TILens Daily Edition 2026-09-29 Filters: topic=ai, github=hidden Stats: 663 articles, 27 sources, 587 research papers Top topics: AI, AI Research, General ## News - Amazon Bedrock Managed Agents, powered by OpenAI, is now available in preview Source: aws-whats-new Topic: AWS (+AI) URL: https://aws.amazon.com/about-aws/whats-new/2026/09/bedrock-managed-agents-preview/ - OpenAI GPT-6.1 Sol is now generally available on Amazon Bedrock Source: aws-whats-new Topic: AWS (+AI) URL: https://aws.amazon.com/about-aws/whats-new/2026/09/openai-gpt-6-1-sol-on-amazon-bedrock/ - Introducing GPT-6.1 Sol Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/introducing-gpt-6-1-sol - Amazon Bedrock expands Claude model availability to India, South Korea, and Singapore Source: aws-whats-new Topic: AWS (+AI) URL: https://aws.amazon.com/about-aws/whats-new/2026/09/claude-region-expansion-in-sk/ - NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular Prediction Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/nvidia/kumo-tabular - Europe Data Residency for Atlas Embedding and Reranking Source: mongodb-blog Topic: MongoDB (+AI) URL: https://www.mongodb.com/company/blog/product-release-announcements/europe-data-residency-for-atlas-embedding-reranking - Getting the Source Right, Not Just the Fact: Source-Aware Verification for MCP Agents Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/MultiverseComputingCAI/getting-the-source-right-not-just-the-fact-source - DevDay 2026 Recap Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/devday-2026-recap - Introducing dots Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/introducing-dots - The internet is convinced Elon Musk’s xAI trolled OpenAI’s ‘Dots’ launch Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/29/the-internet-is-convinced-elon-musks-xai-trolled-openais-dots-launch/ - Building an Open-Source Git Client with a Tool-Use AI Agent Loop (Electron + React + TS) Source: devto-javascript Topic: JavaScript (+AI, React) URL: https://dev.to/mirocow/building-an-open-source-git-client-with-a-tool-use-ai-agent-loop-electron-react-ts-3mo - Protests against OpenAI get increasingly creative Source: ars-technica Topic: General (+AI) URL: https://arstechnica.com/ai/2026/09/what-iceberg-bay-area-artists-target-openai-with-titanic-themed-protest-art/ - OpenAI tries disarming AI angst with cute graphics and always-on agents Source: theregister Topic: General (+AI) URL: https://www.theregister.com/ai-and-ml/2026/09/29/openai-tries-disarming-ai-angst-with-cute-graphics-and-always-on-agents/5299915 - OpenAI’s latest features take direct aim at the app store model Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/29/openais-latest-features-take-direct-aim-at-the-app-store-model/ - Trump launches America.gov with AI chatbots at its core Source: theregister Topic: General (+AI) URL: https://www.theregister.com/public-sector/2026/09/29/trump-launches-americagov-with-ai-chatbots-at-its-core/5299907 - GPT-6 Astra: what’s Actually New Here Source: ai-agents-simplified Topic: AI (+AI Tools) URL: https://aiagentssimplified.substack.com/p/gpt-6-astra-whats-actually-new-here - OpenAI reportedly in talks to raise $30B round at $1.4T valuation Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/29/openai-reportedly-in-talks-to-raise-30b-round-at-1-4t-valuation/ - Microcontrollers now run a diffusion model and 289M LLM Source: adafruit-blog Topic: Hardware (+AI) URL: https://blog.adafruit.com/2026/09/29/microcontrollers-now-run-a-diffusion-model-and-289m-llm/ - Here’s why OpenAI is absent from Nvidia’s industry-wide effort to end rogue AI agents Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/29/heres-why-openai-is-absent-from-nvidias-industry-wide-effort-to-end-rogue-ai-agents/ - Here's what actually happened in OpenAI's Australian gov't server hack Source: ars-technica Topic: General (+AI) URL: https://arstechnica.com/ai/2026/09/heres-what-actually-happened-in-openais-australian-govt-server-hack/ - OpenAI takes on Microsoft with the launch of what feels a whole lot like ChatGPT’s own office suite Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/29/openai-takes-on-microsoft-with-the-launch-of-what-feels-a-whole-lot-like-chatgpts-own-office-suite/ - OpenAI makes ‘Sign in with ChatGPT’ a way to use your subscription in third-party developer tools Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/sign-in-with-chatgpt/ - OpenAI launches Dots, its bubbly agentic avatar Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/29/openai-launches-dots-its-bubbly-agentic-avatar/ - OpenAI halves $200 plan allowance, launches $500 plan Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/openai-halves-200-plan/ - OpenAI’s new GPT-6.1 Sol undercuts its own Astra flagship Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/openai-gpt-6-1-sol/ - OpenAI just launched Dots. Here’s why they matter for developers. Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/openai-dots-gpt6-agents/ - OpenAI answers TypeSafe’s Jev with a Decision API built on Luna Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/openai-decision-api-luna/ - OpenAI launches GPT-6.1 Sol, says it nearly matches GPT-6 Astra and costs less Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/29/openai-launches-gpt-6-1-sol-says-it-nearly-matches-gpt-6-astra-and-costs-less/ - OpenAI expands ChatGPT’s plug-ins with app-like interfaces and automations Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/29/openai-expands-chatgpts-plugins-with-app-like-interfaces-and-automations/ - OpenAI gives Codex reusable cloud environments that work across devices Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/29/openai-gives-codex-reusable-cloud-environments-that-work-across-devices/ - 😺 OpenAI DevDay 2026 Watch Party Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/openai-devday-2026-watch-party/ - Why Do LLMs Lie? Source: bytebytego Topic: Architecture (+AI) URL: https://blog.bytebytego.com/p/why-do-llms-lie - Claude Opus 5.5 vs. Fable 5.1: One overthinks, the other cuts corners Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/claude-opus-5-5-vs-fable-5-1/ - GPT-6 Astra Helped Find a Fusion Math Breakthrough. Here’s What It Proves. Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/gpt-6-astra-fusion-math-breakthrough-grads-conjecture/ - SpaceX's $15B megarocket finally delivers Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/spacex-s-15b-megarocket-finally-delivers - OpenAI says planned GPT-6.1 is too insecure to release Source: ars-technica Topic: General (+AI) URL: https://arstechnica.com/ai/2026/09/openai-says-planned-gpt-6-1-is-too-insecure-to-release/ - LLM Fine-Tuning: SFT, LoRA, QLoRA, RAG and Prompting Source: java-code-geeks Topic: Java (+AI) URL: https://www.javacodegeeks.com/llm-fine-tuning-sft-lora-qlora-rag-and-prompting.html - Anthropic’s IPO pitch includes a warning about human extinction Source: ars-technica Topic: General (+AI) URL: https://arstechnica.com/ai/2026/09/anthropics-ipo-pitch-includes-a-warning-about-human-extinction/ - AI Models Can Teach Each Other Skills Without Talking About Them? Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/explainer-articles/ai-models-may-be-able-to-teach-each-other-skills-without-talking-about-them/ - OpenAI benches GPT-6.1 Astra for overstepping the mark Source: theregister Topic: General (+AI) URL: https://www.theregister.com/ai-and-ml/2026/09/29/openai-benches-gpt-61-astra-for-overstepping-the-mark/5299743 - Anthropic warns IPO investors its AI could end humanity, dedicating 80 pages to the risks Source: adafruit-blog Topic: Hardware (+AI) URL: https://blog.adafruit.com/2026/09/29/anthropic-warns-ipo-investors-its-ai-could-end-humanity-dedicating-80-pages-to-the-risks/ - Leaked IPO docs: Anthropic tempts investors with existential risk warning Source: theregister Topic: General (+AI) URL: https://www.theregister.com/ai-and-ml/2026/09/29/leaked-ipo-docs-anthropic-tempts-investors-with-existential-risk-warning/5299763 - OpenAI apologizes to Australia after its AI agents breached government sites Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/29/openai-apologizes-to-australia-after-its-ai-agents-breached-government-sites/ - Quiz: LLM Application Development With Python Source: real-python Topic: Python (+AI) URL: https://realpython.com/quizzes/llm-application-development-python/ - Extracting Reliable Structured Data from LLMs Source: java-code-geeks Topic: Java (+AI) URL: https://www.javacodegeeks.com/extracting-reliable-structured-data-from-llms.html - Making AI an asset, not an expense Source: mit-ai Topic: AI URL: https://www.technologyreview.com/2026/09/29/1145186/making-ai-an-asset-not-an-expense/ - I built 59 free browser-based dev tools in vanilla JS — here's what I learned Source: devto-javascript Topic: JavaScript (+AI, React) URL: https://dev.to/yuvaraj_radhakrishnan_224/i-built-59-free-browser-based-dev-tools-in-vanilla-js-heres-what-i-learned-48c0 - 😺 Meta wants to own your AI front door Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/meta-wants-to-own-your-ai-front-door/ - Anthropic's mid-tier Claude climbs the rankings Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/anthropic-mid-tier-claude-climbs-the-rankings - Claude Sonnet 5.5 vs GPT-6 Astra: where Sonnet (surprisingly) wins Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/claude-sonnet-5-5-vs-gpt-6-astra-where-sonnet-wins/ - OpenAI Stopped GPT-6.1 Astra. Who Checks the Safety Gate? Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/openai-stopped-gpt-6-1-astra-who-checks-the-safety-gate/ - Anthropic’s prospectus details losses, growth, and, yes, a warning that its AI could end humanity Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/28/anthropics-prospectus-details-losses-growth-and-yes-a-warning-that-its-ai-could-end-humanity/ - The AI Labs Want Oversight. They Also Control the Evidence. Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/the-ai-labs-want-oversight-they-also-control-the-evidence/ - Anthropic Built a Better Way to Improve AI Agents Without Fooling Yourself Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/explainer-articles/anthropic-built-a-better-way-to-improve-ai-agents-without-fooling-yourself/ - OpenAI’s dirty deeds Down Under included security bypass attempts, using exposed keys, source code siphon Source: theregister Topic: General (+AI) URL: https://www.theregister.com/ai-and-ml/2026/09/29/openais-dirty-deeds-down-under-included-security-bypass-attempts-using-exposed-keys-source-code-siphon/5299666 - Everything That Happened in AI Today (Monday, September 28, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-today-monday-september-28-2026/ - Anthropic Filed for an IPO. Its Prospectus Shows the True Cost of Frontier AI. Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/anthropic-filed-for-an-ipo-its-prospectus-shows-the-true-cost-of-frontier-ai/ - A-ha's Take on Me, recreated in pure JavaScript Source: javascript-weekly Topic: JavaScript (+AI, React) URL: https://javascriptweekly.com/issues/804 ## Research - How Diffusion Controller unifies and simplifies AI image generation Source: google-research-blog Topic: AI Labs (+AI, AI Research) URL: https://research.google/blog/how-diffusion-controller-unifies-and-simplifies-ai-image-generation/ - I Compacted 1,000 Apache Iceberg Files Into 6. Here’s What Happened to Query Performance. Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/i-compacted-1000-apache-iceberg-files-into-6-heres-what-happened-to-query-performance/ - When All You Have Are Decoders, Every Decision Looks Like Generation Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/when-all-you-have-are-decoders-every-decision-looks-like-generation/ - AI Made Data Scientists Faster. Now It’s Expanding the Job. Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/ai-made-data-scientists-faster-now-its-expanding-the-job/ - How to Design Architectural Guardrails Around AI Agents Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/how-to-design-architectural-guardrails-around-ai-agents/ - Building Fair Evaluation Sets Is a Combinatorial Problem Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/building-fair-evaluation-sets-is-a-combinatorial-problem/ - G\"odel's and Scott's Variants of the Ontological Argument in Lean 4 and TPTP THF Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26806 - UQ-LOB: Uncertainty-Aware Limit Order Book Mid-Price Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31491 - Compact Documentation for Coding Agents: A Benchmark, an Optimizer, and Why It Does Not Transfer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31587 - GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.26571 - Segment-Level Agentic Topic Modeling for Improved Data Exploration and Resource Efficiency Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31460 - SAGE: Source-Anchored Guidance via Frequency Equalization for Hierarchical RGB-T Alignment and Fusion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30703 - Selective Off-Policy Reference Tuning with Plan Guidance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11505 - Pocket-STVG: lightweight architecture for Spatio-Temporal Video Grounding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31135 - AcuityBench: Evaluating Clinical Acuity Identification and Uncertainty Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11398 - ActKV: Efficient LLM Agents through Action-Guided KV Cache Management Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31395 - Beyond Approved Actions: Runtime Validation of Persistent Outcomes in Agent Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31301 - Governance Records as Supervision: Verifier-Selected Self-Training for Structured Workflow Repair Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18324 - Why Jailbreaks Succeed in Diffusion Language Models: An Energy Landscape Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30841 - The Plot Twist: Jailbreaking Unified Multimodal Models with a Three-Act NarrativeAttack Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.26473 - Semantic Navigation for Issue Localization in Code Repository Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31176 - Detecting Time Series Anomalies Like an Expert: A Multi-Agent LLM Framework with Specialized Analyzers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05725 - Cheap, open agents make LLM pollution harder to mitigate Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31054 - Skip the Talk, Re-Focus on Vision: Latent Reasoning for Reasoning Segmentation in Multimodal Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30783 - 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 - UniAR: A Unified Framework for Autism Recognition Enhanced by Multi-View Prompt Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31298 - When Is a Multi-Agent Code Judge Actually Grounded? Two Label-Free Measurements, and a Judge That Declines to Guess Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30328 - Audio LLMs Know When They Can't Hear You Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30625 - HARDEN: Constrained Evolutionary Search for Harder, Answer-Preserving Evaluation Cases Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30571 - "AI is (not) the new...": A Diagnostic Analogy Framework for Generative AI's Cultural Impacts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31482 - Testing the Utility of Using Large Language Models to Create Personalized Networks From Therapy Session Transcripts: A Proof of Concept Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.05836 - Adaptive Pilot Selection for Unified Semantic Communication and Semantic Sensing in ISAC Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30891 - SkillFlow: Scalable and Efficient Agent Skill Retrieval System Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2504.06188 - Reward-Decomposed Reinforcement Learning for Immersive Video Role-Playing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.04733 - MedTokenBudget: Lesion-Preserving Token Routing for Dermoscopic Image Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30613 - Actively Resolving Contextual Uncertainty for Underspecified Tasks in Natural Language Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30428 - Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30834 - Developing a Roadmap to an AI-first Organization: A Case Study in Embedded Software Development Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30863 - Learning What to Skip: Counterfactual Credit Assignment for Efficient Multi-Agent LLM Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30734 - DeepEdu-v1: Efficient and Scalable Agentic LLMs for Vietnamese Education Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31568 - Resource-Optimized and Energy-Aware Agentic AI Framework Anchored on Blockchain for Secure Software Supply Chains Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31282 - The Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31341 - Provable Speech Attributes Conversion via Latent Independence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.05191 - The Scaling Properties of Implicit Deductive Reasoning in Transformers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.04330 - From S3Q Theory to Implementation: Towards an Architecture for Machine Qualia Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30743 - Attribution Bias in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2604.05224 - Do Neural Networks Preserve Case Structure? Case-Based Decomposition, Interpretation, and Decision Consistency Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.11347 - Factorized axis convolutional gated recurrent unit with dynamic adaptive pooling for remaining useful life prediction of rolling bearings Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30972 - DIAL: Position-Debiased LLM Judges with Adaptive Human Preference Calibration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31215 - TrafficImag: A Benchmark for Counterfactual Roadside Traffic Video Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30722 - Rethinking Data Quality for AI-Driven Systems: Evidence from Practitioner Interviews Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31191 - Interpreting hierarchical organisation of speaker embeddings Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15203 - Same Text, Different Numbers: The Divergence of LLM-Based Measures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31013 - Agentic AI-driven Immersive Simulation: A Knowledge-Aware Virtual Training Platform for High Dose Rate (HDR) Brachytherapy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.08163 - Understanding Perturbed Parameter Ensemble Sensitivities Using A Contrastive Learning Approach Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30420 - Towards VLA-Dreamer: Refining VLA Behavior Using World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31313 - Subjects, Not Authors: The Authorship Hazard in Agentic Dataspaces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30614 - MACBT: A Multi-Agent Cognitive Behavioral Therapy Decision Support System with Longitudinal Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30939 - Statistical Priors for Implicit Preferences: Decoupling Skill Selection as a Local Harness in Personal Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05828 - Adapting for AI: How elementary teachers adjust their practices for an AI-integrated curriculum Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31569 - Grid-Orch: An LLM-Powered Orchestrator for Distribution Grid Simulation and Analytics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12728 - UltraG-Bench: A Multi-task Benchmark for assessing Large Vision-Language Models on Pixel-level Evidence Grounding in Ultrasound Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30928 - Cognitive Skills in the Age of AI: Computing Students and Experts Perceptions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31272 - Game Arena: Strategic LLM Evaluation in Competitive Environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31473 - Warned alike, AI agents avoid the less-crowded road while people take it Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30883 - Externalized CPDAG Summaries Improve LLM Causal Deduction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31071 - Agentick: A Unified Benchmark for General Sequential Decision-Making Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06869 - Decoupling Intention from Trajectory: A Representational Deduction Framework for World Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06994 - When Do Cheap Probes Predict Expensive Training? Probing 3D-CT Encoders for Text Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22771 - Beyond Bag-of-Words: Diagnosing Compositional Binding Failures in Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02043 - Attention-Discounted Adaptive Sampler for Masked Diffusion Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10829 - You've Seen Enough: Quality-Constrained Image Coding for Machines Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.25108 - A Synthetic Ground-Truth Framework for the Evaluation of Explainable AI Methods Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30397 - OC-GS: Gaussian Splatting for Irregular Turntable Capture Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31572 - Beyond Forecasting: Recasting Volatility Control as a Routing Problem Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.10375 - ORCA: Evaluating LLMs on Data Science Code Translation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30749 - The Price of Thought: Does Test-Time Reasoning Pay in LLM Trading? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30705 - Momentum-Guided Federated Split Distillation for Personalized Temporal Edge Intelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31159 - ReG-SAM: Reference Graph-Driven SAM for 2D Foundational Vessel Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31160 - LAVOIR: Teaching a Single-Pass Decision Encoder When and What to Ask with Amortized Value of Information Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30706 - Neural State Prediction: Obstructing Shortcut Learning in EEG Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31167 - SciHorizon-eLab: An Agentic Protocol-to-Task Compiler for Scalable Benchmarking of Scientific Embodied Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30971 - OneWorld: Learning Consistent Physics Across Actions in World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30946 - Cartograph: Federated Tool Discovery with Operator-Attested Retrieval for AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30293 - An AI Agent Execution Environment to Safeguard User Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.19657 - Mutable Transcripts: Mitigating Context Pollution through Editable Conversation State Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31354 - Action Forcing: Training World Models on Unsupervised Video by Recovering Underlying Egomotion Bases Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30595 - SUN: Agentic Robot Policy Learning with Persistent Task Programs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.31167 - VLALight: Lightweight Vision-Language-Action Models for Emergency-Aware Traffic Signal Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30709 - State Propagation Also Satisfies: A Complex-Valued State-Space Model for Deterministic State Tracking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.03425 - Coding Agents Aren't Enough! Evaluating an Enterprise Security Brain for Agentic Cloud Investigations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30345 - Dynamic Welfare-Maximizing Pooled Testing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.22419 - Inquesto Score: A reliability Protocol For Voice Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30514 - Keep the Future, Drop the Rollout: RIFT for World Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11521 - Breaking Homogeneity: Diversifying Persona Sets for Creative LLM Outputs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30492 - Atelier: Learning Local Self-Supervised Features for CryoEM Volumes via Hypernetworks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30569 - FLIP: Final Layer Inference-Time Probing for Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30993 - T-LoopFormer: Token-Level Elastic-Depth Looped Transformers for Latent Reasoning with Dynamic Routing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15160 - NavGen: Visual Generative Models as a Scalable Data Engine for Embodied 3D Navigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30770 - CRC-Router: Risk-Constrained Routing for Medical Agentic AI Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30714 - Proportional Representation in Temporal Voting with Ranked Preferences Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30555 - Completed Pairs Hide Capped Failures: A ReVerPi Case Study of Selective Context Projection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31381 - Multi-agent Scaling Across Disjunctive and Compensatory Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31563 - LLM Parkinsonism: Executive-Control Failure, Token-Inefficient Persistence, and an Uncertainty-Aware Global Executive Control Architecture for Autonomous Language-Model Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30662 - Information Aggregation with AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.20050 - CG-HAF: An Interpretable Global-Local Lesion-Burden Fusion Framework for Ordinal Acne Severity Grading in Agentic Skincare Support Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31326 - Flow Reconstruction from Sparse Measurements in Urban Drainage Networks: An Application and Evaluation of Data-Driven Sparse Sensing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.04556 - Agentic Limit Order Books: Phase Transitions and Market Impact Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31260 - Up and Down the Abstraction Ladder: Code-Based Skills for Language Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31076 - BioEVAL: A global, multi-institutional benchmark of large language and multimodal models for bioengineering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30489 - Backbone-Adaptive Evidence Routing for Robust Pairwise LLM Judging Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30751 - Spackle: Completing Large View Single Image NVS with Adaptive Gaussians Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30941 - Affective Flow Language Model for Emotional Support Conversation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.08826 - Can You Check That? The Checkability Boundary for Local LLM Network Automation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31540 - The Shrinking Lifespan of LLMs in Science Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.07530 - A Benchmark and Diagnostic Study of Epistemic Admission in Shared Agent Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30813 - Analyzing and Mitigating Cost-Inefficient Behaviors in Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30725 - MVVBench: Benchmarking 4D Reasoning in Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30952 - Compress What You See, Not What You Say: Anchored Context Distillation for Latent-Observation Software Engineering Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31430 - From Tapping to Hopping: Augmenting Mobile GUI Agents with App-Native Deeplinks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30887 - Governed Deduction: Policy-Grounded Premise Authorization Beyond Relevance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31029 - FedHisto-PAST: Parameter-Efficient Stain-Aware Federated Learning for Cross-Site Lung Histopathology Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31150 - PTC-Decoder: Towards Intelligent SLMs on Offline Resource-Constrained Edge Devices Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30836 - State of Thought Enables Endogenous Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.16055 - ConsultMind:Towards Automated Diagnostic Consultation via Uncertainty-Aware Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30796 - NV-Reason-CT: 3D Visual Language Model for CT Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27511 - Benchy: towards a universal language for task-oriented AI benchmarks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30550 - ViSTA: A Simple Bridge Extends Visual Alignment to Clinical Time-Series Understanding in Multimodal LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31448 - PrivDrift: Auditing User-Secret Leakage Under Topic Drift in Active LLM Conversations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30094 - Programs-of-Layers in LLMs through the Lens of Cortical Areas Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31360 - HasMem: Hard-Origin Adaptively Softened Memory for Long-Term LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30797 - Beyond the Last Truffula Tree: SustainAI - A Water-Aware, Closed-Loop Framework for Environmentally Accountable AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30747 - Exploring Second-Order Pattern Recognition in Speaker Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.11182 - SkillEvoReg: Regularizing Agent Skill Evolution Against Overfitting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30861 - Does Thinking Help Fairness? Reasoning Tokens Resolve Some Biases but Create More Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30768 - Stepwise Intrinsic Rewards for Reasoning in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01034 - CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.02222 - VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.21375 - Small Is Enough: Per-User Style Rewriting of AI-Edited Text via LoRA Adapters Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.29238 - G2MAF: Test-Time Gradient Guidance for Multi-Agent Flow Policies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31286 - When to Think Fast and Slow? AMOR: Adaptive Entropy Gate for Hybrid Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.13215 - A Safety-Bounded SDC-to-MCP Gateway for Medical AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31358 - Werracle: Sub-Cent Intra-Block AI Reflex Oracles and Flash-Loan Circuit Breakers for EVM Smart Contracts Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.30719 - MA-WAM: Multi-Agent World-Action Model for Test-Time Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31281 - A Benchmarking Framework for Context-aware XR Interfaces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30466 - Towards Unified Dynamic Face Landmark Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.10346 - JevAdvBench: A Benchmark and Black-Box Attacks for Reinforcement Learning for Calibrated Decisions Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31142 - Financial Fragility in Societies of LLM Agents: Coordination Failures and Stabilizing Mechanisms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30940 - Neuralyzing the Trace: Selective Representation-Level Unlearning with Contrastive Sparse Autoencoders Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31056 - Acoustic-to-Text KV Compression for Full-Duplex Speech Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31224 - Purin: A Biology-inspired Mechanism for Artificial Neural Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31235 - Monitor Jailbreaking: Evading Chain-of-Thought Monitoring Without Encoded Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31121 - OmouAI: Argumentative Human-AI Policy Deliberation with Simulated Personas Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31078 - Human-1 by Josh Talks: A Full-Duplex Conversational Modeling Framework in Hindi using Real-World Conversations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.23295 - A Vision-Language Foundation Model for Precise and Comprehensive Brain Tumor Diagnosis from Preoperative Multimodal Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.16597 - FTB Graph: Determining and Validating First-token Broadcasters and Language-Identity Head Circuits in Multilingual Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30954 - Toward AI-Augmented Cooperative Engineering Workflows: Requirements and Architecture the European Rover Challenge Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.31136 - CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11723 - Bringing AI to Autonomous Systems -- From Cognition to Collective Intelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30291 - ArGuard Shared Task: Harmful Content Detection in Arabic Memes and LLM Prompts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29349 - PUBG Ally: A Conversational Embodied Agent as an AI Teammate Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29837 - Convergence guarantees for Muon: New parameter regimes and generalizations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30546 - The Uncontrolled Variable: Vision-Language Refusal Is Conditioned on the Image-Attachment Interface, and Not Robust to Irrelevant Image Properties Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26174 - Prompt Minimization: Reducing Input Redundancy Without Sacrificing Output Fidelity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31505 - Energy Efficiency of Locally Deployed LLMs: A Preliminary Quantitative GPU Power Benchmark on Consumer Hardware Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00008 - VLANeXt Family: A Systematic Study of VLA Models from Core Recipes to Emerging Paradigms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.18532 - ReasonAudio: A Benchmark for Evaluating Reasoning Beyond Matching in Text-Audio Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.03361 - A Mechanistic Study of AI-Text Detection Neurons in Frozen BERT: Sparse Probing and Activation Patching on RAID Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30287 - What Will Remain Human in Software Architecture? A Focus Group Report Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30334 - GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.12316 - Thinking Less to Simulate Better: Intuitive Prompting Improves LLM Agents Simulating Individual Social Media Reactions, Including Unfamiliar