14f728a/scaffolded-dependencies-are-attack-surface-auditing-a-new-project-in-5-minutes-6pc - Top 7 Sites To Buy iCloud Email Accounts in 2026 (PVA & ... Source: devto-javascript Topic: JavaScript URL: https://dev.to/mindl6743/top-7-sites-to-buy-icloud-email-accounts-in-2026-pva--3lf4 - Browser Tools vs Mobile Apps: Where Do Quick Dev Tasks Belong? Source: devto-javascript Topic: JavaScript URL: https://dev.to/ke_jia_24bb2f9f84f14f728a/browser-tools-vs-mobile-apps-where-do-quick-dev-tasks-belong-23c4 - degit vs npx: Which Way of Getting a Template Actually Scales? Source: devto-javascript Topic: JavaScript URL: https://dev.to/ke_jia_24bb2f9f84f14f728a/degit-vs-npx-which-way-of-getting-a-template-actually-scales-53a2 - Top 4 Site To Buy Outlook Accounts In This Year Source: devto-javascript Topic: JavaScript URL: https://dev.to/mindl6743/top-4-site-to-buy-outlook-accounts-in-this-year-5b7l - 9 Best Sites to Buy Hotmail Accounts (PVA, Bulk & Aged) Source: devto-javascript Topic: JavaScript URL: https://dev.to/mindl6743/9-best-sites-to-buy-hotmail-accounts-pva-bulk-aged-4bdp - Commodore 128 Becomes Marine Vessel Tracker Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/25/commodore-128-becomes-marine-vessel-tracker/ - Huawei Cloud Rolls Out Enterprise AI Products Across the Board, Building an Open Agentic Cloud Source: theregister Topic: General URL: https://www.theregister.com/ai-and-ml/2026/09/25/partner-content-huawei-cloud-rolls-out-enterprise-ai-products-across-the-board-building-an-open-agentic-cloud/5298765 - Russia's Hybrid Cyber-Physical War in Europe Heats Up Source: darkreading Topic: DevSec URL: https://www.darkreading.com/physical-security/russia-hybrid-cyber-physical-war-europe - Project leader thought his team understood the plan, ended up fixing their 'interpretation' of it Source: theregister Topic: General URL: https://www.theregister.com/networks/2026/09/25/project-leader-thought-his-team-understood-the-plan-ended-up-fixing-their-interpretation-of-it/5298754 - Performance Improvements in JDK 26 Source: baeldung Topic: Java URL: https://www.baeldung.com/java-jdk-26-performance-improvements - A Guide to Structured Output in Spring AI Source: baeldung Topic: Java (+AI) URL: https://www.baeldung.com/spring-ai-structured-output - GM’s Experimental EV from 1969 Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/24/gms-experimental-ev-from-1969/ - Lightspeed targets $250M for new India fund, focusing on early-stage AI Source: techcrunch Topic: General URL: https://techcrunch.com/2026/09/24/lightspeed-targets-250m-for-new-india-fund-focusing-on-early-stage-ai/ - Everything That Happened in AI Today (Thursday, September 24, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-today-thursday-september-24-2026/ - Claude Opus 5.5 Broke Our GPT-6 Benchmark: Full Livestream Guide with Demos, Prompts & Timestamps Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/explainer-articles/claude-opus-5-5-vs-gpt-6-sol-demos-prompts-timestamps/ - 2026 just became the year of FreeBSD on the (Amazonian cloud) desktop Source: theregister Topic: General URL: https://www.theregister.com/os-platforms/2026/09/25/2026-just-became-the-year-of-freebsd-on-the-amazonian-cloud-desktop/5299025 - Fuzzy search in Postgres with pg_trgm and Supabase (multilingual, typo-tolerant) Source: devto-javascript Topic: JavaScript (+Information Retrieval, PostgreSQL) URL: https://dev.to/thiagolongom/fuzzy-search-in-postgres-with-pgtrgm-and-supabase-multilingual-typo-tolerant-2ipf - React Signup Tests: Make Email State Observable Source: devto-javascript Topic: JavaScript (+React) URL: https://dev.to/ryanlee91/react-signup-tests-make-email-state-observable-4n9o - The Modern Pragmatic Web: Mastering HTMX and Alpine.js Source: devto-javascript Topic: JavaScript (+React) URL: https://dev.to/digitalgh0st/the-modern-pragmatic-web-mastering-htmx-and-alpinejs-3i3g - Zero updated rows do not fail a D1 batch: testing the rollback boundary Source: devto-javascript Topic: JavaScript URL: https://dev.to/hirodeath/zero-updated-rows-do-not-fail-a-d1-batch-testing-the-rollback-boundary-3odn - FPGA for All — CERN Releases “colibri” VHDL Library Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/09/24/fpga-for-all-cern-releases-colibri-vhdl-library/ - MemBrowse continuously tracks firmware memory footprint, is free for open-source projects Source: cnx-software Topic: Hardware URL: https://www.cnx-software.com/2026/09/25/membrowse-continuously-tracks-firmware-memory-footprint-is-free-for-open-source-projects/ - How OmniGIF Removes GIF Backgrounds Entirely in the Browser Source: devto-javascript Topic: JavaScript URL: https://dev.to/sunkehappy/how-omnigif-removes-gif-backgrounds-entirely-in-the-browser-5e23 - 15 Practical HTMX Project Ideas to Master Hypermedia published Source: devto-javascript Topic: JavaScript URL: https://dev.to/digitalgh0st/15-practical-htmx-project-ideas-to-master-hypermediapublished-27ia - List Comprehensions: The Matrix of Python Magic Source: devto-javascript Topic: JavaScript URL: https://dev.to/timevolt/list-comprehensions-the-matrix-of-python-magic-4i5m - Day 8: HTML Media Tags & Starting My JavaScript Journey 🚀 Source: devto-javascript Topic: JavaScript URL: https://dev.to/saravanan_cn_183fcba7cc7a/day-8-html-media-tags-starting-my-javascript-journey-1f9e - UUID v4 vs. UUID v7: Was ist der Unterschied? Source: devto-javascript Topic: JavaScript URL: https://dev.to/uuidtools/uuid-v4-vs-uuid-v7-was-ist-der-unterschied-5d3k - Co-Living PG and Hostel in Knowledge Park 2 Source: devto-javascript Topic: JavaScript URL: https://dev.to/thehotelproperties/co-living-pg-and-hostel-in-knowledge-park-2-2m6k - I built a free image and PDF toolkit that runs entirely in the browser Source: devto-javascript Topic: JavaScript URL: https://dev.to/sabbirhossain02/i-built-a-free-image-and-pdf-toolkit-that-runs-entirely-in-the-browser-aaa - AdCP Scopes the Buy in adagents.json. OpenRTB imp Does Not Carry That Scope Back. Source: devto-javascript Topic: JavaScript URL: https://dev.to/aleksuix/adcp-scopes-the-buy-in-adagentsjson-openrtb-imp-does-not-carry-that-scope-back-4kkg - CircuitPython 11.0.0-alpha.1 Released! Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/24/circuitpython-11-0-0-alpha-1-released/ - Raspberry Pi 5 TV HAT Case with Pimoroni NVMe #3DThursday #3DPrinting Source: adafruit-blog Topic: Hardware URL: https://blog.adafruit.com/2026/09/24/raspberry-pi-5-tv-hat-case-with-pimoroni-nvme-3dthursday-3dprinting/ - Change your components, keep your infrastructure Source: pulumi-blog Topic: DevOps URL: https://www.pulumi.com/blog/component-state-migrations/ - Signals come to React-Redux Source: react-status Topic: React (+JavaScript) URL: https://react.statuscode.com/issues/492 - Advanced soft-bodies for games with the Rapier physics engine Source: this-week-in-rust Topic: Rust URL: https://dimforge.com/blog/2026/09/25/advanced-soft-bodies-for-games-in-the-rapier-physics-engine/ - Rust Reborrowing, Aliasing, and Mutable References Source: this-week-in-rust Topic: Rust URL: https://developerlife.com/2026/09/25/rust-reborrowing/ - Google's space datacenter 🛰️, Bezos $30B bet 🚀, CPU shortage 💻 Source: tldr-tech Topic: General URL: https://tldr.tech/tech/2026-09-25 ## Research - 10 Things I’m Learning Beyond AI to Become More Technologically Fluent Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/10-things-im-learning-beyond-ai-to-become-more-technologically-fluent/ - Your Model's MSE Is Lying to You: Part II Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/your-models-mse-is-lying-to-you-part-ii/ - RAG Isn't an Agent — I Built the Layer Between Retrieval and Action Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/rag-isnt-an-agent-i-built-the-layer-between-retrieval-and-action/ - Jev vs. LLMs: When AI Moves from Generation to Decision-Making Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/jev-vs-llms-when-ai-moves-from-generation-to-decision-making/ - MQSS-Selector: RL-Guided Pass Selection for an MLIR Compilation Pipeline Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30104 - Generalized Graph Variational Autoencoders: Bounded Divergences Control Posterior Collapse Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29546 - MLPerf Automotive Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.27065 - Continuous Online Fault Detection for Mobile Robots via Adaptive Edge Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29194 - UltraBench 2: Towards Robust Evaluation of Vision Foundation Models on Ultrasound Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28610 - Stacked SVD or SVD stacked? A Random Matrix Theory perspective on data integration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.22170 - Learning Generalizable Behaviors for Terminal Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22631 - Named Entity Recognition using Sliding Window Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29682 - IatroBench: A Pre-Registered Benchmark of Clinical Omission in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.07709 - On Cost-Aware Designs for Sequential Hypothesis Testing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.19067 - Beyond Average Safety: Chance-Constrained LLM Fine-tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29960 - FlowAtom: Atom-Based Evidence Aggregation for Multi-Label Website Fingerprinting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29330 - Speculative Evaluation of Stochastic LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28560 - VG-TIE: An interpretable tabular-to-image encoding method based on visibility graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29650 - Sample-Weighted End-to-End Trace-Norm Geometry for Multitask Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29520 - DCRMTA: Deep Causal Representation Learning for Multi-Touch Attribution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2401.08875 - A Multimodal 3D Foundation Model for Light Sheet Fluorescence Microscopy Enables Few-Shot Segmentation, Classification, and Deblurring Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26026 - Evaluation of Multi-Turn Consistency in LLM Agents: Survival Analysis and Failure-Rationale Taxonomy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29508 - Elucidating the Conformal Structure of the Brinkman Penalisation Method for Geometry-Adapted, Structure-Preserving Operator Learning of Hamiltonian PDEs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29847 - ASIRF: An Agentic Framework for Context-Dependent Sensitive Information Redaction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29191 - EvoTreeNAD: Genealogy-Guided Evolution for LLM-Driven Neural Architecture Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29016 - When Temporal Perturbations Act Like Sensor Biases: Label-Free Auditing of Wearable Activity Recognizers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29937 - Predicting Symptoms of Amotivation and Anhedonia among University Students with a Novel Oversampling Method Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29690 - A Neural Hierarchical-Matrix Preconditioner for Real-Time GPU Solves Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13343 - TAM-Chain: Multi-Scale Thyroid Cytology Classification via Absorbing Markov Chains and Shannon Entropy Uncertainty Quantification for False-Negative Suppression and Domain-Shift Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28590 - Learning a Flow to Self-Supervised Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29350 - Time-Varying Bayesian Optimization Without a Metronome Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.18963 - Direct Message Approximation (DMA): A Consistency-Based Framework for Tractable Approximate Inference on Factor Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29466 - Learning and interpreting policies for simultaneous entanglement requests in quantum networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30157 - Online Task Adaptation via Self-Organisation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29281 - GeoDose-CP: Graph-Local Conformal Inference for Continuous-Treatment Earth Observation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28895 - Response-state Learning for Transferable Vibrational Spectroscopic Characterization with Electron Prior Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28935 - Improving the Last-Iterate Guarantees of Anytime Algorithms for Stochastic Monotone Variational Inequalities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15257 - Where Does Exactly-Once Live? Model, Harness, and Tool-Contract Effects on Duplicate Side Effects in LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29095 - Let Training Guide Selection: Online Synthetic Data Filtering via Real-Anchored Utility Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29988 - Scaling of Capability and Efficiency at Inference Time in Large Reasoning Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27166 - Time-Series Foundation Models That Understand Data Revisions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28576 - How Many Humans Are 32 LLM Judges Worth? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21277 - Spatio-temporally complementary feature propagation on graphs for longitudinal AADT estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29906 - Diffusion-aided Task-oriented Semantic Communications with Model Inversion Attack Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.19886 - Task-Resolved Fisher Spectroscopy for Quantum Reservoir Computing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29570 - AIR: Analytic Imbalance Rectifier for Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2408.10349 - GCUL: Ambiguity Identification in Text Emotion Classification via Cluster-Guided Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29327 - Quantum Attention by Overlap Interference: Predicting Classical and Many-Body Quantum Sequences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.06699 - Federated Learning of AnDE Classifiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28695 - Beyond Model Size: Redesigning LiSenNet for embedded speech enhancement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29866 - GridSFM: A Foundation Model for Solving AC Optimal Power Flow Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30173 - GBFRVFL: Granular-Ball Computing-Based Fuzzy Random Vector Functional Link Network Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29670 - Beyond Static Graph World Models: Learning Stochastic Latent Dynamics over Evolving Topologies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28670 - Learning tactile perception from high-bandwidth single-point sensing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24621 - Too Sure to Be Safe: Model Calibration for Reliable Log Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.17965 - No Free Lunch in Flow Surrogates under Time-Varying Boundary Conditions: A Two-Regime Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.23667 - Dynamic Generalized Gromov-Wasserstein Optimal Transport Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20008 - From Text Decisions to Pixels: An Study of Jev-Style Visual Choice Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29283 - DecoVAE: a Lightweight Interpretable Trend-Seasonal VAE Framework for Efficient Probabilistic Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20052 - A Concentration Bound for Two-Timescale Actor-Critic Algorithm Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29117 - Foundations of Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.09223 - Intrinsic-Extrinsic Coupling in Learning Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30185 - QUARTET: Quad-branch cross-Attention and Random-walk Traces for Enhancing Transformers on Relational Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26855 - A New Gap Sequence for Shellsort: RL-Driven Algorithm Discovery Beyond $N^{4/3}$ Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29881 - SechKAN: Kolmogorov-Arnold Networks with Hyperbolic Secant Functions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.18290 - Aim Short to Reach Far: Your Frozen World Model Can Plan Better Than You Think Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30036 - Decoupled Learning and Selection in Slate Recommendation for Privacy and Stability Under Noisy Scores Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29453 - A Computational Framework for Modelling Organisation-Level Semantic Identity from Longitudinal Textual Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29584 - Operator Packages, Proposer Strength, and Construction-Family Plateaus in Office-Scale Verified Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29636 - Does a model's stated reason for rejecting a candidate do any work? