TILens Daily Edition 2026-10-05 Filters: topic=ai, github=hidden Stats: 860 articles, 28 sources, 816 research papers Top topics: AI, AI Research, General ## News - AWS Weekly Roundup: Amazon Bedrock Managed Agents powered by OpenAI, Q3 service availability updates, Kiro workflows, and more (October 5, 2026) Source: aws-news-blog Topic: AWS (+AI) URL: https://aws.amazon.com/blogs/aws/aws-weekly-roundup-amazon-bedrock-managed-agents-powered-by-openai-q3-service-availability-updates-kiro-workflows-and-more-october-5-2026/ - Our approach to EU text provenance rules Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/eu-text-provenance - Building advertising for the way people use AI Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/new-chatgpt-ads-format-and-measurement - dbForge 2026.2 Adds a PostgreSQL Debugger, Visual Object Editors and Broader Context for dbForge AI Assistant Source: postgres-news Topic: PostgreSQL (+AI) URL: https://www.postgresql.org/about/news/dbforge-20262-adds-a-postgresql-debugger-visual-object-editors-and-broader-context-for-dbforge-ai-assistant-3394/ - Create an AI Voice Agent for Customer Support Source: devto-javascript Topic: JavaScript (+AI, FastAPI, Python) URL: https://dev.to/voice_developer/create-an-ai-voice-agent-for-customer-support-440b - Developers are secretly hoping OpenAI fails to ship this month Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/openai-codex-shipping-sprint/ - OpenAI will start watermarking ChatGPT’s text in the EU Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/10/05/openai-will-start-watermarking-chatgpts-text-in-the-eu/ - OpenAI brings text watermarking to its API — and unlike Anthropic, it’s off by default Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/openai-api-text-watermarking/ - The AI safety check that runs on a laptop and nearly matched a 35B model Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/red-hat-guardrail-benchmark/ - OpenAI to flood your eyeballs with visual ads Source: theregister Topic: General (+AI) URL: https://www.theregister.com/ai-and-ml/2026/10/05/openai-to-flood-your-eyeballs-with-visual-ads/5301152 - Connecting AI agents to enterprise knowledge Source: mit-ai Topic: AI URL: https://www.technologyreview.com/2026/10/05/1145580/connecting-ai-agents-to-enterprise-knowledge/ - The LLM Blindspot: Why Models Forget What’s in the Middle of Your Prompt Source: bytebytego Topic: Architecture (+AI) URL: https://blog.bytebytego.com/p/the-llm-blindspot-why-models-forget - OpenAI launches visual ads that appear alongside image generation results Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/10/05/openai-launches-visual-ads-that-appear-alongside-image-generation-results/ - [$] An update on the Sashiko patch-review system Source: lwn Topic: Open Source (+AI) URL: https://lwn.net/Articles/1096963/ - California crashes robot fight club Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/california-crashes-robot-fight-club - 64 AI Concepts Every Software Engineer Should Know Source: system-design-newsletter Topic: Architecture (+AI) URL: https://newsletter.systemdesign.one/p/ai-concepts-explained-for-beginners - Bringing predictive analytics to the agentic AI era Source: mit-ai Topic: AI URL: https://www.technologyreview.com/2026/10/05/1143813/bringing-predictive-analytics-to-the-agentic-ai-era/ - Security updates for Monday Source: lwn Topic: Open Source (+AI) URL: https://lwn.net/Articles/1098599/ - What the Kyoto Vision Means for AI-Powered Science Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/kyoto-vision-ai-powered-science/ - Import AI 475: Swarm scaling; Google DeepMind watermarks biology; and the AI science economy Source: importai Topic: AI URL: https://importai.substack.com/p/import-ai-475-swarm-scaling-google - Anthropic says its IPO could herald the end of the world as we know it Source: theregister Topic: General (+AI) URL: https://www.theregister.com/ai-and-ml/2026/10/05/anthropic-says-its-ipo-could-herald-the-end-of-the-world-as-we-know-it/5300908 - What If AI Is a Phase in Earth’s Evolution? Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/explainer-articles/what-if-ai-is-a-phase-in-earths-evolution/ - Cubicle v0.21: my AI-agent office now asks me things (and I can answer from Telegram) Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/megventure/cubicle-v021-my-ai-agent-office-now-asks-me-things-and-i-can-answer-from-telegram-265b - Ubuntu 'Stonking Stingray' beta swims out: Deeper Rust 'oxidization' plus LLM speech-to-text Source: theregister Topic: General (+AI) URL: https://www.theregister.com/os-platforms/2026/10/05/ubuntu-stonking-stingray-beta-swims-out-deeper-rust-oxidization-plus-llm-speech-to-text/5301023 - Presentation: Building Reusable Evaluation Frameworks for Agentic AI Products Source: infoq-architecture Topic: Architecture (+AI) URL: https://www.infoq.com/presentations/elastic-ai-agent-evaluations/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Architecture+%26+Design - 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-347a - 😺 Trump named an AI czar Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/trump-named-an-ai-czar/ - What Nvidia and AMD’s AI Acquisitions Say About the Next Chip War Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/why-chipmakers-nvidia-amd-buying-ai-companies/ - An OpenAI safety insider calls the culture 'broken' Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/an-openai-safety-insider-calls-the-culture-broken - People really hate AI, so why can’t they get enough? Source: mit-ai Topic: AI URL: https://www.technologyreview.com/2026/10/05/1145682/people-really-hate-ai-so-why-cant-they-get-enough/ - Stay ahead in web development: latest news, tools, and insights #157 Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/urbanisierung/stay-ahead-in-web-development-latest-news-tools-and-insights-157-3ij - EmTech Future 2026: When AI Meets Everything Source: mit-ai Topic: AI URL: https://www.technologyreview.com/2026/10/05/1145413/emtech-future-2026-when-ai-meets-everything/ ## Research - Open and Emergent Problems in Agentic Privacy and Security: A Contextual Angle Source: google-research-blog Topic: AI Labs (+AI, AI Research) URL: https://research.google/blog/open-and-emergent-problems-in-agentic-privacy-and-security-a-contextual-angle/ - Computer Vision: SIFT algorithm (Scale Invariant Feature Transform) Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/computer-vision-sift-algorithm-scale-invariant-feature-transform/ - How to Build a Cheap, Yet Reliable Model Router With Jev Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/how-to-build-a-cheap-yet-reliable-model-router-with-jev/ - A Locally Penalized Cross-Estimate Federated Method with Guarantees for Constrained Personalized Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.19617 - XGenAct: Geometry-Enhanced World Action Models through Cross-Task Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03516 - HyperFuse: Fast Self-Supervised Node Embeddings for Attributed Hypergraphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03211 - DyRA: Dynamic Residual Approximation for Efficient Matrix Multiplication in DNNs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02882 - Get a GRIP, this will be a long TRIP: A Quantifiable Long-Range Framework for Verifying Over-squashing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03556 - Mastering Atari 2600 Games with Discovered Options Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03604 - DAGR: State-Conditioned Goal Representations via Difference-Aware Goal Cross-Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.13731 - Penalized Nonreversible Langevin for Constrained Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.25381 - FastKernels: Benchmarking GPU Kernel Generation in Production Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23215 - SimuVerity: Benchmarking Agents for Engineering-Grade Simulink Model Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02304 - Efficient Neural Field Learning via Adaptive Coverage and Focused Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02410 - It Takes Little to Rewrite Perception: Targeted Semantic Substitution in Vision-Language Models at $\epsilon \leq 4/255$ Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38298 - Student-Guided Teacher Distillation for Efficient LLM Task Routing: Positioning Against Jev-Style System-1 Classifiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02516 - LayerRoute: Action-Conditioned Mixture-of-Layers Routing for Vision-Language-Action Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06079 - Fisher-Guided Submodular Data Selection for Continual