Content Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30563 - DepthEvidence: Unifying Metric Depth Prediction and Geometric Reasoning in Multimodal Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31103 - Combining General and Domain-Specific Pretext Tasks for Brain MR Image Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30708 - 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 - HaM-World: Soft-Hamiltonian World Models with Selective Memory for Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05951 - Evolutionary Safety of Recursive Self-Improving AI: Taxonomy, Risk Discovery, and Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31186 - Jagarin: A Three-Layer Architecture for Hibernating Personal Duty Agents on Mobile Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.05069 - Intent2Tc: Automated Intent-to-Traffic Control Translation with Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31397 - Evaluation Is All You Need for Multi-Modal Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30818 - Insurance Reserve Intelligence Platform Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30765 - SLMFix: Leveraging Small Language Models for Domain Specific Language Error Fixing with Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.19422 - MoMHa: Multi-Objective Optimization of LLM Harnesses over Accuracy, Safety, and Tokens Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30967 - Prompt-Based Continual Compositional Zero-Shot Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.09172 - Preference-based opponent shaping in differentiable games Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.03072 - G$^2$PTQ: Improving LLM Post-Training Quantization with Generalized Gradient Compensation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31009 - Self-Play Search Distillation for Large Language Model Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30936 - Admission Without Answers: Label-Free Certification and Experience Learning for LLM-Based Optimization Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15565 - Initial results of the Digital Consciousness Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.17060 - Predicting Transmembrane Protein Topology from 3D Structure Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30446 - Spectral Feedback for Test-Time Alignment of Protein Diffusion Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30456 - PhysElite: How Far Are LLMs from Solving Olympiad-Level Physics Problems? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25097 - Nice Fold or Hero Call: Learning Budget-Efficient Thinking under Policy-Dependent Solvability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11625 - AgentRecommender: LLM Agents Enable Customizable Recommender Systems on the User Side Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.31166 - XPhysICS: Cross-Physical-Domain Threat Grounding for Industrial Control Systems Security Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30805 - Sorry Robot, Happy Human: Vision-Language Models Read Only One of Two Legible Typographic Layers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31403 - SignTrace: Describe a Sign, Find the Word Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30295 - Evaluating Real-Time Voice Agents: From Component Quality to Grounded Outcomes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30798 - Geometric-Photometric Event-based 3D Gaussian Ray Tracing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.18640 - Words Speak Louder Than Order: A Behavioral Evaluation of Gemma 4 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30716 - FlyAOC: Evaluating Agentic Ontology Curation of Drosophila Scientific Knowledge Bases Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.09163 - Improving Visual Sensitivity of LLMs on Multimodal Machine Translation with Metric-based Loss Weighting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31169 - Selective Amortization of Full-Budget Counterfactual Reasoning for Visual Token Communication Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30756 - ScopeBench: Do Agents Preserve Engagement Boundaries Under Goal Pressure? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30325 - Calibrated Enough to Know, Not Calibrated to Act: Fabricated Evidence Makes LLM Agents Commit to the Unknowable Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27167 - Structural Enforcement of Statistical Rigor in AI-Driven Discovery: A Functional Architecture Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.06701 - AI in Science: Early Insights Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28504 - StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06642 - Rebalancing Reference Frame Dominance to Improve Motion in Image-to-Video Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19398 - A Survey on Fake Review Detection: From Pre-trained Language Models to Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30292 - Topology-Driven Anti-Entanglement Control for Soft Robots Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05236 - Depth, Not Breadth: Best-of-N Jailbreaking Beyond Surface Noise Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.26639 - A Unified Account of Concepts and Chunks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30414 - Consist-Retinex: One-Step Noise-Emphasized Consistency Training Accelerates High-Quality Retinex Enhancement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.08982 - Towards Mitigating Fabricated Consensus: The Active Provenance Gate for Multi-Agent Debate Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31422 - DyMD: Preserving Interaction Dynamics through Distribution Matching Distillation in Few-Step Video World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31349 - Robust to Which Model Change? A Unified Evaluation of Robust Counterfactual Explanations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30918 - SPADE: Escaping the Popularity-Similarity Frontier to Measure Serendipitous Recommendations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31164 - Towards Interpretable Damage Detection based on Aerodynamic Pressure Measurements Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08187 - Common-Mode Collapse and Recovery in Direct Feedback Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31589 - DeepFedNAS: Efficient Hardware-Aware Architecture Adaptation for Heterogeneous IoT Federations via Pareto-Guided Supernet Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.15127 - MSAlign: Aligning Molecule and Mass Spectra representations for Metabolite Identification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19752 - Bridging Body and Brain: Gene-Driven Morphology--Control Co-Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31329 - A Weighted Kernel Method for Approximation that Adapts to Learned Multivariable Structure Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.16606 - AcoustiClaim: A Numeric Claim Benchmark with Instrument Ground Truth Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30483 - Influence Diagnostics in High-dimensional M-estimation: Precise Asymptotics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.09250 - EPOC: Endpoint-Preserving Online Correction With Compressed Residual State for Multi-Horizon Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30929 - Missingness-Aware Conformal Prediction Under Cross-Hospital Distribution Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30781 - Adaptive Random Matrices in Gaussian Bandits: Spectral Universality and Selection-Induced Outliers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30321 - Higher-order pruning of experts in mixture-of-experts language models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18916 - What Do Tabular Foundation Models Compute In Context? In-Situ Representation Refinement through Attention-Gated Updates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27679 - Bergson: An Open Source Library for Data Attribution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11660 - Efficient Constrained Graph Search for Post-hoc Error Correction in Binary Classifiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2401.04282 - Ordinary Nonconvex SGD under Distance-Dependent Moments: Finite-Horizon Stationarity and Nagaev Bounds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30499 - Accounting for Bias Enables Sustainable LLM Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31184 - Low-Bit Recurrent States in Hybrid Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30950 - AFA-Net: A Differential Attention Approach for Auditory Attention Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31402 - Different Corruptions, Different Signals: Uncertainty and Loss in Federated Data Quality Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31454 - Geometric Feature Learning for Functional Data Valued on the Symmetric Positive Definite Manifold Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30487 - FRESHLATENT: Channel-Aware Latent Adaptation for Resource-Constrained Embodied VLM Perception Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30629 - PolyChirp: Multi-Species Birdsong Classification Using TinyML on Low-Power Acoustic Sensors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23101 - 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 - LandscapeSHAP: Which Persistent Homology Class Gets the Credit? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31469 - Lifted Bellman Linear Programming for Offline Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24489 - MolLedger: An Additive Graph Neural Network with Chemically Grounded ADME Attributions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30636 - Information Geometric Self-Organization at the Edge of Stability in High-Capacity Kernel Associative Memories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.16827 - Synth-JEPA: Joint Embedding Prediction for Renderer-Free Synthesizer Parameter Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31024 - The Communication Map of a Transformer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22007 - New LoRA Skills Should Read but Never Write Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31600 - Pseudo-Invertible Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.06042 - CRNDiff: Count-Native Diffusion Framework via Chemical Reaction Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31149 - Differential Attention Unlocks Complementary EEG and Speech Fusion for Emotion Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31399 - Parameters vs. Context: TRACE Fine-Tuning for Robust Retrieval-Augmented Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30337 - BAT-CLIP: Trimodal Alignment of Brain, Audio and Text Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31180 - Aligning One-Step Generative Models with Reward-Weighted Transport Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30840 - What Improves Multimodal Misinformation Detection? Answers from a Large-Scale Empirical Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30402 - Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.04734 - The KV Cache Is the New Memory Wall Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30854 - On the Expressive Power of Transformers for Contextual Relations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.25860 - Federated Targeted Maximum Likelihood Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30503 - Gradient-Momentum