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30151 - An Exposition of GPT Astra's Proof of Lower Bound on DP Continual Counting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28528 - DeGRe: Dense-supervised Generative Reranking for Recommendation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25749 - The Sharp Tail of Uniform Stability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24098 - RLVR landscapes for iterated multiplications can be benign: Insights from spin-glass theory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28625 - Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18366 - SpaFactor: Lightweight Spatial Context-Aware Gene Program Modeling for Histology-to-Transcriptomics Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28563 - Leakage-Safe Machine Learning for Hydrogen Embrittlement Detection in 316L Stainless Steel: A Region-Held-Out Evaluation of Texture and Deep Features in SEM Micrographs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28567 - Improving Calibration of Black-Box Radiology AI Using Test-Time Augmentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29931 - CataOPD: Catalytic On-Policy Distillation for Large Language Model Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29518 - Certified Predictive Value-of-Advice Gating for Cost-Aware Language-Model Guidance in Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29548 - An Exploratory Ablation of a Small MLA--SSM Hybrid Language Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29618 - Automatic Harness Evolution for Hardware Design Verification: Can LLMs Consolidate Gains Across Discovered Harnesses? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28908 - Calpric: Inclusive and Fine-grain Labeling of Privacy Policies with Crowdsourcing and Active Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2008.02954 - Decoupled Early Exits for Task-Dependent Compute Allocation in Flow-Matching VLAs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29382 - Graph-Based Inference and Topology-Aware Multi-Agent Reinforcement Learning for Large-Scale Railway Network Management Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30150 - Functional dynamic mode decomposition: Learning infinite-dimensional systems from data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29159 - Enabling Approximate Joint Sampling in Diffusion LMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.22738 - GHOST-Q: Towards Studying Grounding Hallucinations Overlooked Under Same-score TradeOffs in Quantized VLMS Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29999 - A hybrid analytical-PINN model for subsurface simulation of geothermal heat exchangers in heterogeneous underground Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.12271 - On Growth and Form, and Function: Reusable Regulatory Handles Control Phenotypic Variation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29755 - NS-ATTENTION: Newton-Schulz Transformations of Attention Outputs in Vision Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27735 - Learning to Fluctuate: Statistical Foundations for Causal Tabular Pretraining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26290 - Uncertainty-Gated Exploration Noise Suppresses Task Collapse in Online RL Fine-Tuning of a Flow-Matching Vision-Language-Action Policy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28838 - REARL: A Closed-loop Autonomous Driving Simulation Enhancement Framework with Real Traffic Data and Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19903 - MORE-PLR: multi-output regression employed for partial label ranking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29386 - CARE: Condition-Aware Representation Regularization for Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28561 - Spectral-Guided Diffusion: Accelerating Inference via Static Spectral Layer Scheduling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29505 - Path-specific harm decomposition: A partial identification framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29938 - Classifier-Dependent Benefits of Pseudo-Labeling for Semi-Supervised Android Malware Attribution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29564 - CORDIAL: Calibrating Ordinal LLM Outputs from Few Labels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29807 - An Analytical Theory of Auxiliary Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29774 - When Does Unsupervised Learning Succeed or Fail? A PoS Perspective on Reconstruction-Based Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28832 - fable.intermittent: benchmarking probabilistic forecasting methods for intermittent time series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28607 - Same Bit Width, Different Outcomes: Post-Training Quantization of Text-to-Speech Across Architectures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28974 - Beyond Compression: Training Latent Representations for Stable Long-Horizon Rollout in Neural Surrogate Solvers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30198 - SPADE-DFL: Communication-Efficient Decentralized Federated Learning via Derivative-Free Linearized ADMM Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29446 - From Processing to Functionality: Engineering Accessible Material States in Cu-Embedded SiO$_x$ Memristive Devices Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30047 - Safety-oriented pedestrian trajectory prediction at urban intersections using time-to-collision and crossing-zone context Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29706 - Sufficiently Reduced Distributional Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29291 - Learning to Discover Interesting Mathematics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28603 - When Identical Rows Disagree: From Benchmark Identifiability to Replication-Robust Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29580 - Beyond Pairwise Attention: Higher-Order Modular Attention for Efficient Sequence Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.11133 - RRSI: Regularized Recursive Self-Improvement of Agent Harnesses Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24972 - 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 - Stream Recursion Model (SRM) Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28809 - TopU-LBVS: A Realistic Multi Target Benchmark for Ligand Based Virtual Screening Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29740 - Orbital Error Dynamics: Self-Organized Criticality, Ephemeral Parameter Resonance, and Non-Linear Biological Ontologies in Zero-Storage Neural Synthesis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30115 - The Mechanics of Delta Learning: Target Design for Generalizable Scientific Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28782 - PoEM: Predicting RL Outcomes from Existing Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30226 - Aftab: A Progressive Design Study of Visual Encoders and Value Estimation for Replay-Free Parallelized Q-Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.07335 - Evaluating Cross-region Generalization for Wavelet-Diffusion Precipitation Downscaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28749 - NumericJev: Jev-like LLM Numerical Decoding with Multiway Decision Trees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28587 - Robust Detection of LLM-Generated Text under Contamination Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29935 - BranchShine-CR: Compact Multilingual IPA Transcription with Self-Conditioned CTC and Consistency Regularization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29069 - Transcript-Supervised Post-Training of Generative Speech Enhancement on Real Recordings via Reinforce Adjoint Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29405 - RADAR: Readiness for AI Discovery and Agentic Reach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28480 - Exact Bayes Regret and Asymptotic Optimality in High-Dimensional Gaussian Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28718 - Policy Complexity, Reaction Time, and Bounded Rationality in Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28737 - LabFactory: Building and Evaluating Executable AI Labs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28697 - DEEPO: Dual-Entropy Enhanced Policy Optimization for Hallucination in MLLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28570 - Learning Causal Structure of Time Series using Best Order Score Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.05370 - A Manifold-Aware Topic Modeling Approach via Rank-Based Prototypes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29630 - On the second-order optimization for spiking neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29379 - HClimRep-Ocean: A Global Ocean Emulator on an Unstructured Mesh Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28601 - Invertible Query-Key Coupling Composes with Attention Mechanisms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.01683 - FlashLoop: Fast and Memory-Efficient Looped Transformers via Lazy Updates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29812 - Gradient Networks for Universal Magnetic Modeling of Synchronous Machines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.14947 - A Multi-level Information Integration Framework for Physically Verifiable Fault Diagnosis of Rotating Machinery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22797 - An Order-Theoretic Characterization of Consistent Inductive Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28551 - GRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30147 - Machine Unlearning for Gibbs Supervised Learning Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29409 - Multiscale Reward Hedging from Correct Demonstrations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06825 - MF-SCBO : Multi-fidelity Scalable Constrained Bayesian Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29941 - Three Ways Classical Test Theory Misleads for LLM Judges Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29709 - Agentic Detection of Online Conspiracies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30250 - Auditing Bayesian Graph Alignment: Diagnostic Comparisons and Reference Failure Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23232 - SLCA-GRPO: Resolving Cross-Segment Credit Misattribution in Tool-Calling RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29050 - Technical Manual for Toolkit for Confidence-Corpus Consistency via Fine-Tuning on a Fabricated Corpus Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28747 - Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.04317 - Edge AI on Constrained Devices for Binary Sleep-Wake Classification in Dynamic Environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29163 - Deep Positive-Unlabeled Anomaly Detection for Contaminated Unlabeled Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2405.18929 - Learning from Mixed-Quality Deployment Experience for Robot Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29000 - Beyond Feature Reliability: Repeat-Informed Multifractal Curve Regression for Brain-Age Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29307 - SMILESGNN: Interpretable Clinical Toxicity Prediction via SMILES-Graph Cross-Attention Fusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28553 - Minimally Invasive Steering of Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30218 - How Weight Encoding Affects Language Model Placement and Performance on the Apple Neural Engine Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22110 - Physics-Informed Self-Supervised Learning for Joint Wire Calibration and Interaction Position Reconstruction in Multi-Wire Parallel Plate Avalanche Counters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28604 - Neuralized Multi-Wavelet Decomposition for Time Series Classification and Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29317 - A JoLT for the KV cache: Near-Lossless KV Cache Compression via Joint Rank-bit Allocation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.12550 - CatSIM: A Categorical Image Similarity Metric Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2004.09073 - J-Zero: Unified Challenger--Solver--Judge Self-Evolution from Zero Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26582 - Distillation for Efficient Multitask Manipulation Policies via Conditional Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28107 - RQ-Reg: A Residual-Quantization-Based Framework for Continuous Value Prediction in Recommender Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.23012 - Improving global precipitation forecasts with an AI weather model trained on satellite observations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03210 - Upholding Robustness in Federated Learning: Trends, Emerging Strategies, and Research Opportunities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28722 - Certified Task-Conditioned Active Observability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28520 - An Agnostic Sample Compression Scheme for Squared Loss of Near-Linear Size in the Fat-Shattering Dimension Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29696 - Complete Neural Electronic Initialization Accelerates Materials DFT Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21759 - SGA: Uncertainty Quantification for Multi-Step Forecasting in Time Series Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28582 - RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28850 - Every Component Is a Lookup: One Linear Graph for Interaction, Composition and Attribution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23393 - TIDE: Temporal Incremental Draft Engine for Self-Improving LLM Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.05145 - Capturing Unseen Spatial Heat Extremes Through Dependence-Aware Generative Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.09211 - StationPDE: Station-Oriented Surface PDE Learning for Multi-Station Multivariate Weather Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22123 - Decoupling Knowledge and Privacy: Post-Task Self-Distillation Replay for LLM Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29711 - Does per-frame early exit pay? A compute-matched study of dynamic depth for on-device speech enhancement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29867 - Physics and Data Driven Transformer-Mamba Framework for Flow Field Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29087 - PartHackBench: Certified Equal-Progress Stress Tests for Partial-Credit Tool-Agent Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29578 - Generative Atmospheric Super-Resolution from Heterogeneous In Situ Observations through Composable Interfaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29027 - Near-Oracle KV Selection via Pre-hoc Sparsity for Long-Context Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.08329 - Revalidation Beats Stateful Routing for Scientific Surrogates Under Distribution Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29715 - Do Audio Language Models Hear and Read Distinctive Features Alike? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30167 - Hybrid Variational Quantum-Classical Framework with Adaptive Weighting and Efficiency Assessment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28491 - Rufus-Air: An Open LLM Post-Training Recipe Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29421 - Error- and Prediction-Driven Motor Learning in the Cortico-Cerebellar Loop Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29945 - TERN: A Delta-rule Memory with a Seasonal Reference and Online Adaptation for Epidemic Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18407 - CFD Correction of Open Tip Clearance Flow in a Compressor Cascade Using VAE Latent Space Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28558 - Neural Transport Nested Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29413 - Stochastic Inertial Krasnosel'skii-Mann Iteration Achieves Near-Optimal Sample Complexity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28543 - Agent Memory with Episodic Retrieval for Financial Decision-Making Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28771 - Segment-Level Risk Discovery in Online Handwriting for Alzheimer's Disease Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29384 - Sequential knowledge editing breaks a model's ability to tell good evidence from bad, without costing it accuracy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29587 - When Does Action Credit Need Updating? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29007 - RoboLDA: A Probabilistic Generative Model for Uncovering Embodied Hierarchical Structures in Voxel-based Soft Robots Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29490 - Topological Signatures of Cyber-Attack Classes in Natural Visibility Graph Representations of Network Traffic Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26990 - MOOSEnger: A Simulation-Aware AI Agent Framework for the MOOSE Ecosystem Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.04756 - AgriCountDINO: Parameter-Efficient Exemplar-Guided Counting and Localization in Agriculture Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29460 - AD-WM: Action-Discriminative World Models for Counterfactual Model Predictive Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30264 - Detecting Glaucoma Across Multi-ethnic Myopic and Non-Myopic Populations Using an Uncertainty-Aware Vision Transformer: A Multicentre Model Development and Validation Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29433 - DENSE: Distilling Agent Trajectories into Evidence-Grounded Shortcut Trees for Self-Refinement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21423 - Less is More: Encoder-only Audio-Visual Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29121 - HEXIS: Compiling Skills into Extended Finite State Machines Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.30123 - Instrumental Monitor Evasion Emerges Under Ordinary Task Pressure Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30217 - Deep Learning-based 3D Oral Cavity Reconstruction Using 2D Intraoral Images Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05998 - Adversarial Closed-Loop Curriculum for Evolving Role-Playing Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28609 - Where Cyber Agents Struggle: Bottleneck Analysis of Multi-Stage LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28572 - Is Reasoning Always Useful? Rethinking Reasoning Utility in Universal Multimodal Embeddings Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29560 - World Action Agent: Harnessing VLMs for Robot Manipulation via World Action Rehearsal Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29964 - Decision Hijacking: Prompt Injection Attacks on Jev's Typed Probabilistic Decisions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28613 - Cross-Modal Emotion Understanding: A Transformer-GAT Approach for Dialogue Emotion Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29556 - KathDB-FAO: Synthesized Query Plans in a Multimodal DBMS Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28761 - From Static Personal Values to Contextualized Personalization: Bayesian Personalized Value Alignment for LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28942 - JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.14777 - When No One Owns the Judgment: Accountability Under Contribution Dissolution in Human-AI Collaboration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29312 - Band-Attention Modulation Network for Robust Face Forgery Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2404.06022 - ERRAND: Budgeted Maintenance of Agent Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29545 - Epistemic-Probabilistic Model for Guarded Multi-Agent LLM Coordination Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29366 - Answering Path Queries under Linear and Guarded Existential Rules Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22636 - Underwater C3-JEPA: An Object-Centric Cross-View World Model for ROV Salvage Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30214 - TWIST: A Proposed Benchmark for Intervention Quality in Conversational Memory, with a Human-Validated Draft-Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28575 - Towards An LLM-Driven Unified Conversion Framework for BT and FSM in Autonomous Intelligent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29228 - SkinAgent AI: A Safety-Grounded Multimodal Agentic Framework for Non-Diagnostic Skincare Support Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29341 - CoSWA-YOLOv12: Scale-Invariant Tiny Object Detection and Segmentation of Malaria Parasites Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29527 - AI in Science: Early Insights Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28504 - EnigmaForge: The Question Is Hidden in the Story Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30144 - Hard Stop: Kernel-Level Preemption and Containment for Rogue Agentic Execution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29808 - CounterRoute: Self-Routed Reasoning via Hierarchical Counterfactual Credit Assignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29109 - ALOE: Semantically Addressed Low-Rank Operators for Knowledge Editing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29269 - A General Framework for Budgeted Threshold Incentives on Request Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29724 - Hyperbolic Multimodal Continual Learning: A Closest-Admissible Solution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29329 - Progressive Skill Discovery as Access Control for Tool-Using LLM Agents: Structural Governance through Role-Scoped Capability Delivery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28693 - From Self-Distillation to Self-Practice: Privileged Information for Multi-Turn Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29051 - BaseCamp --- An Agentic AI Framework for Automating DNA Sequencing Data Pipelines Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28557 - On the Effectiveness of Kernel-Level Evidence for Agent Security Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28915 - Who Is Behind the Harness? Fingerprinting LLMs through Agentic Behavior Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28559 - Novelty Adaptation Through Hybrid Large Language Model (LLM)-Symbolic Planning and LLM-guided Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.11351 - DocuTeam: Mixed-Initiative Multi-Agent Discussions around Evolving Documents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29309 - Working with Agentic `Teammates': When a New Organizational Actor Collides with the Human Ecosystem of Work Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29901 - ELiSe: Efficient Learning of Sequences in Structured Recurrent Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2402.16763 - Evolve Vision-Language-Action Model into an Agent with On-the-fly Tool-use Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14047 - Accelerating Video Diffusion via Training-Free Trajectory Routing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30096 - Beyond Simple Input-Output Assessment Tasks: Leveraging Automated Programming Assessment for Non-Trivial Courses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29363 - SheetMind: Actions Set Accuracy, Agents Set the Failure Mode Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.12339 - Domain Recentering and Confidence-Weighted Prior Calibration for Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29358 - Ontology-Mediated Neurosymbolic Constraint Acquisition from Multiple Stakeholders Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29876 - AgentKernel: The Trust-Native Agentic Operating System Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29647 - Refusing Everything Looks Safe: Restoring the Benign Arm to Encoded-Prompt Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26176 - AgileLog: A Forkable Shared Log for Agents on Data Streams Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.14590 - ENDOPROMPT: Victim-Side Pseudo-References for Utility Degradation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29948 - The Gold in Bias: Maturing the AI Design Process through Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29730 - PEEL: Physics-Enabled Evidential Learning for Identifiable Uncertainty in CT Imaging Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29599 - Requirement-Bound Verified Commissioning: A Frozen Four-Billion-Parameter Local Model as a Candidate Generator under an External Acceptance Layer with Verification and Release Authority Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30219 - Right Choice of Classification Algorithms Based on Reinforcement Learning for Prediction of Non-Alcoholic Fatty Liver Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29181 - NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03159 - Neural-Network Solutions to Real-Space Charge Density and Generalization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14906 - A Risk-Adaptive and Evidence-Constrained Framework for Generative AI Feedback in Programming Education Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29874 - Rolling-WAM: World Action Models with Rolling Imagination Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30247 - Human-AI-Powered Hypothesis Testing: Cost-Aware Selective AI Scoring and Sequential Human Escalation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28859 - Omni-Decision: Evidence-Ledger Planning for Omni-Modal Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.11433 - Back to the Definition: Estimating Step-Level Advantages via Trajectory Graphs for Agentic Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28963 - Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.17174 - Beneath the Scores: Rethinking Hallucination Evaluation for Video Understanding Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28991 - TARL: Transaction-Aware Reliable Ledgers for Executable Memory Management in Long-Term Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.03699 - Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29892 - Understanding and Exploiting Initialization Anchoring Weakness in Feedback-Based Agent Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29697 - DrGait: Biomechanically Grounded Visual Reasoning for Interpretable Clinical Gait Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28796 - Guardrails or Roadblocks? Effects of Pedagogical Style and Context Awareness in AI Teaching Assistants for Programming Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29995 - A Living Benchmark for Information Retrieval from Electronic Health Records Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.30205 - QINA: Quantum-Inspired Nonlinear Adapters for Pretrained Vision Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29592 - VLANeXt: Recipes for Building Strong VLA Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.18532 - WST-Graph: Topology-Preserving Wavelet Scattering Front-End for Speech Deepfake Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29372 - Sharp Limits for Honest Uncertainty in Hard-Budget Repeated Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29140 - Fair Like Us? Auditing LLM Alignment in Resource Allocation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29692 - Template Ageing and Longitudinal Verification in Fixed-Text Keystroke Dynamics: A Subject-Disjoint Study Across Eight Weeks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29851 - A Wrong Turn Does Not Ruin the Journey: Deviation-Guided Skill Self-Evolution for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29154 - 3D Oral Modelling with Improved Vertex Distribution Using Matching-Based Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07907 - Training Object Permanence in World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28654 - The Troy Moment: How LLM Agents Adjudicate the Decision Point Under Impossible Tasks, Claimed Authority, and Peer Information Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15494 - The Tokens Remember: When Tokenization Bypasses Knowledge Editing and Unlearning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29045 - Cryptographically verifiable authorization for autonomous AI agents: a falsifiable hypothesis and proof of concept Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.21325 - Broadening Uncertainty Estimation for Audio Question Answering Across Methods, Formats, and Inputs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28879 - The Convention Gap: Towards Measuring Implicit Communication in Cooperative AI Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.11489 - Type-Safe Is Not Error-Free: A Constrained Decision Head Follows the Option Name, Not the Rubric Bound to It Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26758 - PAWS: Policy-driven Agentic World Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28547 - Search-Based Software Engineering and AI Foundation Models: Current Landscape and Future Roadmap Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.19625 - Step Recursion: Exact Depth Does Not Determine Algebraic Expressiveness Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2609.29586 - A Polynomial-Time Test for Peak-Oriented Rationalizability Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2609.30042 - A General Composition Theorem for Approximate Degree Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2609.30139 - Exact Quantum Circuit Optimization is co-NQP-hard Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2510.16420 - Quantum Query Advantage Requires Space Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2609.29497 - Lossless Hardness Condensation in Deterministic Communication Complexity Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2609.28691 - Exponential Correlation Bounds for Polynomials Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2609.28839 - Complexity of Quadratic Bosonic Hamiltonian Simulation: BQP-Completeness and PostBQP-Hardness Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2603.26561 - An $n^2\log\log n$ Lower Bound for Permanent Circuits with Valid Division Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2609.29568 - Step Recursion: Mixed Stride Spectra, Path Factorization, and Synchronization Geometry Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2609.29585 - The Complexity of Multiplayer Colonel Blotto Games with Player-Specific Values Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2609.30019 - NP-Hardness of Bounded Distance Decoding for Reed-Solomon Codes Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2609.29120 - Constant-Probability Witness Isolation Implies $\mathrm{NP}\subseteq\mathrm{P/poly}$ Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2609.29302 - Convex Networks Remain Hard to Certify: Dimension-Accuracy Barriers for Lipschitz Constants Source: arxiv-cs-cc Topic: Algorithms URL: https://arxiv.org/abs/2608.16150 - Where LLM Graders Succeed and Break: Evidence from Two Computer-Science Exams Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29333 - Self-Play Pretraining with Zero Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30063 - Cultural Divergence Preservation: Diagnosing Flattening and Caricature in LLM-Simulated Survey Populations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29928 - Likelihood Ranking doesn't Scale Like Prompting in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29390 - Who Put the I in AI? Provenance and the Admissibility of Machine Self-Report Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29494 - Augur: A Synthetic Decision Lab for Rehearsing Reactions to Product and Policy Changes Source: arxiv-cs-cl Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.29952 - Design and Evaluation of LLM Chaining-Based Task Planning for General Purpose Service Robots Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29043 - MeshHeal: Two-Timescale Self-Healing for Gray Failures in Decentralized LLM Agent Networks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29015 - R-DEIM Net: An Efficient Rationale-Augmented Dual-Expert Interaction Model for Paraphrase Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30100 - Accent Analogy Guidance: More Speaker Similarity at Equal Accent in Cross-Lingual Voice Cloning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29123 - Style, Not Self: Surface Cues Explain Zero-Shot Code Attribution by Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30048 - YODAS v3: Over 1 Million Hours of High-Bandwidth, Stereophonic, Multilingual Speech Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29448 - Screen Before You Serve: Simulation for Production Customer Experience AI Agents at 140M Scale Source: arxiv-cs-cl Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.30137 - Baseline Shape Decides the Verdict: A Controlled Re-Examination of Ternary Language Models at 60K Parameters Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29397 - ARGUS: Role-Aware