Pre-Training of Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02593 - Invariance of Clustering Operations in Causal Effect Identification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03101 - PTNO: Training Neural Operators with Noisy Monte Carlo Estimates for Particle Transport Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.40090 - LESSER: Post-Training Data Selection with Output-Layer Gradients Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03702 - Distributed Learning with Selective State Space Models: Architecture-Aware Convergence Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02659 - Exact Recovery Thresholds for Weighted Data Selection in Vector-Valued Linear Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30254 - Cocoon: A System Architecture for Differentially Private Training with Correlated Noises Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.07304 - Smart Sensing for Safer Bridges: From Sensor Signals to AI-Driven Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03082 - Trained Agentic Context Management Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02404 - Cross-cohort TB classification using clinical data gathered in Uganda and South Africa Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03256 - VERSE: Verified Self-Evolving Optimizer for Agent Harnesses Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02616 - Kernel Singular Value Decomposition with Extension to Multiple Data Sources Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03216 - Differential Privacy as a Perk: Federated Learning over Multiple-Access Fading Channels with a Multi-Antenna Base Station Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.23463 - Sentry: Learning to Recover from LLM Agent Failures at Test Time Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02994 - Learning from Evolving Errors: Adaptive Iterative Repair for On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02700 - On the Limits of LLM Adaptability: Impact of Model-Internalized Priors on Annotation Task Performance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00467 - Denser $\neq$ Better: Limits of On-Policy Self-Distillation for Continual Post-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.01763 - Multi-Fidelity Policy Gradients Stabilize Data-Scarce Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02505 - Do ResNets Route? Sparse Interaction Experts in Residual Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02907 - A Width-Matched Comparison of Hybrid Quantum-Classical Self-Supervised Learning for Fingerprint Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39172 - Mitigating Watermark Forgery in Generative Models via Randomized Key Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.07871 - Objects Without Morphisms: What LLMs for Mathematics Do Not Represent Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03551 - WebFovea: When the Model Is Right but the Click Is Wrong -- Reliable Round Trips for Vision-Based Web Agents on Live Websites Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03036 - Demonstration-Guided Observation Attacks on Black-Box Safe Reinforcement Learning Controllers for Robotic Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.16543 - ArrivalBench: Agent-Generated Data Pipelines Are Correct Once and Wrong Under Time Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02363 - UniIntervene++: An Adaptive Intervention Agent for Efficient Real-World Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03620 - DISSOLVR: An Interpretable and Fast Framework for Aqueous and Organic Solubility Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02574 - Mitigating Convergence Collapse in Fixed-Target Anomaly Detectors via Kernel-Anchored Locality Regularization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02345 - Learning Closure of Dynamical Systems with Kernel Ridge Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02564 - Toward Omni Multimodal Graph Foundation Model: A Topology-Driven Binding Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02881 - Universal Byte-Level Encoding: UTF-8/UTF-16 Routing to Reduce Cross-Script Token-Budget Disparities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01984 - Graph-Conditioned On-Policy Agent Distillation from Off-the-Shelf Teachers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37522 - VisAudit: Evaluating Multimodal Agents for Visual Diagnosis and Repair Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02399 - Measure Less, Know More: Self-Supervised Test-Time Feature Acquisition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03454 - Variance-reduced accelerated methods for decentralized stochastic double-regularized nonconvex strongly-concave minimax problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2307.07113 - Inner Momentum for Differentially Private Muon Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02738 - What Does a ProcGen Generalization Gap Measure? Action Rules, Residual Entropy, and the Missing Random Floor Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32532 - HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03574 - Explainable Suicide Risk Assessment on Social Media with Multi-Task QLoRA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00610 - Unifying Distributional Training for One-Step Visual Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35763 - Autonomous Robotic Navigation for Endovascular Brain-Computer Interface Access Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03537 - ROUTEAUDIT: Interaction-Aware Identification for Budgeted Multi-Verifier Routing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02808 - VTBench: Evaluating Visual Tokenizers for Autoregressive Image Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.13439 - BaCP: Backbone Contrastive Pruning for Preserving Representations in Extremely Sparse Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02524 - Divergence controls entropy in distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03529 - CRISP: A Framework for Clause-Reconstructed Interpretable NeuroSymbolic Propositions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02431 - Neural Data Needs Semantic Tokenization: Behavioral Events as Boundaries of Session-Transferable Tokens Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03001 - Recursive Agent Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06639 - From Benchmarks to Production: A Text-to-SQL System for Complex Financial Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03524 - Causal Representation Learning with Instantaneous and Lagged Relations via Nonstationarity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03452 - HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.17873 - How Causality Bridges the Semantic Gap Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02594 - Predicting Collision Cross Sections with GRACE: Geometric Residual Adduct Conditioning via Early-fusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.12223 - Does Physics Live in the Activations? Localizing Physical Quantities in Video Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03154 - CATCH: A Controllable Analysis Testbed for Reward Hacking in Coding RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39533 - The Price of Greenwashing: Algorithmic Verification and Market Discipline using Conformal Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02225 - Identify then Realize: Contrastive Learning of Latent Port-Hamiltonian Dynamics from Partial Observations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16682 - PowerBench: Measuring Language Model Bias in Power-shifting Requests Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02303 - WakeKV: Reactive, Reversible KV Residency for Heads That Change Their Minds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02713 - SD-DPC: Sparse Dictionary Differentiable Predictive Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02466 - The Fragility of Trigger-Tag Mechanisms for Misuse Detection in Open-Weight LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03124 - Balancing Multimodal Learning via Functional Progress Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03035 - Threat-Preserving Representation Sensitivity in Agent-Security Benchmarks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03585 - Spectral Alignment in Forward-Backward Representations via Temporal Abstraction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.20103 - Why Does Adaptive Batching Help LLM Pretraining? A Perspective from Unbounded Variance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02355 - Clinical Concept Centers in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02829 - Generalizable single-cell perturbation response prediction using energy-guided flow matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02232 - Escaping the Capacity Ceiling: Routing on the Stiefel Manifold for Bilinear SPD Layers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.31043 - Localized Conformal Safety Monitoring with Vision-Language Models for Autonomous Driving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02765 - Bandits via Additive Quantized Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02440 - Decoupling Memory from Context: Structured Memory for Token-Efficient Test-Time Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02687 - Mapping and Advancing the Scalability-Accuracy Frontier of Nonlinear Causal Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03258 - Inherit-MAS: Test-Time Evolution of Multi-Agent Systems through Workflow and Execution Inheritance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02396 - Fixed Universal Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.31423 - What Should World Models Forget? Stratified Retention for Continual Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03713 - Most-Recent Anchoring with Recurrent Ordering for Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03494 - Slow-Fast Multi-Teacher On-Policy Distillation for Capability Preservation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02324 - Light Entropic Optimal Transport on Riemannian Manifolds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03085 - Bellman Error Minimization Via Linear Programming Normalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02730 - Gated Slot Attention-2: Two-Sided Associative Memory Correction in Linear Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02816 - Recoverability Has a Law: The ERR Measure for Tool-Augmented Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.22352 - Probe the Harness: Setup Checks for Stale-Data RL Comparisons in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02911 - Can SGD Handle Heavy-Tailed Noise? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.04860 - Getting Your Guidance Weights Right in diffusion and flow-matching posterior sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03503 - RMCW: A Deletion-Robust Watermark Based on Reed--Muller Codes for Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02817 - Planning to Learn Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03667 - Learning to Price Electricity for Optimal Demand Response Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00755 - Geometric Data Perturbation with Noisy-Anchor Alignment for Privacy-Preserving Collaborative Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18749 - Trade-off Functions for DP-SGD with Subsampling based on Random Allocation: Tight Upper and Lower Bounds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06259 - From Behavior to Provenance: Attributing Tabular Foundation Models to Synthetic Pretraining Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02347 - Electronic Density versus Geometry for Machine-Learned Molecular Absorption Spectra Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03444 - A Polynomial-Time Algorithm for Variational Inequalities under the Minty Condition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.03432 - When May a Bandit Leave Its Anchor? E-Process-Authorized Thompson Sampling under Non-stationarity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03646 - Generalization Properties of Score-matching Diffusion Models for Intrinsically Low-dimensional Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02663 - Latent Goal Prediction from Language for Model-Based Planning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.20627 - Deep Bayesian REFoCUS Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03419 - On-Board Anomaly Detection for Efficient Marine Environmental Monitoring Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03649 - MolWorld: Molecule World Models for Actionable Molecular Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08954 - Beyond Global Divergences: A Local-Mass Perspective on Bayesian Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.27090 - The Surprising Effectiveness of Shared Memory in Looped Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02383 - JOVE: Joint Execution and Verification for Resource-Aware LLM Task Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03296 - Constraint-Aware Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02909 - CoMemNet: A Continual Memory Network with Drift-Aware Sampling for Traffic Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05738 - Hold-Out Scoring for Efficient Gaussian DAG Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02785 - Expected Utility Regret Rule: Minimax and Bayes Optimal Portfolio Choice Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02290 - Fragmentation is Efficiently Learnable by Quantum Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.00751 - SoTa: Soft Tactile Skins for Dexterous Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02338 - From Solo to Social Learning: Characterizing Recursive Social Improvement in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38516 - Coverage You Can Steer: Online Conformal Calibration for RL-Driven Hardware-Aware NAS Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03127 - ORACLE: Agentic AI Orchestrator Routing Via Adaptive Verifier Calibration Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22465 - Escaping Oversquashing: Addressable and Support-Aware Global Memory for Message Passing Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02709 - A Path Integral Surrogate for Multi-Step Gradient Inversion in Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03597 - Stimulus symmetries can confound representational similarity analyses Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21324 - When Does Synthetic Relational Data Teach Models to Use Relations? Tracing Predictive Structure from Pretraining Data to Model Behavior Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03057 - Counterfactual Action Evaluation, Observation Bottlenecks, and Representation Geometry in Joint-Embedding Predictive World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02860 - Single or Multiple Policies for Phase-Structured Reinforcement Learning? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03475 - Scale-Recursive Rectified Flows for Few-Step Precipitation Ensembles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02611 - MaskCoFT: Masked Co-Adaptive Fine-Tuning for Memory-Efficient MoE Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34077 - Goldilocks RL: Tuning Task Difficulty to Escape Sparse Rewards for Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.14868 - Counterfactual Predictions in Scientific Emulators Without Controlled Experiments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02252 - Conditional Capacity and Routing in Mixture-of-Experts Particle Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02701 - Forecasting from Counterfactual Simulator Rollouts: A Sim2Real Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03662 - LiteEMG-FM: An Efficient and Deployable Foundation Model for Robust EMG Sensing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02497 - Using large language models to probe the limits of atom-centered structural descriptors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.26984 - Online Verification of Language Model Responses Under Cost Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02632 - TACTICS: Taxonomy-Aware Intelligent Corpus Sampling for Machine Translation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17956 - Understanding Trajectory Heterogeneity in Federated World Model Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02957 - Peer Effects in Signed Networks: Separating Influence Through Positive and Negative Ties Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02872 - Robust Adversarial Quantification via Conflict-Aware Evidential Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.05937 - 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 - Exploring Subnetwork Interactions in Heterogeneous Brain Network via Prior-Informed Graph Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.19307 - Tangent Schr\"odinger Bridge Matching: Learning Stochastic Transport with Mechanistic Sensitivities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02906 - Bidirectional Voronoi-biased Exploration Curriculum for Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03395 - Broken scale symmetries in undercomplete linear autoencoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03640 - Architecture-Dependent Fusion Pathways in MLLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03289 - A Unified Framework for Bayesian Data Assimilation with Generative Models and Observation Interpolants Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03396 - A Sobel-Gradient MLP Baseline for Handwritten Character Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.11902 - Differential Privacy of Gradient Descent on Perturbed Objectives Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02716 - Nearly Optimal Fixed-Confidence Best-Arm Identification with 1-Bit Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02771 - Uncertainty Quantification for Flow-Based Generalist Robot Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18043 - DAGS: Disentangled Appearance-and-Geometry Steering of a Frozen Image DiT for Temporally Stabilized Generative Rendering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02567 - Closing the Train-Test Gap in World Models for Gradient-Based Planning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.09929 - A hybrid CNN-adjoint optimization framework for reconstruction of viscoelastic tissue properties in magnetic resonance elastography Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02634 - Cephalonauts One: A deep fMRI dataset for decoding naturalistic speech in the human brain Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03558 - Heads, Tails, and AI Fails: LLMs, Randomness, and Human Judgments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.00092 - High-Dimensional Asymptotics and Dataset Selection for Private Transfer Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02578 - Provable Benefits of Regularization: Fast Rates for Adversarial Imitation Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35698 - Timescale Separation Enables Deep Reinforcement Learning Control of Rotating Detonation Engine Mode Transitions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.14398 - Sample complexity of variance-reduced policy gradient: weaker assumptions and lower bounds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03165 - Beyond Trained Models: Compiling GNNs for a Sound Explainer Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03526 - An Irreducible Quantum Advantage in Aligning World Models with Reality Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19779 - Fine-Tuning Generative Models for Extreme Events via CVaR-Penalized Wasserstein Gradient Flows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11544 - Exploring the Trade-Off Between Structured Pruning and Fault Tolerance in Deep Neural Networks for Space Applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03117 - JARQ: Joint Alternating Refinement for Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38599 - How Far Does a Shared Linear Map Go? Probing Feature-Space Manipulability for Image Editing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11203 - Geometry-Aware Time Reparameterization for Flow-Map Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02427 - Joint Movement and Compression Ratio Design for Mobile Embodied AI Networks (MEAN) Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02334 - FSPO: Policy-Consistent Risk and Pareto-Feasible Control for Budgeted LLM RL Post-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02828 - System-Prompt Anchoring with Cross-Attention Layers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09737 - Learn Feasibility Once, Optimize All Objectives: Derivative-Free Diffusion Models for Chance-Constrained Programming Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03071 - S$^{2}$-PINN: Stochastic Separable Physics-Informed Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03303 - RAOA: Alternating-Operator Neural Computation with Programmable Radio Propagation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02683 - Explainable Molecular Structure Inference from GC--MS with Diffusion Models and LLM Reranking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03066 - Intent-Hiding Jailbreaks: An Information-Theoretic Framework for Compositional Attacks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02302 - LEAF: A Living Benchmark for Event-Augmented Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16358 - Evolving Hybrid Quantum-Classical Architectures for Image Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03220 - Do as the Romans Do: Learning Universal Behaviors from Heterogeneous Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18537 - The Neuro-Physical Inverter: A Modular Framework for Magnetotelluric Inversion Coupling Ensemble Conditioning with Residual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03225 - Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality Gaps Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02740 - Permutation Robustness Is Not Enough: Action Collapse in Multi-Agent Transformer Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02848 - Overcoming Challenges of Interpretive Structural Modeling with Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02254 - Post-Training Quantization of Autoregressive Weather Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02511 - DeskForge: Dense Supervision from Desktop Environments for Computer-Use Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02320 - Multimodal Ambivalence/Hesitancy Recognition in Videos for Personalized Digital Health Interventions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.11730 - A Composable AI-Accelerated Iterative Solver for 3D-IC Thermal Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02461 - ULTRADISCOVERY: Abductive Exploration in an Interconnected, Epistemically Open Universe Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03092 - Platonic Task Arithmetic Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00929 - OpenGameEval: Benchmarking Agentic Programming and Exploration in a Stateful Game Engine Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02563 - Can AI Understand the Language of Origami? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.13856 - Predictor-Guided Latent Space Codon Optimization for Maximizing Protein Expression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03098 - Rhetorical Questions in LLM Representations: A Linear Probing Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.14128 - Dynamic Expert Pruning for Multi-Agent Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02951 - Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20744 - Teaching LLMs to See Graphs: Unifying Text and Structural Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10247 - Discriminating Fixture Coverage in Agent-Infrastructure Verification Suites Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02928 - RINS: Residual-Image Neural Subspace Solvers for Large Sparse Linear Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02217 - Safe Streaming Flow Planning by Aligning Sampling Dynamics with Execution Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03132 - Adaptive Spectral-Koopman Dynamics Modeling for Temporal Domain Generalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02822 - Dense Mixture-of-Experts as a Reparameterized Wide FFN: A Granularity Sweep at Fixed Compute Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02584 - Characterizing the Performance Gap in Human Activity Recognition for Older Adults Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02711 - Diffusion-Based Synthetic Data Pretraining for Enhancing Activity Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02292 - Dual-Context Analog Retrieval for Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03491 - LatticeSMC: Where to Spend Inference-Time Compute in Chunked Sequence Generators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02774 - Temporal Geometry of Deep Networks: Hyperbolic Representations of Training Dynamics for Intrinsic Explainability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03000 - Instance-Dependent Regret for CMDPs with Step-Wise Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02520 - Cordial Learning: Distributed Training with Correlated Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03330 - Hyperparameter selection for equation learning with biologically-informed neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02954 - AECSF: Adaptive Ensemble Conditional Score Filtering for High-Dimensional Nonlinear Data Assimilation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32411 - How to Have a Sensitive Debate: An Instance-Optimal Protocol for AI Debate Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02557 - Contrastive Neural Embeddings Reveal Individual Traits Beyond Conversational Role Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03410 - TRACE: A Reproducible Benchmark for Electricity Price Forecasting with Official Operational Text Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02256 - No-Free-Graph: Learning When Multimodal Data Should Be Graphified Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02768 - RIPPLE in Still Water: Zero-Shot Clustering in Federated Learning with Wavelet Scattering Transform Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03054 - CLEAN: Psychometrically Consistent Incremental Cognitive Diagnosis under Concept-Space Expansion via Architectural Isolation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02278 - PaMIR: Open Benchmark of Public Credit-Default Datasets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03259 - Harnessing LLMs as Agents: What Does It Cost? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02488 - IDRF: Inverse-Distilled Reward Fine-tuning of Masked Discrete Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03641 - Multimodal Representation Learning Conditioned on Semantic Relations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.17497 - Tailoring the Quantization Space for 1-Bit KV Cache Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03027 - RNADyn: A Benchmark for Generating and Understanding RNA Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03712 - IGNITE Tokamak World Model Architecture Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02515 - ChronoSpike: An Adaptive Spiking Graph Neural Network for Dynamic Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01124 - DAWIS: Data Assimilation with Windowed Inverse Sampling via Multitask Interpolants Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03314 - LS-AR: Future-Predictive Latent Steering in Autoregressive LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03093 - GTDD: Generative Test-Driven Development for AI Coding Agents with Adversarial Testing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02952 - Classical and Quantum Speedups for Non-Convex Optimization via Energy Conserving Descent Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.13022 - Scalar Federated Learning for Linear Quadratic Regulator Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.05088 - Frequency Is Not Sensitivity Identifying Safety-Sensitive Experts in Sparse MoE LLM Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02910 - TrueMuse: A Benchmark for Data Attribution in Text-to-Music Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00835 - Muon Learns Facts Better: Understanding the Role of Spectral Orthogonalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02798 - When Can We Trust the Matching Principle? Robust Deployment Geometry Under Finite-Sample and Model Uncertainty Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02894 - Uncovering EEG Patterns Consistently Associated with Cybersickness Discomfort Using Deep Learning Interpretability Maps Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.20620 - Evaluating and Improving the Robustness of Large Language Models to Input Sequence Variations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02432 - TomoTransformer: Towards a Foundation Model for CT Reconstruction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37605 - ReForge: Refining Merged Models with Anchor-Regularized Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12843 - Estimating prevalence with precision and accuracy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.06061 - Conformal Prediction for Time Series with Deep Sequence Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02357 - Learning Jazz Pianist Style with Cross-Attention Conditioning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02918 - Efficient Support Recovery of Mixtures of Sparse Linear Classifiers with Fewer Measurements Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32176 - High-Dimensional Asymptotics of Differentially Private PCA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.07270 - VIGOR: Zero-Shot Visual Generalization via Latent-Space Consistency in Model-Based Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02801 - Are you Synthesizing or Recalling? Evaluating LLMs on Algorithmic Code Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02438 - Continual Reinforcement Learning with Neuroevolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01583 - Landscape-Dependent Performance of Photonic Quantum Solvers in QUBO Feature Selection for Financial Risk Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03161 - Range-GRPO: Policy Optimization via Pairwise Relations among Reward Intervals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01548 - Jumping up and down: Denoiser diffusion models for discrete ordinal data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02754 - Efficient Memory Crystallization for Graph Learning under Non-Stationary Distribution Shifts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02795 - LEAP: Learning Efficient Action Proposals For LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02670 - Activation Sparsity with Weight Approximation for Faster LLM Decoding on Offloaded Weights Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02598 - Theoretical Lower Bounds on the Robustness of Deep ReLU Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.18674 - Approximation Property of Dropout Neural Networks: Sobolev Rates and Confidence Bounds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02253 - ParaGeo: Decomposing Paralinguistic Variation into a Shared Latent Geometry Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03125 - Learning the structure of open quantum systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.30358 - AvoKV-E: Payload-Aware KV Cache Eviction for Long Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03007 - Context-Tower Conversion Preserves Generation While Freezing Retains Knowledge: Low-Budget AR-to-Diffusion Conversion of MoE LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02657 - A Controlled Audit of Personal AI Memory for Rating Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02764 - PoCoFL: POlicy-COmpliant Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03650 - Learning the Latent Structure: A Feature-Centric Approach to Graph Data Augmentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02517 - Rank-Aware Speculative Sampling for Diffusion Draft Trees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02251 - Demystifying LLM-as-a-Judge: Analytically Tractable Model for Inference-Time Scaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.19905 - Asymptotic Performance of Time-Varying Bayesian Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.13012 - Quantum parameter estimation with uncertainty quantification from continuous measurement data using neural network ensembles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.10756 - Noise Sensitivity and Learning Lower Bounds for Hierarchical Functions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.05073 - NegT2IBench: When Negation Changes the Picture. A Polarity Benchmark for Text-to-Image Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03084 - Dirac-Interconnected Neural Elements: Discovering Modularity in Physical Systems Without Reduction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02960 - Training-Loss Guarantees for Muon with Finite-Step Newton--Schulz Orthogonalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03306 - Wrong Organ, Right Physics: Transferring Echocardiography Pretraining to Lung Ultrasound for Tuberculosis Screening Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03290 - GenoTrace: Inheritable Watermarks for Genome Foundation Model Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35881 - When Does Pooling Pay? Credibility and Resolution under Forgetting in Intermittent-Demand Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.12749 - How to Find and Reuse Policies for Continuous Adaptation in Lifelong Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03119 - Near-Optimal Convex Optimization with Lazy Second-Order Oracles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03222 - Flow Map Denoisers: Traversing the Distortion-Perception Plane for Inverse Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.19802 - FASTDIAR: Frame-level speaker encoder for Streaming