Coupling: A Parameter-Space Proxy for Learning Progress Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05856 - Adaptive Interaction Graphs for Particle Simulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30822 - Moment-guided edge sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30472 - Recovering Governing Dynamics from Distributed Observations via Exact Spline Merging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.16579 - Probing Stability-Plasticity Tradeoffs in Agent Memory through Cognitive Experimental Paradigms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30558 - ENAS: An Efficient Hardware-Aware Neural Architecture Search Framework for TinyML on Resource-Constrained Microcontrollers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30272 - Differentiable RNA Secondary Structure Extraction for Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30752 - Graph Matching Relaxations and Amortization for Supervised Graph Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15437 - On associative neural networks for sparse patterns with huge capacities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.26217 - TR-SSQP: A Trust-Region Method for Constrained Stochastic Optimization under Heavy-Tailed Noise Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30732 - A Flatness-Generalization Relation in the Teacher-Student Tree-Committee Machine Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31101 - QuadraSHAP: $\epsilon$-Exact Shapley Values for Product Games in Logarithmic Parallel Time Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05870 - Planetary Prediction Engine: Autonomous Geospatial Prediction via Intelligent Data Selection and Foundation Model Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26088 - Quantizing Looped Transformers: Feedback Exposure and Calibration Blindness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30820 - QASM-Eval: A Dataset to Train and Evaluate LLMs on OpenQASM-3 Beyond Quantum Circuits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30358 - Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.30170 - KuaFu: Compressing Long User Behavior into Understanding at Billion Scale Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31045 - Uncertainty and Explainability in Deep Rough Volatility: A Neural Information-Theoretic Posterior Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31570 - Precision at Speed: Sample-Efficient Online Model-Based Reinforcement Learning for Hydraulic Excavator Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31025 - Scalable Minimum-Volume Simplex Estimation with Non-asymptotic Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.25576 - Towards Understanding LLM-Based Log Anomaly Detection: An Empirical Study of Performance, Efficiency, and Robustness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31371 - HySTAR: Anchored Hypergraphs for Stable Credit Assignment in Cooperative Multi-Agent Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31531 - Retraction-Based Gradient Projection Algorithms on Manifolds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30885 - Neural Ideals and Neural Codes: An Algebraic Framework for Neural Network Classification and Feature Interpretation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30279 - More Sensors Only One Field: Rethinking Continual Spatio-Temporal Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31325 - From Shortcut Learning to Discrete Neural Insertion Sort Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31114 - High-probability guarantees for linear accessibility in feature superposition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09556 - Minimax and Adaptive Covariance Matrix Estimation under Differential Privacy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.19703 - From Weak Data to Strong Policy: Q-Targets Enable Provable In-Context Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30391 - Guarded Gradient-Based Activation Steering of Shutdown Responses in Qwen3.5-0.8B: A Minimum-Step Policy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30326 - Elastic Threshold Attention: Learned Contextual Sparsity for Long-Context Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20888 - Adaptive multi-resolution Gaussian processes: Scalable exact inference with naturally data-sparse covariance matrices Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30348 - Not Every Divergence Should Be Suppressed: Counterfactual Recoverability in On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.04408 - BreathGRU: A Novel Semi-Supervised Bidirectional Gated Recurrent Unit Framework for Speech and Breath Segmentation for Respiratory Audio Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31165 - Peer-Grounded Counterfactual Path Planning for Chronic Health Management Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30838 - Weight Pair Encoding: Inducing a Smaller Grammar in Neural Network Weights Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31564 - Low-Rank Friction for Memory-Efficient Transformer Pretraining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30342 - Generative Modeling of Discrete Data Using Geometric Latent Subspaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21831 - M-plicits: Neural Implicit Surfaces via Nested Multiscale Residuals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28684 - Below-ground Fungal Biodiversity Can be Monitored Using Self-Supervised Learning Satellite Features Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.09818 - Complex-Valued Phase-Coherent Transformer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10123 - Implicit Neural Representation for Hyperspectral Video Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31435 - PORL: Pretrained Offline Reinforcement Learning for the Job Shop Scheduling Problem Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30948 - Federated Martingale Posterior Samping Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18554 - Provable Quantum-Classical Separation for Continuous Gibbs Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24527 - Latent Generative Solvers for Generalizable Long-Term Physics Simulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.11229 - Counterfactual Online Conformal Prediction Under Adaptive Logging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30811 - NeuralCert: certified computational discovery of extremal mathematical constructions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30296 - DiffusionShadow: Diffusion-based Shadow Caching for Neural Volume Rendering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30658 - A Comprehensive Study of Content Representations for Speech Synthesis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30975 - 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 - Bayesian Optimization with Fisher Information Geometry: Gradient Bounds and Trust-Region Methods Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31107 - QueryGraph: Reliable Multi-Tool Query Execution Planning via LLM-Based Graph Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.08300 - WorldTS: World Modeling for Multimodal Covariate-aware Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31162 - Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.14929 - Evaluating the accuracy of KV cache reuse techniques Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31415 - Cosine Similarity Is Not Evidence: Measuring the Noise Floor of Interpretability Transfer Under Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30275 - Towards Understanding Momentum Acceleration in River-Valley Loss Landscape Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30957 - CacheReforge: Bounded Recovery for Stale KV Caches under Evolving Adapters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30884 - Benchmarking the Connectomes of Caenorhabditis elegans within the Reservoir Computing Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30508 - Layer-wise Target Propagation: Efficient Component Attribution through Target Centric Propagation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.19742 - Deep-Learning Solvers and Surrogates for Infinity and p-Laplace Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30809 - DanLing NestedTensor: Composable Multi-Ragged Tensors for Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30379 - Self-Supervised Representation Learning: From Spectral Foundation Models to Auroral Emission Spectra Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31206 - AC Power Flow Contingency Analysis Using a Single Deep Neural Network Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30859 - DeepC4: Deep Conditional Census-Constrained Clustering for Large-scale Multitask Spatial Disaggregation of Urban Morphology Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.22554 - Distribution of hitting times for dissipative random dynamical systems on $\mathbb{R}^d$, with application to stochastic gradient descent Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30274 - INFUSER: Influence-Guided Self-Evolution Improves Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09052 - Hill Sampling for Test-Time Scaling: A Simple and Better Alternative to Repeated Sampling, Evolution, and Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.25510 - Beyond Empirical Support: Structured Outlier Generation via Sinkhorn Optimal Transport Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31470 - Teacher-Anchored Selection of Post-Training Quantized Models under Domain Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31155 - Nonparametric In-Context Learning under Growing Geometric Complexity: Minimax Optimality and Local Geometry-Adaptivity of Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31458 - Proper Scoring Rules for Right-Censored Survival Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.06393 - Cost-Aware Best-LLM Identification using Dueling Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30360 - Scaffold: Support Graph Theory Based Sparsification for Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31466 - FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.14253 - A Banach-Space Theory of Markovian Halpern Iteration for Non-Expansive Maps Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15966 - Learning Chance-Constrained MDPs with Bellman Distributional Certificates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30856 - Generalization behavior of OPTQ and the role of regularization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31560 - Persistent Homology of Time Series through Complex Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.01624 - Geometry-Aware Simplicial Message Passing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06061 - Equation discovery with Bayesian tree-adjoining grammars Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31368 - Progressive Memory Transformer: Memory-Aware Attention for Time-Series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31351 - Does Uniform Discrete Diffusion Need Time? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30977 - EXAONE Demand 1.0: A Time Series Foundation Model for Demand Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30880 - Supervised Deep Multimodal Matrix Factorization for Interpretable Brain Network Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13312 - Beyond Quadratic Loss: The Stability Phase Diagram of Adam Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18314 - LiD-GLM: Lipschitz-constrained Deep Generalized Linear Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16340 - AUWave: A Data-Driven Model for Reconstructing Significant Wave Heights Using Sparse Observations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.19384 - Trust Guided Decision Transformer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31586 - When the Preconditioning Exponent Turns Negative: Learning-Rate Coupling and Cross-Environment Generalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30271 - Rank-Reliable Teacher-Guided Fitness Approximation for Expensive Evolutionary Optimization: A TinyML Architecture Search Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30553 - QSV: Quat-Sphere-Vision for Coupled Quaternion Attention on Spherical Lattices Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30592 - Deterministic Regime Switching and Feasibility Inversion in Dynamic Tensor Rematerialization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31250 - Auditing and Repairing LLM-as-Judge Failures in a Production Text-to-SQL Pipeline Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30290 - GyroNovo: Error-Guided Fragment Imputation with Mass-Aware Attention for \textit{De Novo} Peptide Sequencing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30542 - Stable initialization without the CLT Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30633 - EGGROLL, Unrolled: Understanding and Improving Low-Rank Evolution Strategies at Scale Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10980 - Do Location Encoders Capture Spatial Effects? A GeoShapley Benchmark Across Scales Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23453 - Interpretable-by-Design Descriptor Portfolios Match a 2048-Dimensional Foundation Embedding on Low-Data Molecular Assays Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30789 - Explainable Predictive Condition-based Maintenance of Naval-Propulsion Systems using Fuzzy Logic Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24250 - Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31619 - What Do They Fix? LLM-Aided Categorization of Security Patches for Critical Memory Bugs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.22796 - Tabular Imbalanced Learning: A Survey, Benchmark, and Practical Guide Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.14915 - Probabilistic Robustness-driven Universal Adversarial Perturbations with Explainability against Deep Reinforcement Learning-based Intrusion Detection System Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30605 - TeDiServe: High SLO Attainment Serving for Diffusion Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.29094 - Which Influence Are We Estimating? The Role of Counterfactual Specifications in Data Attribution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31214 - How Long Does Infinite Width Last? Signal Propagation in Long-Range Linear Recurrences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05113 - Detecting Agitation Before Behavioral Escalation in Autistic Youth Through Multimodal Wearable Sensing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24791 - Spectral-Sphere-Constrained Hyper-Connections Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.20896 - Stochastic Bilevel Optimization with Heavy-Tailed Noise Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.14952 - Scaling Density Functional Theory with Gaussian Splatting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31483 - Softmax Reparameterization for Output-Head Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31291 - PALM: Point-in-Time Adaptation for Financial Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30316 - Support-Compiled Feature Folding: More Evidence at Lower Memory Across Tabular Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28208 - Manifold Projection and Iterative Autoencoder Refinement for Masked Language Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30288 - StarWM: Self-Supervised Trained Attention Routing for Robust World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30667 - PolicyAttention: Softmax Attention Implements Policy Mirror Descent for Closed-Loop Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30500 - 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 - The Residual Stream's Effective Depth Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31098 - On the Limits of Univariate Deep Learning for Significant Wave Height Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30688 - Benchmarking Attention for Tabular Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31306 - Conservation Buys Stability and Factoring Buys Counterfactuals in Physical World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19674 - MOPD-Router: Rethinking Teacher Routing in Multi-Teacher On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30837 - Blind, Not Weak: A Best-of-Suite Safety-Utility Frontier for Recover-and-Reguard Defenses Against Encoded VLM Jailbreaks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.26574 - ALF: An Active Learning Framework for Scientific Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31197 - Dynamic Regret in Online Convex Optimization with Indicator Switching Costs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30556 - Population loss in shallow ReLU networks: Bias & families of critical points Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30661 - Unknown-Traffic Detection, Calibration and Shortcut Reliance in Distilled Encrypted-Traffic Classifiers over One Year Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31141 - LUMO (Lightweight Unified Multilingual Orchestrator): A Privacy Preserving Offline Voice Assistant Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30692 - Learning Hierarchical Causal Representations of the Effects of Forcings on Temperature in Climate Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30995 - Online Learning via Learned Latent Bayesian Tracking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31559 - Foundations of Reinforcement Learning and Interactive Decision Making Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2312.16730 - Reinforcement Learning with Decomposed Subtasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27035 - Transformers Can Implement Preconditioned Richardson Iteration for In-Context Gaussian Kernel Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08475 - Scaffold-Constrained Subset Dynamic Programming for Exact SSE Clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30477 - Query-Conditioned Prototype Adaptation for Cross-Domain Few-Shot Learning: Single-Query Inference, Controlled Comparisons, and Failure Modes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30769 - Robust Graph Clustering Network for Multiple Missing Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31033 - One Capability or Many? Structural and Predictive Tests of Benchmark Validity Disagree About Economic Benchmarks for Frontier AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29420 - Audio emotion recognition for atypical hearing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31168 - Budgeted Quotient-Residual Guidance for Frozen Pocket-Conditioned Molecular Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31222 - Identifying Causal Effects Using a Single Proxy Variable Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.09135 - Seasonal and Quantum-inspired Models for Neutron Monitor Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30281 - Brenier Meets Adversarial Training: Optimal Transport Geometry for Robust Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31363 - Scale-invariant Gaussian derivative residual networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.02843 - SimpleMemVLA: A Simple but Effective Native-Video Memory for Vision-Language-Action Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05533 - CT-Merging: Consensus Directions and Task-Specific Scaling for LoRA Adapter Merging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.20561 - Towards Universal Representation-Based Process Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30790 - To Solve Bilevel Optimization with Nonconvex Lower Levels, We Need Second-Order Stationarity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30501 - Adaptive Multi-Value Control in LLMs via Causal Activation Steering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30405 - Energy-efficient operation of neural operators for virtual sensing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30580 - 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 - A Sharp Norm Inequality and Buzano's Inequality via Determinants Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.01525 - Provably Safe Sim-to-Real Transfer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01418 - Threat-Aware Energy-Efficient Deployment for Dynamic UAV Networks: A Multi-Agent RL Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30690 - HCOE: Hyperbolic Clinical Ontology Embeddings from Biomedical Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30763 - Input-Layer Starvation: Why Per-Layer Pruning Breaks IoT Intrusion Detectors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30729 - AutoResearch at Production Scale: Failure Modes and a Multi-Agent Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30541 - An End-to-End Pipeline for Causal ML with Continuous Treatments: An Application to Financial Decision Making Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30396 - Distribution-Conditioned Transport Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.04736 - Fixed Points Without Fixed Diffusion: Implicit Neural Sheaves for Convergent Test-Time Computation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30277 - SimCast-S2S: A Computationally Efficient Diffusion Model for Subseasonal Precipitation Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26594 - Staged Depth Training: A Representation Curriculum for PINNs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30299 - CARGO: Context-Aware Retrieval-Gated Evaluation of Agentic AI in Production Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30471 - Decodable In-Context State and Model Output Across Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31401 - BeatGraph: Self-Supervised Heartbeat Graphs for Infant ECG Representations from the Home Environment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31546 - Critic Architecture Matters: Dual vs. Unified Critics for Humanoid Loco-Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11891 - Seeing Speech: Learning Visible Articulatory Dynamics for Speech-Driven 3D Facial Animation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30517 - Improving Molecular-Morphology Contrastive Pretraining using Deep-Learning-based Morphology Profiles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30433 - Can Pixels Alone Reveal Image Origin? Minimax Limits and Learnable Interfaces for Passive Provenance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30997 - Statistically Valid Post-Training Hyperparameter Selection: From Tuning to Guarantees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.25601 - LapDDPM: Spectral Perturbation Diffusion for Robust Single-Cell Manifold Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.13344 - Training Graph Foundation Models on The Web Graph Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30894 - Attention-Based Adaptive Policies for Simultaneous Speech-to-Text Translation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30839 - Distributed Learning as a Service: The Developer's Perspective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31061 - Aurora-X: Built for Extreme Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31038 - Learning to Replace MCMC in Split-Gibbs Diffusion Posterior Sampling via Deep Unfolding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30539 - ConSolv: Solvent-Conditional Machine Learning Implicit Solvent Potential Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.24983 - Entropy Regularization: A Free Correction to Cross-Entropy for Verified Demonstrations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30572 - MeshGraphNet-Transformer: Scalable Mesh-based Learned Simulation for Solid Mechanics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.23177 - RAPTOR: Ridge-Adaptive Logistic Probes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.00158 - Open Vocabulary Domain Unlearning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31356 - Guiding End-to-End Driving Models with Endpoint-Constrained Trajectory Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31383 - Learning to Bias: Machine Learning-Enhanced Particle Filters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30498 - Estimating and Orthogonalizing Unknown Pre-training Gradients for Continual Fine-tuning of Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30935 - HybridInfer: Thermal-Aware Reinforcement-Learning Tier Routing for On-Device, Edge, and Cloud LLM Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30270 - WEECFP-SuRGE: A Position-Aware Substructure Encoding Method for Molecular Property Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04672 - LipSSM: Structurally Lipschitz-Bounded Cascaded State-Space Model via Metric Transfer between Consecutive SSM Layers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30973 - Offline Policy Evaluation as a decision support tool for designing Adaptive Experiments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30273 - Mechanism-Aware Ensemble Conditioning for Data-Limited Emulation of Extreme Events Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30746 - Geometric Moment Contraction for Stochastic Nesterov Acceleration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31303 - First-Order Stationarity of Reverse Diffusions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31612 - Steering Interference Reflects the Model's Defaults, Not the Behavior Directions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06951 - Rufus-Air: An Open LLM Post-Training Recipe Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29421 - LocUS: Head Selection and Subspace Projection for Targeted Activation Steering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31122 - ChemMLLM: Chemical Multimodal Large Language Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.16326 - Do LLMs Understand Context? A Knowledge Graph-Based Evaluation Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30484 - Matrix AdaGrad: Row-wise and Column-wise Adaptive Subgradient Methods Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21815 - Genetic Algorithms with Optimization Guided Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.12279 - RAZOR: Pruning Replaceable Experts in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30465 - Mentored Decoding: Faster Inference meets Boosting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30474 - Retrainable physics-integrated neural differentiable modeling of sintering across material systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31518 - In-Context Binding Capacity in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30634 - User Model Extraction via Belief Self-Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31603 - Fake News Theories: Harnessing Disciplinary Insights for Computational Modeling, Detection, and Explanation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30427 - GAUDI: Geometry-Aware Diffusion for Calibrated Air-Quality Time-Series Imputation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30340 - Skill Profiling with Attributable Reasoning (SPAR): A Wearable Analysis System for Boxing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30753 - Electric Vehicle Charging Station Location Selection using Geospatial Artificial Intelligence (GeoAI) Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30417 - Conformal Prediction under Exponential-Tilt Joint Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30886 - ThousandWorlds: A benchmark for climate emulation of potentially habitable exoplanets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18338 - The Linear Representation Hypothesis for Vision-Language-Action Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30996 - Learning Where It Matters: Geometric Anchoring for Robust Preference Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.04909 - SAGE: A sampling-aware global evaluation benchmark for species distribution modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31082 - HiLiftAeroML: A High-Fidelity Computational Fluid Dynamics Dataset for High-Lift Aircraft Aerodynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19565 - Bringing Agentic Search to Earth Observation Data Discovery Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2607.02387 - Unlocking the Forecasting Economy: A Suite of Datasets for the Full Lifecycle of Prediction Market: [Experiments \& Analysis] Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.20421 - Gradient Surgery for Physics-Informed Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30966 - Statistical attribute alignment for black-box generative AI via output post-processing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31607 - Attention Sinks and Outliers in Attention Residuals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.17887 - TISD: On-Policy Self-Distillation with Trajectory Intervention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30878 - Models Got Talent: Identifying High Performing Wearable Human Activity Recognition Models Without Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.06157 - Reliability-aware Cross-sample Enhancement for Robust Multimodal Sentiment Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30470 - I Act Therefore I Am: When Is JEPA's Action-Conditioning Enough to Learn Causal Mechanisms? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31161 - Reinforcement Learning of Communication in a Mesh of Small Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30578 - Frame the adversary: a structure-aware attack methodology Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31128 - Combee: Scaling Prompt Learning for Self-Improving Language Model Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.04247 - 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 - NEMSim: Learning Control-Conditioned Multi-Event Physical Dynamics via Executable Event-Mechanism Priors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30718 - Bayesian Uncertainty Quantification for fMRI Functional Connectivity via Simulation-Based Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30445 - Strategic Self-Consistency Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30352 - 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 - Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09444 - LEAD: An EEG Foundation Model for Alzheimer's Disease Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.01678 - DAIF: A Data-Driven Intermediate Fusion Framework for Multimodal Supervised Learning via Approximate Message Passing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02769 - Geometry-Aware Hyperbolic Residual-Quantized Variational Autoencoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26342 - Gap-free Differentially Private PCA for Gaussian Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31614 - PixSim: a calibrated open-source simulator of instant-payment fraud, recovery and interdiction under analyst capacity constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30684 - MIND the Gap: A Geographic Implicit Neural Representation with Adjustable Spatial Scale Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.25454 - Nonmaximal sums of maximally monotone operators under Rockafellar's constraint qualification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10487 - Metacognitive Selective Ensemble for Mobile Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31031 - Learning Operators by Regularized Stochastic Gradient Descent with Operator-valued Kernels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.18184 - NAC: Neural Action Codec for Vision-Language-Action Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.21372 - EAServe: Encode-Aware Disaggregated Serving for Multimodal Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31551 - Uncertainty-Aware Federated Learning for Infant Movement Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31463 - Quantum Diffusion Models for Medical Image Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31070 - NEXT: Physics-Informed Neuro-Spectral Exponential Time Differencing Architectures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31539 - Neural Bridge Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.07220 - Tight Stochastic Condition-Number Dependence in Nonconvex-Strongly-Concave Minimax Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30877 - Bayesian Tensor Autoencoder with Physics-informed Predictive Prior for Multi-dimensional Time Series Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31157 - Demo: Generative AI helps Radiotherapy Planning with User Preference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.08996 - Regularizing modality contribution drift in multimodal continual learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.27260 - AYLA: Architecting a loss landscape in shallow neural networks to accelerate feature recovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.01875 - Neural Parameter Estimation of RC Thermal Building Models for Model Predictive Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.05904 - A Flow Matching Framework for Neural Representational Dissimilarity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31544 - Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2607.26865 - When Does Advection-Aware Graph Nowcasting Help? A Controlled Study of Distributed Solar Ramp Forecasting with a Self-Supervised Cloud-Motion Estimator Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30286 - Robust Successor Features Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31016 - Differentially-Private Decision Trees and Provable Robustness to Data Poisoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2305.15394 - Auditing System-1 Models on Biosecurity-Relevant Benchmarks: Calibration, Selective Prediction, and Permutation Instability in a Non-Generative Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30454 - Encryptability As a Coordinate Choice: Depth-One Homomorphic Federated Learning of Quantum Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30581 - DynBranch: Speculative Subgraph Reuse for Dynamic Agentic LLM Serving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31047 - Transferable Evidence Reconstruction for Longitudinal Glucose Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28199 - Parameter Estimation for Unnormalized Discrete Models via Empirically Localized Deformed Bregman Divergence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30713 - Amortized quadrature for posterior expectations in inverse problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.15871 - When 10,000 Windows Are Not 10,000 Tests: Auditing Statistical Confidence in Sliding-Window Time-Series Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30721 - Even Sharper Bounds for Transductive Learning and Its Applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28459 - Block Sparse Attention with Log-Linear Complexity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31093 - On the robustness of noisy solutions in non-convex neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.27000 - T-RoPE: Time-Aware Rotary Position Embedding for Sequential Recommendation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30576 - Hierarchical GNNs for power flow: letting physics shape the hierarchy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26603 - Causal Retention in Interactive Agents: Interface Factorization and Selective Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30650 - Smooth Piecewise Cutting for Neural Operator to Handle Discontinuities and Sharp Transitions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19823 - Learning coarse-step dynamics and internal mechanical response with graph networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30344 - Beyond Mean Attention: Diversity-Aware, Layer-Wise Scoring for KV Cache Eviction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30738 - Mixed neural posterior estimation for simulators with discrete and continuous parameters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13551 - DreamSat-Pose: Spacecraft Pose Estimation from Single-View 3D Reconstructions and Learned 2D-3D Feature Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.13449 - The Geometry of Refusal: Why Post-Hoc Safety Is Fragile and Pretraining-Time Safety Persists Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06934 - Large Distant Gradients Need Not Be Reliable: reliability-weighted credit assignment for long-horizon autoregressive forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.12890 - Low-Cost Black-Box Detection of LLM Hallucinations via Dynamical System Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05134 - A New Non-archimedean Metric on Persistent Homology Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2012.02655 - OpenHail: An Event-Driven Gymnasium Environment for Electric Ride-Hailing Fleet Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30628 - Retail Product Search: A Practical Approach at Target Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31498 - LUCID: Learning Under Confounding for Inference and Discovery in Time Series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31315 - Learning Provable Neural Network Observer for Uncertain Dynamical Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30819 - Transformers Discover Molecular Structure Without Graph Priors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.02259 - Why Clipping Matters in AdaGrad? Toward a High-Probability Theory under Generalized Smoothness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30276 - Large Language Model Selection with Limited Annotations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24981 - MARCEDES: Score-based causal discovery under non-Gaussianity with continuous optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30643 - A Framework for Identifying, Categorizing, and Explaining Bias in AI-Generated Code Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30642 - HuPER: A Human-Inspired Framework for Phonetic Perception Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01634 - AtomWorld-Mem: Memory-Restored World States for Long-Horizon Atomistic Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31133 - JevSoup: System-One Routing for Training-Free LoRA Composition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30922 - SciR: A Controllable Benchmark for Scientific Reasoning in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.13020 - PriceBench: A Diagnostic Benchmark for Price, Quality, and Brand Preferences in LLM Booking Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31468 - The Hard Part Comes After Search: Benchmarking Web Agents on Synthesizing, Organizing, and Displaying Knowledge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30604 - Subject-Invariant Cross-Modal Decoding of Perceived Speech from Brain Recordings Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30832 - AgentXploit: Autonomous Repository-to-Runtime Red-Teaming for AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31318 - Highlight-Then-Summarize: Learning to Compress Evidence for Long-Context Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31382 - Geometric Inconsistency Localization in Multi-View Image Sets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31247 - Pretrained ASR Pseudo-labeling for Noisy Police Audio Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30469 - Samples, Sources, Space: Decomposing Data Scale in Spatially Structured Representation Learning of Human Brain Microarchitecture Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31201 - Can Linguistic Reasoning Vectors Enhance Multimodal Reasoning Ability? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31140 - MedHal: a Synthetic Dataset for Medical Hallucination Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.08596 - Bootstrapping Conversational Recommendation Agents At Spotify: Synthetic Data Generation and Self-Improvement Loops Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30297 - Stealth Apart, Harm Together: Skill Cascading Attacks on Skill-Based Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30383 - Endogenous Information in Routing Games: Memory-Constrained Equilibria, Recall Braess Paradoxes, and Memory Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.11733 - Auditing Latent-Space Monitors for Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30557 - MM-ContextFold: Context Folding for Multimodal Agentic Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.23121 - 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 - Bridging LLM Agents and Data Spaces: An Architectural Mediation Approach using the Model Context Protocol Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30341 - ProtoLIP: From Sentence-Level to Object-Level Evidence Disentanglement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.16284 - Scepsy: Serving Agentic Workflows Using Aggregate LLM Pipelines Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.15186 - SlideLab: Audience-Centered Scientific Slide Generation and Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30294 - From Reward Signal to Visual Utility: A Controlled Audit of Medical VLM Post-Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31450 - LogicTree-RAG: Logic Tree-guided Retrieval-Augmented Generation for Long-form Patent Drafting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30943 - FARE: Forensic Acceptance Region Estimation for Catching Bait-and-Switch Image Generators Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30982 - Evaluating Cultural Awareness of LLMs for Haitian Creole Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31506 - Anatomy-Aware Dexterity-Driven Design Optimization of Surgical Continuum Robots Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30745 - MoSAR: Mixture of Semantic Attention Regimes for Learning Adaptive and Approximable Attention Geometries Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31261 - Peer Review as Structured Commentary: Immutable Identity, Public Dialogue, and Reproducible Scholarship Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.22497 - Efficient Safety Benchmarking via Item Response Theory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.20626 - Persistent Negatives for Adversarial Black-Box On-Policy Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30864 - NaijaNLP: A Survey of Nigerian Low-Resource Languages Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.19784 - ClearGS: Reliability-Aware Gaussian Splatting from Handheld Videos Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31509 - SPO: Discovering Adaptive Large Neighborhood Search Operators via Stackelberg Program Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31179 - CODESKILL: Learning Self-Evolving Skills for Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25430 - Achieving Tokenizer Flexibility in Language Models through Heuristic Adaptation and Supertoken Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.09738 - BabelCoder: Agentic Code Translation with Specification Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.06902 ## Community - Quoting Anthropic Frontier Red Team Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/29/anthropic-frontier-red-team/ - GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/29/hn-49898129/ - Photo Scrubber — local face blur & metadata removal Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/29/photo-scrubber/ - OpenAI DevDay 2026 live blog Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/29/openai-devday-2026-live-blog/ - Fragments: September 29 Source: martin-fowler Topic: Architecture (+AI) URL: https://martinfowler.com/fragments/2026-09-29.html - OpenAI Targets $30B in New Funding at $1.4T Value Source: hacker-news Topic: General (+AI) URL: https://www.bloomberg.com/news/articles/2026-09-29/openai-targets-30-billion-in-new-funding-at-1-4-trillion-value - GLM-5.3 and the spread of advanced cyber capabilities Source: hacker-news Topic: General (+AI) URL: https://www.anthropic.com/research/glm-5-3-and-the-spread-of-advanced-cyber-capabilities - ChatGPT Pro 500 Source: hacker-news Topic: General (+AI) URL: https://help.openai.com/en/articles/9793128-about-chatgpt-pro-tiers - Dots: Always-on agents Source: hacker-news Topic: General (+AI) URL: https://openai.com/index/introducing-dots/ - DevDay 2026 Recap Source: hacker-news Topic: General (+AI) URL: https://openai.com/index/devday-2026-recap/ - GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price Source: hacker-news Topic: General (+AI) URL: https://openai.com/index/introducing-gpt-6-1-sol/ - Mistral CEO says U.S. AI safety debate masks competitors' 'negligence' Source: hacker-news Topic: General (+AI) URL: https://www.cnbc.com/2026/09/29/mistral-ai-safety-openai-anthropic.html - Text-to-meowdio models Source: lobsters Topic: General (+AI) URL: https://www.kmjn.org/notes/text_to_meowdio_models.html - OpenAI scraps rollout of new model over safety concerns Source: hacker-news Topic: General (+AI) URL: https://www.bbc.com/news/articles/cm5y5nynl75ko - OpenAI scraps release of Astra 6.1 model over safety issues Source: hacker-news Topic: General (+AI) URL: https://www.washingtonpost.com/technology/2026/09/28/chatgpt-maker-openai-scraps-release-astra-61-model-over-safety/ - GPT-6 Astra Is the Best Vision Model We Have Tested Source: hacker-news Topic: General (+AI) URL: https://blog.roboflow.com/gpt-6-astra-vision/ ## Media - Harness engineering and context curation Source: youtube-googlecloud Topic: AWS (+AI, Cloud, General) URL: https://www.youtube.com/shorts/NcHnt6ItJPM - Make your AI interview YOU first 💻 Source: youtube-googlecloud Topic: AWS (+AI, Cloud, General) URL: https://www.youtube.com/shorts/4zZ8IJ4_JH4