Event Knowledge Graphs for U.S. Employment-Discrimination Complaints Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30184 - DP-IPI: A Hybrid Differential Privacy Text Rewriting Mechanism for Indirect Personal Identifiers in Clinical Texts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29684 - Learning New Words from Unlabeled Test Data in Automatic Speech Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28877 - An Evaluation Framework for Structured Audio Captions Validated by Controlled Perturbations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.21424 - MultiViewDx: Evidence-Linked Multi-View Clinical Diagnosis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.14948 - Reasoning Instructions Can Break Answer Decoding in Vision--Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29278 - Human Agreement and Return Association Are Not Interchangeable Criteria Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.11144 - Benchmarking Argumentative Behaviour of LLMs: A Study of Defences Against Character Attacks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28673 - Script Choice in LLMs: Evidence for Late-Layer Commitment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28784 - Scoring Both Directions: LLMs realize the MRS they cannot reliably parse Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30071 - LLM Forensics: Where Do Backdoors Hide? Localizing and Controlling Trigger Mechanisms with Sparse Autoencoders Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07746 - Two Emojis of Difference: What Multilingual Affective Generation Benchmarks Actually Measure Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29445 - Qwen-Audio-3.1-Realtime: Towards Reliable Agentic Voice Interaction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.25176 - Predicting Emerging Topics from Outliers: A Prospective Study of Weak Signals in Embedding Space Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29183 - How broad is that claim? Mapping Generalisation in NLP Research Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14770 - pylazaro: a Python package for anglicism extraction in Spanish Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29276 - LOCKR: A Hidden-State Trajectory-Guided Planner for Detecting and Repairing Stable-but-Wrong Lock-In in Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27220 - Personalized Korean Lipreading as Visual Speech Recognition: Transfer, Census and Adaptation on OLKAVS Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28988 - MILO: Efficient Many-shot In-Context Learning with Block-wise Low-rank Compression Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29913 - ChunkRank: Model-Aware Text Chunking and Abstention-Aware Answer Selection for LLM Pipelines Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29828 - LLMersion: A Local-First AI Agent Framework for Low-Cost Home Language Learning toward Educational Equity Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29672 - Can Classical Semantic-Extractive Summarization Be Evaluated in Hindi? A Replication Study Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29090 - COILD: An Indic-Centric Parallel Corpus and Benchmark for Machine Translation Across Indian Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28826 - What a Cross-Model Fixed-Point Census Can and Cannot Arbitrate About Repetition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29507 - Free the Language Model From the Vision Encoder: Semantic Serialization as a Perception Interface for Small Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29601 - Low-Cost Assays for Measuring Model Behavior Across Vendors and Releases Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30012 - Grammatical "grandmother neurons" are rare in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29328 - PTC-Bias: Phoneme-Level Temporal Competition for Bias Retrieval and Post-Decoding Correction in Speech LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28727 - PROOF: Profiling Reliability of Object-Level Facts in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29504 - RapidUn: Influence-Driven Parameter Reweighting for Efficient Large Language Model Unlearning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.04457 - Frontier Lag: A Bibliometric Audit of Capability Misrepresentation in Academic AI Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.04135 - Persona Prompting in Multimodal Urban Perception: Descriptive Convergence and Interpretive Variation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29064 - LLM surprisal is necessary but not sufficient to capture English garden-path effects: Evidence from joint latent modeling of reading paradigms Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.04489 - Controlling Backchannels in Streamable Full-duplex Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29418 - Evaluation of OpenAI o1: Opportunities and Challenges of AGI Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2409.18486 - Conversational DNA: A Visual Language and Interactive Atlas of Human and AI Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.07520 - Small yet Assistive: Spatially-Aware Post-Training for Low Vision Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28757 - EAGER: Enhancing Generative Event Extraction via Reinforcement Learning with Verifiable Rewards Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29230 - Metrics That Write Themselves: Evolving an Evaluator from Its Own Blind Spots Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18744 - When Search Becomes Memory: Accelerating Robot Design Discovery with Self-Evolving Skills Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25832 - IDRBench: Benchmarking the Interactive Capabilities of Deep Research Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.06676 - Correct Prediction, Wrong Steps? Consensus Reasoning Knowledge Graph for Robust Chain-of-Thought Synthesis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.14121 - Adaptive Fisher-Whitened Cross-Covariance for Low-Resource Speech Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29800 - ArGuard Shared Task: Harmful Content Detection in Arabic Memes and LLM Prompts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29349 - PUBG Ally: A Conversational Embodied Agent as an AI Teammate Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29837 - Persuaded, Not Informed: Incentive-Misaligned Witnesses Defeat In-Context Grounding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28854 - How Do Users Negotiate Harmful Value Conflicts with AI Companions? A Study with Minion, a Technology Probe for In-Situ Human-AI Conflict Response Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.07042 - BanglaKontho: Closing the Long-Form Gap in Bangla Text-to-Speech Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29146 - Gaokerena: A Small Persian Medical Language Model Family Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00932 - Consequential Behaviour and Representational Fairness in the Validation of Synthetic Research Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27690 - Framing by Wording, Framing by Selection: A Large-Scale Two-Dimensional Audit of French News Headlines, 2022-2025 Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28487 - Multimodal Thinking with Renderable Programs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30130 - Temporal Taxation Compounds Under Post-Training Compression of Whisper Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28739 - Polite but Misaligned: Evaluating LLM Politeness Judgments Against Human Pragmatic Norms Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29001 - Combating Instruction Conflict via Energy-Driven Latent Conflict Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08646 - A Native-Reference Phone-Class Geometry for Second-Language Pronunciation Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30075 - CRISS: A Retrieval-Augmented AI Chatbot for Assisting Cancer Registrars Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29075 - Automated Regulatory Compliance Question Answering in Financial Services with Domain-Adapted Retrieval-Augmented Generation Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.30009 - When Should Forecasting Agents Reason? Behavioral Stress Tests for Reliability Routing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28475 - Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29845 - DiscoPhon: Benchmarking the Unsupervised Discovery of Phoneme Inventories With Discrete Speech Units Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18612 - Brain-to-Language Decoding: Tasks, Signals, Methods, Evaluation, Practical Use and Beyond Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27650 - Benchmarking Arabic--Russian Machine Translation: A Comparison of Fine-tuned NMT and Few-shot LLMs under Rich Morphology and Low Lexical Overlap Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29559 - PPTBench: Can Coding Agents Reconstruct the Visual World through Structured, Editable Slides Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29718 - Delay-of-Gratification as a Multi-Agent Survival Micro-benchmark for Long-Horizon LLMs: Social Exposure, Personas, and Tool Use Budgets Source: arxiv-cs-cl Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.29509 - StepCOPS: Closed-Testing Lower-Tail Certificates for Language-Model Policy Selection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29549 - iCoder-27B: Recursive AI-Led Development of Frontier Industrial Coding Model Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29626 - Spooftral: Can Voxtral Audio-Language Model Detect Speech Spoofing? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28713 - Calibration Is Not Enough: Evaluating Confidence Estimation Under Language Variations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.08064 - Reward-Tilted On-Policy Distillation for Acoustic Grounding in Audio-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28778 - Same Words, Different Actions: Paired Turn-Taking Evaluation under Rewritten Dialogue Contexts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17360 - Multi-Task Learning by using Contextualized Word Representations for Syntactic Parsing of a Morphologically Rich Language Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29855 - Conduct Under Pressure: What Sixty Language Models Do When a User Pushes Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.25447 - Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29429 - Universal Fractal Natural Language Decision Map: Real-Time Edge Triage Across Heterogeneous Domains Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.25498 - EnSiTa - A Trilingual Multi-Domain Parallel Dataset and Benchmark for Domain-Specific Machine Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29511 - BiMamba2 Masked Discrete-Unit Prediction for Multilingual Speech Representation for Unsupervised Speech in the Wild Challenge Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28758 - SemMSA: Latent Semantic-Aided Robust Multimodal Sentiment Analysis with Incomplete Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30238 - No More Free Lunch: Corpus Task Complexity Matters as Corpora Grow Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29245 - CONSISTRE: A Unified Consistency-Aware Framework for Document-Level Relation Extraction with Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.24312 - LLMs Anchor on Chief Complaint and Fail to Integrate Evidence in Sequential Clinical Triage Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22904 - Policy as Code: A Coroutine-Bridge Harness for Fast-Reasoning Reliability on CAR-bench Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29251 - From Policy Documents to Structured Survey Responses: Evaluating Large Language Models for Policy Monitoring Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29370 - ModularSQL: A Runtime Guardrail for the Multiplicity Blind Spot in Text-to-SQL Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29573 - Empath: Tracing Multi-Level Emotion Dynamics in Crisis Counseling Dialogues Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29056 - Benchmarking and Domain Adaptation of Automatic Speech Recognition (ASR) for Adolescent Health Communication in Ghanaian Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29798 - Large Language Models for Programming: Actually Fixing or Reimplementing Incorrect Code? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29410 - How To Do Things With Prompts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29657 - An Empirical Study of Automating Agent Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11378 - Proactive for Uncertainty: Cause-Aware Error Diagnosis and Interactive Clarification for Spoken Dialogue Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25404 - DuplexDrama: A Synthesized Dialogue Dataset with Scenarios, Full-Duplex Behaviors, Expressive Speech, and Sound Events Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.12872 - Evaluating Explanation-Driven Vision-Language Reasoning via Generation Order Interventions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29496 - Confident but Wrong: A Constrained Decoding Diagnostic for Low-Resource Automatic Post-Editing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29680 - LOGIC: Efficient and Robust Contextual Biasing for Speech LLMs via Logit-Space Integration Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.15397 - SkillGym: Internalizing Human Skills into LLMs for Real-World Problem Solving Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27717 - TimeBraid: Unifying Time Series and Language for Understanding and Forecasting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29792 - Do not be greedy, Think Twice: Sampling and Selection for Document-level Information Extraction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.18395 - Encoded but Not Decoded: Layer-Localized Evidence for a Three-Level Gap in LLM Syntax Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29848 - Closing the Quality Gap in Low-Resource Text-to-Speech: LoRA Fine-Tuning of VoxCPM2 for Khmer and Korean Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.26618 - IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis Source: arxiv-cs-cl Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.29444 - Calibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00949 - ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30199 - Language Specific Knowledge: Do Models Know Better in X than in English? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.14990 - agentic-ger: terminology recovery in long-form speech using global context Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29428 - Artificial Societies Benchmark: A Validation Framework for Synthetic Research Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30030 - VietPrism: A large-scale Vietnamese speech and deepfake corpus with diverse dialects and code-switching Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30005 - Q-CueGraph: Query-Conditioned Visual Evidence Graphs for Multimodal Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.04452 - STRAND: Benchmarking and Improving Object-Centric Spatio-Temporal Monitoring in Video Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29607 - PrivDrift: Auditing User-Secret Leakage Under Topic Drift in Active LLM Conversations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30094 - Interactive In-Meeting Speaker Correction with Human Feedback Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.18377 - JevOut: Natural Context Can Flip Decision Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30243 - JEV vs. LLMs as Rubric Judges: Cheaper, Faster, and Wrong in the Same Places Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29769 - A Training Criterion with Token-Level Tolerance to Transcription Ambiguity for Automatic Speech Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30160 - Clinical Intent Extraction: A FHIR-Aligned Representation and the CIRCA Benchmark Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29479 - BanglaTurn: A Benchmark and Whisper-Based Model for End-of-Turn Detection in Bangla Speech Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29371 - Learning to Ideate for Scientific Impact Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29802 - What, When, and How: Audio Description as Constrained Global Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30121 - Recovering the Zipfian Distribution in Unsupervised Term Discovery Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10781 - Tag-Aware Structured Text Translation: Towards a Systematic Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29131 - An Explainable DistilBERT-BiLSTM-Attention Framework for Binary and Multi-Class Hate Speech Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28703 - The Domestic Unprotected Zone: Algorithmic Governance and the Reproduction of Perpetrator Discourse in Conversational AI Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28479 - Parts-of-Speech as Emergent Categories in SAE Latent Space Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29362 - Continued Pretraining of FinBERT on Finnish Histopathological Reports: Train-Time Signals and Proxy Downstream Correlations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.14815 - Sharp Lovasz-Theta Bounds on Random Graphs Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2609.30064 - The Richness of CSP Non-redundancy Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2507.07942 - Strong NP-Hardness and Approximation Algorithm for Weighted Tardiness with Release Dates and Identical Processing Times Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2609.28751 - On the Binary Rank of Matrices with Constant Real Rank Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2609.30203 - An Algorithm for Linear Parametric Minimum Cycle Mean Problem Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2609.29234 - There are no nontrivial chordal square-complementary graphs Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2609.28702 - Packing Tails of Reciprocal Rectangles into Squares of Equal Area Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2609.28791 - Smooth weakly modular graphs Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2609.30035 - Lettericity Is NP-Complete Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2609.28023 - The coarse Erd\H{o}s-P\'{o}sa theorem Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2609.29414 - Zero Forcing Sets in Temporal Graphs Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2609.29054 - A Proof of the Imbalance Conjecture Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2608.09191 - Boolean threshold functions, neuron capacity, and memory retrieval Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2609.29756 - A Deterministic Polynomial Kernel for Odd Cycle Transversal Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.29141 - VAC: A Volume-sampling-based Elimination Rule for Approximate Cholesky Factorization Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.20241 - A Counting and Sampling Lov\'asz Local Lemma Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2608.08616 - A Group-Based Resource Allocation Model for the Fractional Knapsack Problem Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.06470 - Fast Spectral Signing for Vector Balancing Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.30044 - Dense Interprocedural Dominance in Acyclic Graphs: Context Bounds and Compact Queries Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.27818 - Eigenvalue and Eigenvector Approximation for Random Matrices Using Low-Degree Polynomials Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.28781 - Asymptotic optimality of dynamic first-fit packing on the half-axis Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2404.03797 - Parameterized Complexity of Spanner Problems with Independent Weights and Lengths Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.29259 - A Faster Algorithm for Fewer Vertex-Disjoint Paths Parameterized by Treewidth Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.29294 - From FPT to W[P]: Classifying Zero Forcing, Power Domination and Their Variants Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.29966 - Polynomial Time Algorithms for the Kadison-Singer Problem Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.19794 - The Longest Common Bitonic Subsequence: Match-Sensitive Algorithms and Conditional Hardness Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2511.08958 - A Proof of the Most Informative Boolean Function Conjecture Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.24931 - Linear-Time FPT Algorithm for Surface Disjoint Paths via Surface Cutting Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.29324 - On Kernels and Leaves: Searching for Bare and Lush Trees Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.29451 - Spectral and combinatorial methods for efficiently computing the rank of unambiguous finite automata Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2511.09703 - Locally Approximating the Top Eigenvector of Bounded Entry Matrices Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2607.08556 - Path Enumeration by Position-Visit Counts in Recombining Trinomial Trees Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2510.02727 - A Tight Cycle-Cover Inequality for Shortest Common Superstring Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.27921 - A Tight Analysis of Khatri-Rao Oblivious Subspace Embeddings Source: arxiv-cs-ds Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2608.28094 - Online Bin Packing with Per-Bin Maximum Delay Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.29589 - Move-rb: Faster Bi-Directional r-indexes and Approximate Pattern Matching Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.30089 - Strongly Refuting Semirandom Linear Systems in Subexponential Time Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.30052 - Practical and Space-Efficient LZ77 and LZ Pre-Compression via String Synchronizing Sets Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.30193 - Tight Approximation Results for Matroid Optimization with a Linear Constraint Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.28708 - Optimal spectrum estimation Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2609.30171 - Optimal Quantum State Testing Even with Limited Entanglement Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2604.07460 - A Systematic Multi-Domain Evaluation of Document Retrievers Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29455 - ScalarLens: Numerical Embeddings with Stable Coordinates and Contextual Responses for CTR Prediction Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29182 - Reinforcement Learning with Verifiable Rewards for Small Search Agents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.28765 - Ingest-Time Fact Compilation for Cost-Efficient and Reliable Question Answering over Revised Corpora Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29661 - LSF-SR: Latent Semantic Fusion for Sequential Recommendation via Flow-based Conditional Variational Autoencoders Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29815 - Stochastic Semantic Evidence Graphs: Uncertainty Propagation and Governance for Agentic AI Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29703 - Anatomy of a Decision: Uncertainty-aware Hierarchical Intent Learning via Flow Matching for Multimodal Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29609 - Cross-Country Code-Mixing for Generative Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.28972 - C3M: Cross-Session Multimodal Memory Maintenance for Long-Horizon Tasks Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29735 - From Interests to Semantic IDs: Retrieval-Grounded Credit Assignment for Generative Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29983 - SmallReason-ColBERT: An Ultra-Small Late-Interaction Retriever for Reasoning Intensive Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29652 - WebArxiv: A Reproducible Benchmark for Evaluating Multimodal Web Agents on arXiv Tasks Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2507.00938 - EvLink: Source-Grounded Evidence Linking for Graph RAG Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29695 - CodeGraph: Open-Taxonomy Knowledge Graph for Source Code with Wikidata Grounding Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29474 - Seek: Self-Evaluative Exploration for Knowledge Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.28980 - X-Rec Technical Report Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29180 - OBLIQ-IR: Training a Dense Retriever for Oblique Queries Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29649 - Asymmetric Dynamic Routing: Balancing Reasoning Depth and Computational Efficiency in Hypergraph RAG Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29282 - SPARQL-LLM: Real-Time SPARQL Query Generation from Natural Language Questions Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2512.14277 - Learning Better Reasoning for Generative Recommendation with Semantic IDs Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29973 - Measuring Brand and Source Discovery under Repeated LLM Queries: A Finite-Sample Audit Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.05059 - Fair Feed Ranking for Participatory Budgeting Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29819 - Claim-Gated Source-Risk Auditing for Generative Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29145 - SALI: Shot-Aware Late Interaction for Cross-Shot Relation Matching in Text-to-Video Retrieval using Film-Grammar Knowledge Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29721 - Advancing Model Research in AgentX: Long-Horizon Autonomy for Industrial Recommender Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.30001 - SEEK: Skill-Routed Evaluation with Evolvable Knowledge for Industrial Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29803 - An Empirical Study of VLM Pipelines for Long-Document QA Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29933 - OneTrans-V2: Unifying Retrieval, Pre-rank, and Fine-rank with One Transformer in Industrial Recommender Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.28589 - Learning the Cost of Reliable Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28322 - Why Does Misinformation Propagate Faster? An Algorithmic Perspective on X Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28947 - Vector Bellman Theory for Multichain Robust Average-Reward Markov Decision Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28792 - Post-Training Leaves Behavioral Shadows on Unrelated Decisions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29233 - Common Covariance Geometry and Certification for Brownian Kernel Ladders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29525 - Automatic Rank Allocation for Low-Rank Adaptation in Large Language Models via lp Regularization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28998 - Thinking Leakage: A Causal Audit of NoThink Post-Training in Hybrid Reasoning Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28682 - On the SoS Certifiability of Log-Concave Distributions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30105 - Not All Confusion Is Equal: A Source-Aware Uncertainty Diagnosis for Fine-Grained Aircraft Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29959 - From Graphs to Feeders: Constraint-Guided Diffusion for Rule-Compliant Feeder Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29879 - OPDiv: Optimal Selection of Top-K High-Scoring, Diverse Compounds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28665 - Concurrent Split Learning Through Stable Client Clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29395 - Vibe Patenting: Evaluating LLM Judges for Professional Patent-Drafting Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.13422 - A Particle-Swarm-Assisted Gradient Meta-Learning Algorithm for Joint Transmit Precoding and STAR-RIS Coefficient Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29150 - Global Convergence of DGM and PINN Algorithms for Solving Nonlinear PDEs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.24726 - UO-FIE: Combining Exact-Label Supervision with Graded Utility for Factivity Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28605 - TinyCardioUNet: IMU-to-ECG Translation with Graph-Encoded Inter-Axis Dependencies and Tensor Decomposition-Based Parameter Reduction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29322 - M-plicits: Neural Implicit Surfaces via Nested Multiscale Residuals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28684 - Transductive Off-policy Proximal Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.03894 - Image Fidelity is Not Field Fidelity: Joint Thermodynamic Reconstruction and Error Localization in Neural Tomography Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28868 - Safety Nudges: User-Facing Interventions for Real-Time AI Risk Awareness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26865 - BridgeMem: Causal Dyadic Transition Residuals for Temporal Knowledge Graph Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29268 - A Unified Benchmark for Dynamic Medical Treatment Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01028 - CrossSafe: Towards Cross-Embodiment Latent Safety Filters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28984 - Auditability Is Not One Property: Rule Overlap, Behavioural Agreement, and Composition in Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28581 - The Impossible Trinity of Time-Series Validation: A Conservation Law among Training Sufficiency, Test Coverage, and Temporal Causality Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29530 - Reconstructing short-lived particles using hypergraph representation learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2402.10149 - GOMA: Toward Structure-Driven Multimodal Alignment from a Graph Signal Smoothing Perspective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.15723 - Reachability-Based Formal Verification of Graph Neural Networks with Node and Edge Features Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30079 - LastOPD: Taming Collapse in Latent On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28845 - BLADE: Distilled LLM Regularization for Calibrated Knowledge Graph Completion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29487 - Bandit Multiclass PAC Learning: Corrected Lower Bounds, Exact Families, and a Confidence Direct-Sum Phenomenon Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29694 - Generating Interesting Scientific Ideas using Knowledge Graphs and LLMs: Evaluations with 100 Research Group Leaders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2405.17044 - Personalised federated learning for Riemannian and Euclidean EEG decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29037 - Self-Localizing MIMO Beam Mapping with Continuously Evolving Channel Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.17007 - Safety Under Scaffolding: How Evaluation Conditions Shape Measured Safety Source: arxiv-cs-lg Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2603.10044 - MultiwayPAM: Multiway Partitioning Around Medoids for LLM-as-a-Judge Score Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.10287 - Sequential Confidence Sets for Coverage-Constrained Conformal Model Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28522 - The kernel of graph indices for vector search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.20584 - Feature Space Selection and Heterogeneous Effect Estimation for Blood-Brain Barrier Permeability: A Random Forest to the Generalized Random Forest Pipeline Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29076 - TTLab at AlexandriaX-2026: A Fine-Tuned Surface Tagger for Arabic Machine-Translation Error-Span Detection and Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29633 - Canopy: Exploiting Piecewise Smooth Tree Priors for Multi-Fidelity Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30017 - Where Hallucinations Live: A Cross-Architecture Circuit in VQ-Tokenized Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29048 - Cluster Assignments in Soft Targets Shape Speech Representations: Evidence from S-JEPA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19084 - Nuclear Norm-Regularized Bayesian Matrix Completion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30078 - M$^2$PFN: End-to-End Disentangled Alignment for Generalizable Multimodal In-Context Learning in Alzheimer's Disease Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28836 - A Fast and Effective Solution to the Problem of Look-ahead Bias in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.06607 - Open-access model for detecting openly dumped dispersed municipal solid waste from crowdsourced UAV imagery in Sub-Saharan Africa Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.02316 - Towards Deployable Underwater Vessel Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29179 - Multimodal AI predicts clinical outcomes of drug combinations from preclinical data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.02781 - Downside-Controlled Online