Diarization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02941 - FastOPD: On-Policy Distillation for Lightweight VLA Deployment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02832 - Bayesian Optimization with Rich Auxiliary Information via LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19437 - Verifiable, Articulable, and Tacit Components of Preference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03025 - Repurposing Pre-trained LLMs as High Fidelity Continuous Text Autoencoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27248 - Mind the Refinement Gap: When Safe High-Level Robot Plans Produce Unsafe Executions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02662 - Where Quantum Fourier Sampling Stops Short: A Three-Gate Audit Protocol for Delay-PUF Security Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02636 - DeReAct: Decomposed Reasoning and Acting for Reliable AI Agents Source: arxiv-cs-lg Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.02351 - Dissecting model behavior through agent trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17454 - ENCORE: Exact Non-equilibrium COntrol with Replica Exchange for Diffusion Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02538 - Token Space: A Category Theory Framework for AI Computations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2404.11624 - Nearest-neighbour baselines for fingerprint prediction from MS/MS spectra under different assumptions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02249 - AI-driven Thermal-aware Data Center Capacity Planning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02442 - Fast Models, Slow Evidence: A Paired and Self-Audited Evaluation of System-1 Decision Models for LLM Agent Harnesses Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02267 - Reliable mechanistic operator recovery with biologically-informed neural networks: principles for architecture and optimisation design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.07425 - On Unlearning for Time-series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02865 - NEEDLEWORK: Offline Rewriting of Robot Data with Verified Local Stitches Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02339 - OPD Before RL: Warm-Starting Rubric-Based RL with On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02781 - Exact Memory-Time Optimization for Prefix-Cached Language Model Serving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02766 - Low-Frequency Shortcuts in Texture-Driven Visual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03493 - Validated Data Onboarding for AI Demand Forecasting on U.S. Building Meter Data: Design, Controlled Evaluation, and a Corrected Negative Result Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02397 - An Automated and Reproducible Workflow for Crack Identification and Damage Assessment of Fusion Materials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03505 - OptiSelect: How does the Optimizer Shape Data Curriculum? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03432 - Below what training size do deep tabular generators stop beating trivial baselines? A preregistered benchmark on a size ladder of clinical and standard datasets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03500 - Continuous Policy and Value Iteration for Relaxed Stochastic Control Problems and Its Convergence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.08121 - Normal-Form Correlation in Markov Games Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03621 - MuLoRA: Spectrally Balanced Low-Rank Adaptation for Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02283 - The Conflict Between Logic and Memory: Training Conditions for Optimizer-Dependent Rule Acquisition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00403 - Operator Calculus for Population-Based Optimization: Modular Convergence and Finite-Population Guarantees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.14289 - Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03665 - Learning from the Gap Between Pass@K and Pass@1 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35793 - Right Order, Wrong Scale: Auditing LLM Judges for Occupational AI Measurement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02492 - Flow Matching for Fast Posterior Sampling in Bayesian Inverse Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02377 - Everywhere Learning: Artificial Intelligence with Pointwise Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01557 - Steering Recurrent Reasoners at Inference Time with Readout Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24136 - Sentence-Level Context Sensitivity as a Training-Free Detector of Unsupported Content, Evaluated Against Trained Verifiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04223 - D2K-Bench: Can LLM Agents Turn Expert Designs into Efficient GPU Kernels? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03226 - Exact Risk Ratios for Weighted Data Selection in Linear Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.28007 - AREX: Affine-Residual Exponential Integrator for Few-Step Sampling in Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03483 - Weights Read and Write Features: Scalable Parameter Decomposition Grounded in Activation Space Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37731 - MASCIT: A Mask-Aware State Space Classifier for Naturally Irregular Time Series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34409 - Turnover-Orthogonal Credit Assignment for Open-Team Multi-Agent Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02847 - MuonIO: Principled Norm-Aware Descent for Embedding Tables and Language Model Heads Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02705 - Fractal dimension predicts quantum kernel collapse in angle-encoded data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00475 - Hesitation Has a Geometry: Entropy-Trained Hyperbolic Probes for Sparse Activation Steering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02391 - Compound AI System Reliability: A Failure Taxonomy and Resilience Pattern Catalog from 150 Production Incidents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02503 - Learning an Interpretable Risk Scoring System for Maximizing Decision Net Benefit Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.04241 - Gradient Descent's Last Iterate is Often (slightly) Suboptimal Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.13870 - Llama-Mobile: Efficient 2.7-Bit Quantization of VLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21134 - Page-EntroKV: Hardware-Aligned, Entropy-Weighted KV-Cache Eviction under Grouped-Query Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03135 - Efficient Exploration for Iterative Nash Preference Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01382 - ZeroMAG: Zero-Shot Multimodal Adapter Generation for Plug-and-Play EEG Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03546 - Evaluation of Sampling Strategies and Physics-Informed Kolmogorov--Arnold Networks in Unbounded Domains Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.12074 - Dual Certified White-Box Inference for Input Convex Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.04722 - Structural-Functional Brain Connectivity Generation via Multimodal Hypergraph-based Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02722 - Hamiltonian locality testing and certification do not achieve the Heisenberg limit Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03205 - DriftWorld: Fast World Modeling through Drifting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.15065 - GPart: End-to-End Isometric Fine-Tuning via Global Parameter Partitioning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.14841 - A Missing Latent, Not a Missing Simulator: Radius-Augmented Inference for Real JWST Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02245 - When Is Accuracy Evidence? A Unified Theory of Generalisation, Validation, and Information Fusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03465 - VIDiff: Translating Videos via Multi-Modal Instructions with Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2311.18837 - A Pre-Training Analogue of Grokking in Language Models: Tracing Delayed Grammatical Generalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00230 - Certified Mechanistic Edits: Behavioral Guarantees for Skill Removal and Preservation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03502 - On the Tip of the Tongue: Why LLMs Hallucinate Answers They Can Decode Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.13911 - AdaStep: Adaptive Step Credit Weighting for