Forecast Combination under Delayed and Revised Outcomes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29096 - Exploiting answer-invariant redundancies in satellite imagery for efficient VLM inference on edge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29029 - RD-JEPA: Predictive latent pretraining for few-trajectory transfer across reaction--diffusion equations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29403 - Tracking States or Tracking Cosets? An Algebraic Account of Learned State Tracking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29951 - Diverse Geometries, Frozen Weights: Robust Heterogeneous Treatment-Effect Estimation via Causal Expert Ensembles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29974 - MemGuard-Alpha: Limits of Membership Inference for Detecting and Filtering Memorization-Contaminated Signals in LLM-Based Financial Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.26797 - A Comprehensive Review of Large Language Models for Nanophotonics: From Surrogate Modeling to Autonomous Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18279 - Unraveling the cognitive patterns of Large Language Models through module communities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.18192 - Reward Hacking Challenges Oversight of Autonomous Research Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28614 - Lossless Anti-Distillation Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18829 - RAPTOR: RAndom-projection Physics-informed Transient sOlveR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29714 - AERIAL: Adversarial Evaluation of Robustness in Accuracy-Preserving Low-Precision EEG Decoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30037 - How Reproducible Are Evaluation Conclusions? A Self-Audit of LLM-Inferred Prompt Structure Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30074 - A Contraction Framework for Stochastic Operators with Bootstrapping: Application to TD Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29961 - ELF-REG: Scaling Continuous Diffusion Language Models to Reasoning Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29102 - Anchored Extra-Proximal Methods: Optimal Higher-Order Methods for Monotone Inclusion Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30212 - Cost-Sensitive Online Window Size Selection for Portfolio Management Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29887 - Selective Inference for Deep Clustering in Latent Spaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28756 - Spectral Graph Neural Networks with Hermite Polynomials: A Comprehensive Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28979 - A Corpus of Real Scam- and Spam-Call Conversations from an Active Voice-Agent Honeypot Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29528 - Matrix Aggregation Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28562 - Not All Synthetic Data Are Equal: Expert-Committee Audit Screening for Imbalanced Crash-Injury-Severity Prediction in Automated Driving Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29687 - Hardware Keystores for AI Agent Signing Workflows: A Zero-Trust MCP Enforcement Architecture Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06130 - Lightweight Probabilistic Downscaling from a Deterministic Base Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29383 - TraceGuard: Adaptive Multimodal Poison Filtering through Cross-Feature Rank Agreement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29099 - TTLab at StanceEval-2026: A Cloze-Style Prompting Approach for Arabic-Language Stance Detection (CLASP-Ar) Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29733 - From Prediction to Explainable Provider Behavior Profiles for Fraud, Waste, and Abuse Review Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28477 - Don't Read the Log: Execution Traces Contaminate Verifiers in Video-Generation Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28564 - AFT Neural Function Approximators for 1D Nonlinear Force Laws Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29242 - Albireo: Adaptive, Energy-Efficient Inference Framework for Video Object Detection on the Edge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29648 - Transformers as Cross-Task Learners: Shared Structure Drives Sample Efficiency in In-Context Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29060 - The Sequential Price of Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29674 - Precise Convergence Speed of Clipped SGD Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29458 - When Explanations Cannot Be Read: Measuring and Correcting SHAP and LIME Rendering for Right-to-Left Languages Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28565 - Limited Structural Reliability in Public Educational Prediction Benchmarks: A Four-Dimension Audit of Seven Datasets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29625 - LAYERSCOPE: A Layerwise Characterization of Video and Multimodal Learned Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28086 - ICE: Task-Aligned Clifford Latent Fields for Multimodal Graph Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29398 - Effective Graph and Rank-based Contextual Embeddings for Textual and Multimedia Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29001 - Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.31046 - Growth-Inspired Graph Generation and Inverse Design of Mechanical Lattices via Dot Matrices Database Augmentation and GCNN Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29024 - A Probabilistic Approach for Model Alignment with Human Comparisons Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2403.10771 - Residual Correlation as a Diagnostic for Joint-Uncertainty Gains from GP Coregionalisation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30085 - BRFID: Toward Byzantine-Robust Federated Intrusion Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28599 - Active Client Selection in Federated Trajectory Prediction with Uncertainty-Awareness and Heterogeneous Complexity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29600 - Language Specificity vs. Domain Diversity: Benchmarking Transformers for Bangla Medical NER Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29101 - WeatherDiagFlow: Evidence-Grounded Radar Nowcasting with Diagnostic Flow Refinement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29772 - Who Owns the AI Recommendation? A Multi-Industry Empirical Map of Brand Category Ownership Across Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23057 - When Fancy Eviction Fails: Rethinking Cache Replacement For LLM Prefix Reuse Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28870 - Taking a Second Look: Correcting Sea Ice Forecasts with Sparse Observations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24591 - Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30258 - CaliPPer: quantifying, predicting and improving AI model performance for binding prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07258 - PocketVE: Stable and Property-Guided Structure-Based Drug Design with Variance-Exploding Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08101 - AT-SKM-Net: An Accelerated Trainable Sampling Kaczmarz-Motzkin Framework for Linear Hard-Constraint Feasibility on Dynamic Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30088 - SwitchPFN: Shared Switching Dynamics for Frozen In-Context Time Series Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29814 - ProCredit: From Outcome Rewards to Progress Credit in Agentic Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27532 - To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30227 - Uncovering Residential PV-EV Co-Adoption from Smart-Meter Data: Load Archetypes and Detection for Demand-Side Planning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28578 - Optimal Recovery Meets Bayesian Learning: Where Worst-Case Bounds Pay Off Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29622 - Stable and Faithful Explanations for Knowledge Tracing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28502 - DiffUNet^2: Bidirectional Conditional Diffusion for Probabilistic Scientific Spatiotemporal Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03926 - Monitoring Urban Traffic Dynamics at Fine Spatiotemporal Resolution Using Distributed Acoustic Sensing and Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28793 - The Fellowship of the Query: Learning Retrieval Actions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28653 - Aero Hand Open: A Simulation-Ready Tendon-Driven Hand for Dexterous Manipulation Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.28578 - DAWN: Noise-Robust Quadruped Parkour via Depth-Denoising World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29092 - Pointwise Generalization in Deep Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18598 - Graph, Loop, and Harness Engineering for Zero-Trust Agentic Data Engineering and Analytical Processing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29668 - Task-Aware Spectral Pruning: A Mixture-of-Masks Framework for Efficient LLM Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29499 - Algebraic Expressivity Certificates for Shallow Polynomial Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28500 - Evidence-Driven Differential Diagnosis of Malignant Melanoma Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29613 - An explicit solution of the five-expert prediction PDE and the exact optimality set of COMB Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14892 - Paging the Experts: A Reproducible Characterization of Flash-Backed MoE Inference on iPhone Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29032 - CLaST: Context-aware Contrastive VAE for Probabilistic Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20025 - Beyond Forgetting: Diagnosing and Harnessing Shared Reasoning in Continual RLVR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18574 - Not Every Token Is Worth Distilling: Selective Supervision for Direct-OPD Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29142 - KernelOPT: Dispatch-Aware Agentic Search for GPU Kernel Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30059 - TabSieve: Explicit In-Table Evidence Selection for Tabular Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.11700 - Physics-Guided Multi-Objective Deep Learning for Ultrasound RF Data Interpolation in Resource-Constrained Imaging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28775 - Temporal Learning for End-Effector Position Estimation under Aerodynamic Disturbances in Aerial Continuum Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28716 - TacSushi: Tactile-Grounded World-Action Modeling for Dexterous Sushi Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19613 - LiveMathematicianBench: A Live Benchmark for Research-Level Mathematical Reasoning with Proof Sketches Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.01754 - Multimodal Routing and Region Refinement for Language-Guided Medical Image Segmentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28860 - The Alignment Illusion in Multimodal Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30210 - Forecast-Dojo: Replayable Environments for Benchmarking and Training LLM Forecasting Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28876 - Multi-Dimensional Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29958 - Unmasking Shortcut Learning in IoT Intrusion Detection: A Forensic, Multi-Paradigm Evaluation of Feature Dependence and Data Leakage Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28725 - FB-GDM: Fully-Bayesian Guided Diffusion Models for High-Dimensional Linear Inverse Problems via Unsupervised Variational Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29216 - A Nearly Quadratic Lower Bound for Linear Optimization over Convex Bodies in the Membership Oracle Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30215 - A Rapid Pipeline for Training and Deploying ML Models on WeBe Band Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29084 - Reflex-Guard: A Low-Latency Guardrail for LLM Prompt Safety Using Dense Semantic Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.17556 - CyFM: Cylindrical Optimal Transport for Few-Step Complex-Valued Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14171 - Two Dimensions Govern Agnostic Multiclass Transductive Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25326 - Learnable Time-Frequency Masks for Explaining Time-Series Classifiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29270 - Wiring Beats Blending: Structure-Aware Compensation for Transformer Downscaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02829 - Few-Shot Specific Emitter Identification via Integrated Complex Variational Mode Decomposition and Spatial Attention Transfer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.16786 - Return or Revise? Learning When Revision Helps Retrieval-Augmented QA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30087 - Efficient Continuous DEM Reconstruction under Limited Target-Resolution Supervision Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29864 - Deep learning of longitudinal visual fields predicts glaucoma progression rate and identifies fast progressors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29256 - Cross-Task Generalization in Handwriting-Based Alzheimer's Screening via Vision Language Adaptation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.05841 - HiPACE: Hierarchical Phase-Boundary Analysis and Controlled Evaluation of Feature Absorption in Sparse Autoencoders Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29551 - IndicBankBench: Evaluating Safety and Reliability of Language Model Assistants in Indian Retail Banking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29167 - A Harness for Synthesizing Diverse Naturalistic Full-Duplex Conversations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28806 - TW3Cast: A Frozen Router of Lightly Fine-Tuned Foundation Models for Time-Series Forecasting on GIFT-Eval, Selected Entirely on the Training Split Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28506 - Calibrated Decision Models for Autonomous Penetration-Testing Harnesses: JEV and Laya as System One Decision Layers for LLM-Driven Pentest Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28940 - PFArena: Benchmarking Language Models for Protein Modification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28921 - To Think or Not to Think: Allocating Reasoning Where It Helps Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29664 - GraphSkillAA: Attribution-Guided Skill-Graph Updating with Targeted Validation and Rollback Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20455 - Clinical Knowledge Graphs for Chest X-Ray Device Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29536 - AI-based detection of worsening heart failure from low-resolution telemonitoring data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29742 - KeyGen: Unsupervised Keypoint based Object-Centric Representations for Category-Level Policy Generalization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28818 - Beyond Surface Style: Aligning Multi-Turn User Simulators with Behavioral Consistency Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28690 - Who Holds the Pen? Let Specifications, Not Agents, Sign Off Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29921 - Generative Evolutionary Design of Voxel-Based Soft Robots with Provable Optimality Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29491 - Control the Harness, Control the Cost: Routing and Governing AI Coding Agents in the Enterprise Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28919 - An auditable conditional-strategy framework for open-ended decision-making in complex lung cancer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29381 - BiGraph-Diffuse: A Bidirectional Diffusion Language Model with Graph-Structured Retrieval For Mental Health Counseling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29519 - NNV3: Expanding Neural Network Verification to New Architectures and Domains Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30050 - Persistent Billable State: Denial-of-Wallet Attacks and Defenses in Tool-Calling LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28585 - MorphIK: Morphology-Conditioned Neural Inverse Kinematics for Unknown Robots Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29908 - How does Adversarial Influence Scale in Multi-Agent Systems? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30028 - Chart-Supported or Model-Supplied? Examining MLLM-Generated Claims for Accessible Visualization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.25021 - SOV-CAD: Stepwise Orthographic Views Guided CAD Modeling Sequence Reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04119 - EIB-Net: Entropy-Guided Information Bottleneck for Generalizable AI-Generated Image Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29064 - TP-CRIV: A Framework for Third-Party Challenge-Response Identity Verification of AI Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29264 - GeoRefer-Bench: A Benchmark from Referring Pixels to Verifiable Geospatial Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29541 - Breaking the Environment Wall: Evolving LLM Agent Environments for Recursive Self-Improvement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29773 - Med-AR: Autoregressive Vision-Language Pretraining for Long-Tailed Chest X-Ray Classification and Uncertainty-Aware Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29156 - Frame-to-Panorama Localization and Context-Aware Sampling for Scene-Specific Ship Detection in a Smart Marina Testbed Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29447 - Driving Epidemic Models with AI Agents: the Epydemix Agent Framework Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28692 - Era by Eon: Benchmarking Enterprise Agents on Hidden Knowledge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30055 - TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30222 - TRACE: Trajectory Aware Reasoning for Multi-Turn Adversarial Conversation Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15594 - SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30192 - Scope Before You Persist: Preventing Cross-Family Interference in Agent Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29144 - Decoding Imagined Speech: A Strictly Subject-Independent Approach Using EEG Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29820 - CrossScale-GLIO: Topology-Preserving Vision-Language Alignment of MRI and Whole-Slide Histopathology for Diffuse Glioma Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28524 - The Entropy Triangle Method (ETM): A novel framework for the prevention of cardiac arrhythmia with a review of more than 10,000 patients Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29187 - RAPID: Robot Agentic Programming from Demonstrations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30249 - Mind What Matters for Reasoning: Aligning Cross-Modal Attention via Selective Probability Mass Concentration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29940 - Spot, Separate, and Enhance: Fully Generative Approach for Audio Mixing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29169 - A Human-AI Theorem Connecting Spontaneous and Field-Induced Mechanisms of Collective Behavior in One Dimension Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00322 - UNWIND: Any-Length Facial Video for Stress Detection without Temporal Windowing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29553 - Anatomy-aware cross-speaker adaptation of complete vocal-tract acoustic-to-articulatory inversion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29766 - WildHSR: Metric Feed-Forward 4D People-Scene Reconstruction from a 3D Foundation Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29106 - Safe Skill Retirement for Physical Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29543 - TOLA: Text-aware One-Step Latent Adaptation for Diffusion-based Text Image Super-Resolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29240 - Math Reasoning in LLMs is Organized by Approach, Not Topic Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27041 - Investigating White Blood Cells as a Source of False-Positive Malaria Parasite Detection in African Blood-Smear Images Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29663 - Decoding ML Decision: An Agentic Reasoning Framework for Large-Scale Ranking System Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.18640 - Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamwork Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24423 - SHRAV: State-Hypothesis-Reason-Action-Verify Framework for Physical Modeling and Inverse Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27621 - When Honesty is Not Enough in AI Debate Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29189 - When Agents Act Unwatched: The Reduced-Supervision Paradox in Agentic AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29547 - Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31825 - When Can Agents Forget Their Reasoning? ICLR for Long-Horizon Agent Context Compression Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29875 - Between the Commits: Process, Error, and Claim Reliability in a Wholly AI-Authored Codebase Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29744 - MPFlow: Multi-modal Posterior-Guided Flow Matching for Zero-Shot MRI Reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.03710 - Stale Does Not Mean Unsafe: Guard Precision for Tool-Using LLM Agents under Infrastructure State Races Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29522 - Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.20470 - Structured Pose-Conditioned Flow Matching for Generative 5G CSI Augmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29912 - Hallucination Neurons and Where to Find Them: An Investigation into the existence of Hallucination Neurons Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29781 - Coding Agents for Generalized Task and Motion Planning Problems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30233 - ReCalMatch:Reliability-Calibrated Semantic Guidance for Semi-Supervised Fine-Grained Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29678 - Search-Aware Reinforcement Learning for Multi-Component Query Understanding in Roblox Game Search Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.30177 - Interpreting and Enhancing Emotional Circuits in Large Vision-Language Models via Cross-Modal Information Flow Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21980 - HarnessPAI: An Evolving Harness for Physical AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29166 - Planning Takes More Than Token Prediction: Causal Plan for Benchmarking and Building Physically Grounded Embodied Reasoners Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01810 - Baszta: Data-Centric Fine-Tuning of a Polish Multi-Label Safety Classifier Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29266 - AI-Moderated Interviews for Market Research and Digital Twins Calibration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29143 - SWE-Prometheus: Measuring Engineering Governance Improvements in Real-World Repositories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29465 - CATCH: Counterfactual Anatomical Tissue Inpainting with Conditional Haar Diffusion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29591 - The Last Human Gate: Forward Deployed Engineering for Governance Automation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29345 - HERMES: A Holistic End-to-End Risk-Aware Multimodal Embodied System with Vision-Language Models for Long-Tail Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.00993 - SHINE: Sequential Hierarchical Integration Network for EEG and MEG Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.23960 - Can Labor Markets Function in the Age of AI? The Evaluation Bottleneck in Hiring Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30058 - ADATEX4D: adaptive texture capacity allocation for 4D gaussian splatting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29963 - Functional Architecture of European Electricity Trading Markets: Requirements for AI Supported Trading Systems under Regulatory Constraints Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29108 - Blockchain-Enabled Artificial Intelligence and AI Agents for Secure Data Sharing and Cybersecurity Applications Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28843 - BEHAVE: Real-Time Modeling of Human Systems as Observable Complex Dynamical Systems and Operational Objects for Physical AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12730 - Wearable ECG Quality Assessment: A Deep Learning and Ambulatory Context-Awareness Approach Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29396 - Pistis Technical Report Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28554 - Multi-Agent Orchestration of 3GPP Channel Estimators Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29044 - S2Planner: Multi-Scale Semantic Planner for End-to-End Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29813 - LLM Agents Can Easily Tamper With Their Own Traces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30266 - Robots That Take Initiative: A Framework for Building and Evaluating Proactive Robots Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28910 - Synthetic Hospital: An Open, Verifiable, Physician-Validated Longitudinal EHR Benchmark Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30027 - Neuro-symbolic AI for Industrial Configuration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29947 - SARFusion: Scene-Aware Routing Fusion for Robust Camera-LiDAR 3D Object Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29235 - Long-horizon autoformalization of a core theorem underlying MIP* = RE Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19814 - Learned Cross-Task Relationships in Multi-Task Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28776 - AlphaDiverse: Post-Training Local Quantitative Research Agents for Diverse Exploration in Alpha Factor Mining Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29014 - SciWalker: Synthesizing Scientific Coding Problems with Operator Graphs and Execution Feedback Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30054 - Do World Models Make Better Robots? A Survey of Evaluation Benchmarks for Predictive Embodied Intelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29669 - Grow the Harness, Not the Context: From Strategy-Free Scaffolds to Reusable Specialist Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26760 - Dual-Frontier: When Can an Agent Trust Its World Model? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26293 - Jev-Mobile: Jev as an Executor for Mobile GUI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30186 - Prefilling the Reasoning Channel: Output-Prefix Attacks on Reasoning LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29775 ## Community - Pre-RFC: Another attempt to re-design the Try trait - Try::Kind and TryAs Source: rust-internals Topic: Rust URL: https://internals.rust-lang.org/t/pre-rfc-another-attempt-to-re-design-the-try-trait-try-kind-and-tryas/24618 - What I learned at DevTalks Cluj-Napoca 2026 Source: vlad-mihalcea Topic: Java (+PostgreSQL) URL: https://vladmihalcea.com/devtalks-cluj-napoca-2026/ - Quoting John Gruber Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/25/john-gruber/ - Northern Gannet, Great Blue Heron, California Brown Pelican Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/25/sighting-403293902/ - `fnmatch.translate` and anchoring Source: discuss-python-ideas Topic: Python URL: https://discuss.python.org/t/fnmatch-translate-and-anchoring/109239 - Umair Shahid: Your Postgres Database Is Slow, and It Isn’t Postgres Source: planet-postgresql Topic: PostgreSQL URL: https://postgr.es/p/9vF - Lenses and Prisms in OCaml Source: ocaml-planet Topic: OCaml URL: https://funcp.org/lenses-and-prisms-in-ocaml - Dmitry Narizhnykh: How to Inspect a pg_dump Without Restoring It Source: planet-postgresql Topic: PostgreSQL URL: https://postgr.es/p/9vE - Andrew Atkinson: Let’s Get Down to Business with Rails and PostgreSQL Source: planet-postgresql Topic: PostgreSQL URL: https://postgr.es/p/9vG - Rodrigo Girão Serrão: TIL #146 – Using maturin through uv Source: planet-python Topic: Python URL: https://mathspp.com/blog/til/using-maturin-through-uv - LernerPython blog, from Reuven Lerner: Pandas dropna: The best way to remove NaN values from a series Source: planet-python Topic: Python URL: https://lernerpython.com/2026/09/25/pandas-dropna-the-best-way-to-remove-nan-values-from-a-series/ - Christophe Pettus: All Your GUCs in a Row: max_replication_slots Source: planet-postgresql Topic: PostgreSQL URL: https://postgr.es/p/9vH - Testing Mollymawk Source: ocaml-planet Topic: OCaml URL: https://blog.robur.coop/articles/2026-09-24-testing-in-mollymawk.html - Graham Dumpleton: A master class in decorators, patching and tracing Source: planet-python Topic: Python URL: https://grahamdumpleton.me/posts/2026/09/a-master-class-in-decorators-patching-and-tracing/ - S3 Is the Future, S3 Is the Past Source: hacker-news Topic: General URL: https://btrblocks.com/blog/s3_is_the_future_and_the_past/ - Bob Mackie dressed stars–if they were brave enough Source: hacker-news Topic: General URL: https://www.economist.com/obituary/2026/09/24/bob-mackie-dressed-stars-if-they-were-brave-enough - OpenAI’s Systems Went Rogue and Meddled With U.S. Government Websites Source: hacker-news Topic: General (+AI) URL: https://www.nytimes.com/2026/09/25/technology/openais-ai-us-government-websites.html - Tell HN: Codex Is Down [fixed] Source: hacker-news Topic: General (+AI) URL: https://news.ycombinator.com/item?id=49851032 - FTC chair suggests AI developers should be liable for conduct of agents Source: hacker-news Topic: General URL: https://www.reuters.com/business/ftc-chair-pushes-back-treating-ai-agents-independent-actors-2026-09-25/ - Exploding variance of means of exponentials: least-squares to the rescue Source: hacker-news Topic: General URL: https://francisbach.com/spectral_log_density_estimation/ - Keep if clauses side-effect free Source: lobsters Topic: General URL: https://www.teamten.com/lawrence/programming/keep-if-clauses-side-effect-free.html - Lab on a Contact Lens Can Measure Stress Through Serotonin Source: hacker-news Topic: General URL: https://spectrum.ieee.org/serotonin-stress-smart-contact-lens - Accelerated Out of Core Shuffling Source: hacker-news Topic: General URL: https://quasiben.github.io/blog/ooc-shuffling-rapidsmpf/ - Hype Is a Business Tool Source: hacker-news Topic: General URL: https://jenson.org/hype/ - KICKI: a DECsystem1060 Source: hacker-news Topic: General URL: https://icm.museum/blog/?p=207 - Show HN: Recurse – Develop and deploy specialist agents faster Source: hacker-news Topic: General (+AI) URL: https://recurse.run - What even is an OS now? Source: hacker-news Topic: General URL: https://sockpuppet.org/blog/2026/09/25/what-even-is-an-os-now/ - NetBSD Playing with disklabels Source: lobsters Topic: General URL: https://movq.de/blog/postings/2026-09-25/0/POSTING-en.html - Show HN: Ekselio – Loveable for finance workflows (local first) Source: hacker-news Topic: General (+AI, JavaScript, React) URL: https://www.gptbeyond.com/try?home=1 - Revealing the details of how OpenAI agents hacked Hugging Face Source: hacker-news Topic: General (+AI) URL: https://swarmtraces.org/ - Teaching a World Model to Play Pokemon Source: hacker-news Topic: General URL: https://nostalgia.dev/posts/teaching-a-world-model-to-play-pokemon/ - North Korea 'Likely' Behind $388M Hack of Crypto Exchange Bitget Source: hacker-news Topic: General URL: https://gizmodo.com/north-korea-very-likely-behind-388-million-hack-of-crypto-exchange-bitget-2000817421 - Excel now supports multiple values in a single cell Source: hacker-news Topic: General URL: https://techcommunity.microsoft.com/blog/microsoft365insiderblog/put-multiple-values-in-one-cell-with-lists-and-arrays-in-excel/4559395 - Analyzing Frontier Model Progress with My Favourite Game: Prince of Persia Source: hacker-news Topic: General URL: https://blog.priyan.in/2026/09/analyzing-frontier-model-progress-with.html - The stupidity and arrogance of GNOME developers (2024) Source: hacker-news Topic: General URL: https://felipec.wordpress.com/2024/03/18/stupid-gnome-developers/ - Finally, A True Blue Rose Exists Source: hacker-news Topic: General URL: https://www.sciencenews.org/article/true-blue-rose-pigment-copigment - Too AI; Didn't Read Source: hacker-news Topic: General URL: https://www.tai-dr.com/ - Asteroids named after Tom Lehrer and 'Weird Al' Yankovic Source: hacker-news Topic: General URL: https://science.slashdot.org/story/26/09/24/009238/asteroids-named-after-tom-lehrer-and-weird-al-yankovic - Writing Efficient C++ Code (2013) Source: hacker-news Topic: General URL: https://asawicki.info/articles/writing_efficient_cpp_code.php - Time Measurement in Game Programming Source: hacker-news Topic: General URL: https://asawicki.info/articles/time_measurement_in_game_programming.php - Rising sea destroys homes, erases beaches in California Source: hacker-news Topic: General URL: https://www.reuters.com/business/environment/rising-sea-destroys-homes-erases-beaches-california-is-worse-come-2026-09-25/ - How we learned to stop worrying and love campus surveillance Source: hacker-news Topic: General URL: https://fnl.mit.edu/how-we-learned-to-stop-worrying-and-love-campus-surveillance/ - Forging 1024-bit RSA signatures in nearly SNFS time Source: hacker-news Topic: General URL: https://github.com/ucsd-hacc/NSNFSSSFSFN - Ask HN: Who's still keeping a DOS machine up because the business depends on it? Source: hacker-news Topic: General URL: https://news.ycombinator.com/item?id=49848955 - Supreme Court permits states to use SAVE database for citizenship checks Source: hacker-news Topic: General URL: https://cyberscoop.com/supreme-court-save-database-voter-citizenship/ - Bug: Border radius has infected VSCode editor Source: hacker-news Topic: General URL: https://github.com/microsoft/vscode/issues/338035 - Watch Steve Jobs in the full 'Antennagate' video before it gets erased again Source: hacker-news Topic: General URL: https://appleinsider.com/articles/26/09/24/watch-steve-jobs-in-the-full-antennagate-video-before-it-gets-erased-again - Letterboxd Is Up for Sale, and A24, Sony and the New York Times Are Bidding Source: hacker-news Topic: General URL: https://www.worldofreel.com/blog/2026/9/24/letterboxd-is-up-for-sale-and-a24-sony-and-the-new-york-times-bidding - Pilots and Flight Attendants Have the Highest Radiation-Related Cancer Mortality Source: hacker-news Topic: General URL: https://jamanetwork.com/journals/jama/fullarticle/2854678 - Pope: AI must serve humans not become tool of domination Source: hacker-news Topic: General URL: https://www.euronews.com/2026/09/25/ai-must-serve-humans-rather-than-become-an-instrument-of-domination-and-injustice-pope-war - Advice to a Beginning Graduate Student (2001) Source: hacker-news Topic: General URL: https://www.cs.cmu.edu/~mblum/research/pdf/grad.html - Sherline Auction of Its Manufacturing Machines Source: hacker-news Topic: General URL: https://www.bidspotter.com/en-us/auction-catalogues/american-auctioneers-group/catalogue-id-bscam10936 - Alan Kay: Shannon gave us a way of dealing with noisy channels [video] Source: hacker-news Topic: General URL: https://www.youtube.com/watch?v=Cjntrqhn8pk - Ollaya – Ollama for open-source, Jev-style decision models Source: hacker-news Topic: General URL: https://ollaya.dev/ - Astronomer watches Starlink satellites sinking to build a 'planetary barometer' Source: hacker-news Topic: General URL: https://www.theregister.com/science/2026/09/25/astronomer-watches-starlink-satellites-sinking-to-build-a-planetary-barometer/5299036 - How to keep enjoying programming in a world of LLMs Source: lobsters Topic: General (+AI) URL: https://discourse.haskell.org/t/how-to-keep-enjoying-programming-in-a-world-of-llms/14705 - Meta's Muse appears to use an OpenAI model labeled muse-special Source: hacker-news Topic: General (+AI) URL: https://mouse.dev/blog/muse-special/ - Tesla moves to electrify trucking after a decade of work and delays Source: hacker-news Topic: General URL: https://techcrunch.com/2026/09/25/tesla-finally-moves-to-electrify-trucking-after-a-decade-of-work-and-delays/ - weave: structural merging for different languages Source: lobsters Topic: General (+Rust) URL: https://github.com/Ataraxy-Labs/weave - LP Voting and Investor Consent for AIFs Source: hacker-news Topic: General URL: https://taghash.io/blog/lp-voting-and-investor-consent-for-aifs-a-practical-workflow - Ezra Klein's Podcast with Jensen Huang Source: hacker-news Topic: General URL: https://thezvi.substack.com/p/on-ezra-kleins-podcast-with-jensen - Snap Wants to be a State Actor??–Kansas v. Snap Source: hacker-news Topic: General URL: https://blog.ericgoldman.org/archives/2026/09/snap-wants-to-be-a-state-actor-kansas-v-snap.htm - The cheap new AI model taking aim at OpenAI and Anthropic Source: hacker-news Topic: General (+AI) URL: https://www.ft.com/content/456884ea-2558-4648-8036-a77b73733430 - Show HN: Doom or Bloom, map your AI worldview Source: hacker-news Topic: General URL: https://www.doom-or-bloom.com - Typst makes big strides Source: hacker-news Topic: General URL: https://lwn.net/Articles/1092993/ - Show HN: I discovered roads in the US across > 1000 themes Source: hacker-news Topic: General URL: https://road-about-a-theme.pinedesk.biz/ - How to use this project? Source: lobsters Topic: General URL: https://github.com/antirez/ds4#how-to-use-this-project - Meta bans another Toronto performer from Instagram and Facebook over Bikini Source: hacker-news Topic: General URL: https://www.thestar.com/news/gta/meta-bans-another-toronto-performer-from-instagram-and-facebook-saying-an-old-photo-of-dancers-in-bikinis-promotes-harm/article_36e2d204-66c0-4559-aa37-0c26b6ce7b87.html - Gravity seems holographic. What does that mean for reality? Source: hacker-news Topic: General URL: https://www.quantamagazine.org/gravity-seems-holographic-what-does-that-mean-for-reality-20260925/ - U.S. appeals court upholds designation of Anthropic as supply chain risk Source: hacker-news Topic: General (+AI) URL: https://www.cnbc.com/2026/09/25/pentagon-anthropic-ai-risk-appeals-court.html - Reinventing the wheel to draw wide tree hierarchies Source: lobsters Topic: General URL: https://lonami.dev/blog/tree-node-positioning/ - Classified estimates show the NSA is paying billions to test AI models Source: hacker-news Topic: General URL: https://www.washingtonsun.com/technology/classified-estimates-nsa-paying-billions-to-test-ai-models - The Netherlands Built a Nix-Basd Linux Desktop Because Microsoft Cut Off the ICC Source: hacker-news Topic: General URL: https://itsfoss.com/news/netherlands-dawo-initiative/ - Previously unheard recordings of John Coltrane, captured by Frank Tiberi Source: hacker-news Topic: General URL: https://www.jazzwise.com/content/news/john-coltrane-centenary-celebrations-see-impulse-records-release-the-legendary-tiberi-tapes - Show HN: Jev Plays Pokémon Red Source: hacker-news Topic: General URL: https://jev-pokemon.vercel.app/ - Factorio that you can touch Source: hacker-news Topic: General URL: https://factorio.com/blog/post/fff-447 - C's Flexible Integer Sizes Were Not a Design Mistake Source: hacker-news Topic: General URL: https://pikuma.com/blog/c-integer-sizes-not-a-mistake - Starcraft Brood War self-play RL bot beats strong human [video] Source: hacker-news Topic: General URL: https://www.youtube.com/watch?v=Lfo4C0xzU04 - An SR-71 Blackbird Has Vanished (Updated) Source: hacker-news Topic: General URL: https://www.twz.com/air/a-sr-71-blackbird-has-vanished - Microsoft abandons personal AI chatbot race with Copilot reboot Source: hacker-news Topic: General URL: https://www.bloomberg.com/news/articles/2026-09-25/microsoft-abandons-personal-ai-chatbot-race-with-copilot-reboot - Allow Carriers on Planes Source: hacker-news Topic: General URL: https://www.jefftk.com/p/allow-carriers-on-planes - First Principles Thinking Source: hacker-news Topic: General URL: https://sunilsadasivan.com/writing/first-principles-thinking/ - ASML says it sold 'absolutely nothing' in Europe in 2026 Source: hacker-news Topic: General URL: https://www.tomshardware.com/tech-industry/semiconductors/asml-says-its-sells-absolutely-nothing-in-europe-calls-on-eu-to-help-create-demand - Does Georgism work? Five years later Source: hacker-news Topic: General URL: https://www.astralcodexten.com/p/does-georgism-work-five-years-later - What happens when you analyze your favorite college football team like the CIA? Source: hacker-news Topic: General URL: https://www.cultivatelabs.com/posts/what-happens-when-you-analyze-college-football-like-the-cia - The state of SIMD in Rust in 2026 Source: hacker-news Topic: General URL: https://shnatsel.github.io/state-of-simd-rust-2026/ - Show HN: Hacker Atlas - A map of what Hacker News talks about Source: hacker-news Topic: General URL: https://hackeratlas.com/ - We’re gonna need a lot more mathematicians Source: lobsters Topic: General URL: https://terrytao.wordpress.com/2026/09/24/were-gonna-need-a-lot-more-mathematicians/ - Commodified Intelligence Source: lobsters Topic: General URL: https://herecomesthemoon.net/2026/09/commodified-intelligence/ - A New Experiment Meta-Strategy Source: hacker-news Topic: General URL: https://chillphysicsenjoyer.substack.com/p/a-new-experiment-meta-strategy - We Should Be Able to Change Our Languages Source: hacker-news Topic: General URL: http://jimmyhmiller.com/change-our-languages - Show HN: Hamilton – a no-internet Android health dashboard, named after my dog Source: hacker-news Topic: General (+AI) URL: https://play.google.com/store/apps/details?id=com.gads.hamilton&hl=en_US - Nobody Asked for a Crab Chair Source: hacker-news Topic: General URL: https://newmobility.com/nobody-asked-for-a-crab-chair/ - The Test Source: hacker-news Topic: General URL: https://tante.cc/2026/09/24/the-test/ - I'm Tired of Being on the Network Source: hacker-news Topic: General URL: https://matduggan.com/im-tired-of-being-on-the-network/ - Platform-independent SIMD in Go Source: hacker-news Topic: General URL: https://go.dev/blog/simd-experiment - Git-bug: Distributed, offline-first bug tracker embedded in Git Source: hacker-news Topic: General URL: https://github.com/git-bug/git-bug - Pentium II at 600Mhz with Voodoo 3 Emulated on 86Box with M6 Mac Mini Source: lobsters Topic: General URL: https://nyaa.sh/reviews/mac-mini-m6-emulation - CommonGrid: The open source registry of the US power grid Source: lobsters Topic: General URL: https://commongrid.info - This Month in Redox - August 2026 Source: lobsters Topic: General (+Rust) URL: https://www.redox-os.org/news/this-month-260831/ - PipePipe: NewPipe hard fork implementing SponsorBlock Source: hacker-news Topic: General URL: https://github.com/InfinityLoop1308/PipePipe - Show HN: Agentic CUDA Kernel Optimizer Source: hacker-news Topic: General URL: https://github.com/bertaye/agentic-cuda-optimizer - A Type Stronger than the Sum of its Components Source: lobsters Topic: General (+Rust) URL: https://www.schneems.com/2026/09/24/a-type-stronger-than-the-sum-of-its-components/ - The Mafia may be keeping fentanyl out of Italy Source: hacker-news Topic: General URL: https://economist.com/europe/2026/09/24/the-mafia-may-be-keeping-fentanyl-out-of-italy - Oracle on the hook to pay data centre investors even if site has no electricity Source: hacker-news Topic: General URL: https://www.ft.com/content/a96bf05a-a299-4d6a-a753-b298dd0f4016 - An airport cooled by natural ventilation Source: hacker-news Topic: General URL: https://www.theguardian.com/environment/2026/sep/25/didnt-need-air-conditioning-airport-cooled-natural-ventilation-reunion - I wrote a ray tracer in Brainfuck Source: hacker-news Topic: General URL: https://epestr.com/blog/writing-a-ray-tracer-in-brainfuck/ - Theranos founder reportedly to be transferred to halfway home next year Source: hacker-news Topic: General URL: https://www.theguardian.com/us-news/2026/sep/24/theranos-elizabeth-holmes-transfer-halfway-home - Topcoat is pushing the boundary of server applications with Rust Source: hacker-news Topic: General URL: https://tokio.rs/blog/2026-09-24-topcoat-server-applications - Ink and Switch interactive homepage Source: hacker-news Topic: General URL: https://www.inkandswitch.com/ - What About Rails? Source: lobsters Topic: General URL: https://jardo.dev/what-about-rails - Cross-Site Scripting (XSS) Cheat Sheet Source: lobsters Topic: General URL: https://portswigger.net/web-security/cross-site-scripting/cheat-sheet - Boards of Casio Source: hacker-news Topic: General URL: https://www.ambionix.com/blog/boards-of-casio/ - Special Projects (2016) Source: hacker-news Topic: General (+AI) URL: https://openai.com/index/special-projects/ - Tell HN: OpenAI $500 ProMax plan listed in API Source: hacker-news Topic: General (+AI) URL: https://news.ycombinator.com/item?id=49841605 - Dutch governments builds alternative for Microsoft based on NixOS Source: hacker-news Topic: General URL: https://www.dawo.community/en/ - Amiga screens: a primer Source: lobsters Topic: General URL: https://www.datagubbe.se/amscr/ - LLM Policies: Progress At All Costs Source: lobsters Topic: General (+AI) URL: https://diegoe.be/2026/09/25/llm-policies-progress-at-all-costs/ - Entering and Breaking the Avast Antivirus Sandbox Part 2 Source: hacker-news Topic: General URL: https://www.safateam.com/intelligence-hub/research/technical-articles/cve-2025-13032-entering-and-breaking-the-avast-antivirus-sandbox-part-2 - Grieving the loss of details Source: lobsters Topic: General URL: https://purplesyringa.moe/blog/grieving-the-loss-of-details/ - London's schools are running out of children Source: hacker-news Topic: General URL: https://www.ft.com/content/5b019594-5b20-479a-8549-7b564127eb3f - AI is not “just a tool” Source: lobsters Topic: General URL: https://brettcodes.com/ai-is-not-just-a-tool/ - Who Is Open Source About? Source: lobsters Topic: General URL: https://blog.glyph.im/2026/09/who-is-open-source-about.html - I stopped letting LLMs do arithmetic Source: hacker-news Topic: General (+AI) URL: https://medium.com/@jwbobbink/best-search-console-mcp-in-2026-gsc-wizard-7a63f91191ca - Jev Based Code Review Source: hacker-news Topic: General URL: https://github.com/egma-ai/jev-code-reviewer - What are you doing this weekend? Source: lobsters Topic: General URL: https://lobste.rs/s/bubfjf/what_are_you_doing_this_weekend - Plan mode is dead Source: hacker-news Topic: General URL: https://www.aymannadeem.com/artificial/intelligence,/developer/tools/2026/09/24/plan-mode-is-dead.html - Paranoia-Sans: A conspiratorial typeface Source: lobsters Topic: General URL: https://github.com/flegfleg/Paranoia-Sans - Understanding NvPCRs in systemd v262 Source: lobsters Topic: General URL: https://katexochen.aro.bz/posts/systemd-v262-nvpcrs/ - Show HN: Avoid smooth spinners, use low-FPS spinners Source: hacker-news Topic: General URL: https://nh2.me/low-fps-spinners/low-fps-spinners.html - Evolving programming languages in the AI era Source: hacker-news Topic: General URL: https://dashbit.co/blog/evolving-ai-era - Biology might not be quantum, but its math is quantumlike Source: hacker-news Topic: General URL: https://www.quantamagazine.org/biology-might-not-be-quantum-but-its-math-is-quantumlike-20260923/ - Every package is already installed Source: lobsters Topic: General URL: https://fzakaria.com/2026/09/24/every-package-is-already-installed - Real-Time Telemetry with Eventlog Live Source: lobsters Topic: General URL: https://www.well-typed.com/blog/2026/09/real-time-telemetry-with-eventlog-live/ - The AI Build-Out Is Becoming the Biggest Economic Bet in U.S. History Source: hacker-news Topic: General URL: https://www.wsj.com/economy/the-ai-build-out-is-becoming-the-biggest-economic-bet-in-u-s-history-c60716dd - Goodbye Google Source: lobsters Topic: General (+AI) URL: https://robert.ocallahan.org/2026/09/goodbye-google.html - Paul Graham on LLMs 'Thinking' Source: hacker-news Topic: General (+AI) URL: https://twitter.com/paulg/status/2103135915195371973 - Lobsters: Rename vibecoding to llms (Greasemonkey script) Source: lobsters Topic: General (+AI) URL: https://greasyfork.org/en/scripts?by=1646191 - Remembering Johannes Doerfert Source: lobsters Topic: General URL: https://blog.llvm.org/posts/2026-09-24-rememberingjohannesdoerfert/ ## Media - SIG Node Meeting for 2026-09-25 Source: youtube-kubernetescommunity Topic: DevOps URL: https://www.youtube.com/watch?v=FX2aLJP3_qM - SIG Contribex Meeting for 2026-09-25 Source: youtube-kubernetescommunity Topic: DevOps URL: https://www.youtube.com/watch?v=KHi_4p_EZhE - Meta is pivoting again... everything you missed from Connect 2026 Source: youtube-fireship Topic: Web (+General, JavaScript) URL: https://www.youtube.com/watch?v=c1rPlzxSZ8E - How to use Claude, Codex, and BYOK in GitHub Copilot for VS Code | GitHub Copilot Day Source: youtube-github Topic: Open Source (+AI, General) URL: https://www.youtube.com/watch?v=_Mqr5B3DLgM - How to build custom tools with Canvas in the GitHub Copilot app Source: youtube-github Topic: Open Source (+General) URL: https://www.youtube.com/shorts/Ln0L9Ptey_8 - walking out onto the 'G 🔥 Source: youtube-docker Topic: DevOps URL: https://www.youtube.com/shorts/se-4mrQlZg4 - Grand Final Parade | Media Conference Source: youtube-docker Topic: DevOps URL: https://www.youtube.com/watch?v=1ScrbBv5UtU - we got some TALL BOYS 🪜 Source: youtube-docker Topic: DevOps URL: https://www.youtube.com/shorts/9CntLogRg9E - PURPLE INVASION 💜 Source: youtube-docker Topic: DevOps URL: https://www.youtube.com/shorts/gaeiEAa7Nr4