Agentic Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03223 - Safe and Robust Neural Policy Learning with Statistical Verification for Sim-to-Real Deployment in Robotics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06481 - Distributionally Robust Survival Models under Subpopulation Shift and Outlier Contamination Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02868 - Learning to Rank Tensor Network Contraction Plans for GPU-Accelerated Quantum Circuit Simulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.05819 - Quantifying the Value of Constructive Induction, Knowledge, and Noise Filtering on Inductive Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02615 - The AI Theorist reveals excitonic structure in $\alpha$-RuCl$_3$ Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02417 - What Is Lost in Post-Training? Default Collapse and the Loss of In-Context Steerability Across Diverse Perspectives Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02614 - Budgeted Cache Repair for Cross-Context KV-Cache Reuse Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02233 - Operator-informed initialization for Fourier features physics-informed neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03378 - Seer: Maximum Likelihood Regression for Learning-Speed Curves Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02610 - MACTS-EM: Multi-Agent Collaborative Time Series Forecasting with Emergent Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02255 - ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.09009 - Co-design Gym: A Unified Benchmark for Embodiment-Policy Co-optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02366 - Min-Cost Flow Routing for Evidence Assembly in Long Multimodal Documents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07235 - EEGDM: Learning EEG Representation with Latent Diffusion Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.20705 - A Generative Model of Complex Networks Using Graphons and Neural Inverse Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02439 - 16-bit Precision of Convolutional Neural Networks on Microcontroller Units for 8-bit Costs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03402 - FALCON: A Model and Dataset Agnostic Framework for Synthetic Data Generation for NL2SQL Pairs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03625 - Teger: Spatiotemporal Covariance for Probabilistic Traffic Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18068 - DIVINE: Simple Cross-Market Stock Pretraining via Diverse Indicator Reconstruction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02866 - Towards Identifying the Dataset Biases Causing Phantom Transfer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14449 - Threshold-Aware Conformal Routing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02487 - Learning PDE Dynamics between Submanifolds Using Green's Observation Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01697 - Amortized Structured Stochastic Variational Inference for Gaussian Process Latent Variable Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03647 - Learning Transferable Policies from Action-free Time Series Through Dynamical Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03065 - Adaptive Second-Order Solvers for Fast Stochastic Diffusion Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03034 - Parameter-Free Interval-Dynamic Regret under Heavy-Tailed Noise Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02258 - Capability Scaling-Down Laws for LLM Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02462 - Learning Style, Forgetting Semantics: A Case Study of SFT and RFT on Classification Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02437 - SlimKV: Joint Token-Feature KV Cache Compression with Reconstruction-Free Beacon Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02953 - Performance Evaluation of Ising and QUBO Variable Encodings in Boltzmann Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.13210 - Predictively Oriented Gaussian Process Posteriors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03201 - Latent-MOPD: Latent Multi-Teacher On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02381 - Diffusion Flow Matching: Dimension-Improved KL Bounds and Wasserstein Guarantees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16610 - Does Every User Need a Private LoRA? Decoupling Personalization from Per-User Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02353 - Coupled reaction and diffusion governing interface evolution in solid-state batteries Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.10944 - Test-time Multi-agent Coordination by Decomposed Value Gradient Flow Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02554 - Why Backdooring Neural Networks is so Easy? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.36117 - Rethinking Epistemic Uncertainty in Node Classification through Information Growth Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03418 - SyntaxBench: A Statistical Diagnostic Framework for Character-Level Reasoning in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03329 - CipherGenome: Homomorphic Inference for Genomic Mixture-of-Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35883 - Signal Simplification Is Not Predictive Simplification: Diagnosing Residual Neural Forecasting in Short-Horizon Volatility Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03019 - Infinity Search: Approximate Vector Search with Projections on q-Metric Spaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.06557 - State-Space Unlearning for Non-Stationary Bias in Land Surface Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02248 - SCAD: Structured Credit Assignment and Distillation for Long-Horizon Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03372 - Drive vs. Decay: On the Training Dynamics of Joint-Embedding Predictive Architectures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02344 - Suan: Rectifying Direct Preference Safety Alignment in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08634 - Not Until the Evidence Says So: Teaching LLM Investigators When to Close a Case Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03190 - Large Language Continuous Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02665 - Effects of interpulse-interval variation on deep-learning classification of bat vocalizations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02284 - A Two-Stage Cascade for Near-Real-Time Forest Anomaly Detection from Sentinel-1 SAR Time Series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02763 - Morality is Contextual: Learning Interpretable Moral Contexts from Human Data with Probabilistic Clustering and Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.21439 - Test-time Calibration Learning for Large Language Model Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02695 - Hardware-Native Joint Sparse-Quantization for Trillion-Scale Mixture-of-Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02241 - TSGuard: A Real-Time Framework for Detecting and Imputing Missing Data in Streaming Time Series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03147 - Open Vocabulary Word Recognition From Transcribed Bangla Texts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01134 - Mixture-of-Experts for Cryptocurrency Order Execution: Training Stability, Tail Risk, and Failure Modes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03369 - From Patching to Pruning Visual Computation in Vision Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03389 - All Work And No Play Makes Jack a Dull Boy: Understanding and Preventing Catastrophic Strategy Collapse in RLVR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02835 - Iterating Consistency Models: Stability, Error Bounds and Noise Schedules Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03414 - Metropolis-Hastings Dominates Importance Resampling for Policy Composition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03480 - Interpretable Discovery from Unstructured Data: A High-Dimensional Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.01680 - From Mixing to Tearing: Graph Decomposition in Decentralized Optimization via Message Passing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03709 - Learning Query Encoders Can Be Hard Even When Vector Retrieval Is Geometrically Easy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02749 - Confidence-Gated Cloud-Edge Cascade Triage via Variational Risk Minimization for Medical Imaging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02269 - HyperThink: Text-to-Parameter Hypernetworks for Efficient Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03039 - Autoregressive latent diffusion for 3D molecule generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.09277 - Accelerated Algorithm for Sparse Regularized Partial Optimal Transport Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.40075 - PerturbCellRL: Aligning Distributions and Grounding Biology via Post-Training Perturbation Generators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.27752 - To Explore The Strange New World Beyond Data Distribution: System Behavior, Causality Tax, and Non-causal Base Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02839 - Generalization of Transformer-Based Neural Quantum States via In-Context Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03463 - Energy Saving in 5G and Beyond Networks: A Quantum Reinforcement Learning Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02403 - AIBL: Augmented Instance-Based Learning with Structured Memory and Neural Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03413 - Useful Features, Backward Scores: OOD in Language-Model Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.00269 - Revisiting Visual Representation Enhancement of VLMs via Kernel Canonical Correlation Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02718 - ROVE: Unlocking Human Interventions for Humanoid Manipulation via Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17011 - MiDShip: Multimodal Dataset of Ship Cargo Hold Structures for Engineering Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02214 - Simulation-Free Learning of Population Dynamics with Wasserstein Lagrangian Residuals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03679 - MintEval: Do LLMs Implement the Trading Strategy You Asked For? A Behavioural-Equivalence Benchmark for Natural-Language-to-Strategy Code Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03080 - SDECast: Probabilistic Weather Forecasting in Continuous Time with Neural SDEs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03313 - Controlling Polar Exposure to Delay Memorization in Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02780 - Predicting and Repairing Merge Collapse in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03199 - SPEAR: A Spectral-Disentangled MoE Neural Operator with Knowledge-Guided Expert Aggregation for Large-Scale PDE Pretraining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03265 - Reliability of Probabilistic Emulation of Physical Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.12997 - NeuroLens: Learning Latent Embeddings of Neural Semantics from Chronic Recordings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02864 - AIGS: Adaptive Incremental Gating System for Online Representation Learning in Non-Stationary Data Streams Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02661 - ASH: Agents that Self-Hone in Long-Horizon Worlds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.14211 - Hybrid Machine Learning-Assisted Raman Spectroscopy with Generative Feature Augmentation for Pharmaceutical Identification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02224 - Lexicographic Multi-Objective On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02359 - Autoregressive Differentiable Method for Integer Programming Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02528 - On the Convergence of Success Conditioning for Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03642 - Understanding Enrichment in Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02846 - GenomeOcean Anywhere: Private WebGPU Inference for Genome MoEs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35882 - When Normalization Selects the Sign: Auditing Robustness Ablations in Quantum Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02641 - Prompted to Discriminate: Generalizing Malicious-Input Probes in the Wild Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02413 - Decision-Aware Training for Sample-Based Generative Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.01171 - From Mathematical to Executable Certificates for Machine Unlearning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02268 - Reward Inflation: A Healthy Stimulus for Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02545 - Zephon: Elastic Determinism for Online, Stateful Foundation Model Data Loading Pipelines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03087 - CriticHack: Evaluating Visual Rewards Under Robot Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02527 - Embodied Neurocomputation: A Framework for Interfacing Biological Neural Cultures with Scaled Task-Driven Validation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13315 - Differentiable Koopman Operator for Contrastive Learning on Dynamic Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02990 - Verify Before You Fix: Agentic Execution Grounding for Trustworthy Cross-Language Code Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.10800 - Follow the Winners: Conservative Policy Improvement with the Cross-Entropy Method for Critic-Free RFT Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03361 - Neuron merging via inverse-activation regression for post-training compression of sigmoid neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02559 - GB-LSR: Local Spectral Decoding with a Learned Global Bandwidth for Arbitrary-Scale Super-Resolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.19617 - S2S-JEPA: Predicting the Predictable at Subseasonal-to-Seasonal Timescales Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03106 - Error Propagation in Dynamic Programming: From Stochastic Control to American Option Pricing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.20239 - SCOPE: Observation-Conditioned Full-Target Prediction for Sparse PDE Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.36527 - Adapter Thickets: Splitting an RLVR Budget Beats Concentrating It Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00991 - Bifidelity Karhunen-Lo\`eve Expansion Surrogate with Active Learning for Random Fields Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.03756 - ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.06565 - Beyond Random Splits: Evaluating Drug-Target Affinity Models Under Chemically and Biologically Motivated Distribution Shifts Copy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03456 - Power-SMC: Low-Latency Sequence-Level Power Sampling for Training-Free LLM Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.10273 - Deep learning-based prediction of time-resolved adhesive forces in viscoelastic Hertzian contacts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.19060 - $\Psi$-Resilience: Model-Free Feature Importance from 1D Topological Signals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02299 - MRVQ: One Resident Index for Dimension- and Rate-Elastic Vector Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.03651 - Learning to Route in Visual Space via Multi-Step Embedding Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.38743 - When History Misleads: Asymmetric Margin Supervision for Instruction-Guided LLM Generative Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.02600 - More Efficient LLM Reranking with Whole-Pool, Setwise, Long-Context Language Models Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2606.01782 - Benchmarking Literature Retrieval for a Model Organism: A Dictyostelium Case Study Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.03130 - Asterism: Exploring and Synthesizing Scattered Observations into Literature-Grounded Hypotheses and Theories Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.02673 - Query-aware routing for Cross-lingual performance gains in Encoders Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.02875 - Adaptive Sparsity Optimization with Learnable Soft Top-K and Per-Term Thresholding for Efficient Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.02572 - On-Premises Multi-Course RAG Tutoring for Business Education: Hardware-Software Trade-offs in a Campus AI Tutor Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research, FastAPI, Python) URL: https://arxiv.org/abs/2610.02510 - Note-Level Temporal Grounding of Musical Concepts in Large Audio-Language Models Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.29480 - Auditing Long-Term Memory Evaluation: Repeated Judging, Reader Variation, and Negative Controls Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.38021 - A Manifold-Aware Topic Modeling Approach via Rank-Based Prototypes Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29630 - SOLO: Certified-Recall Metric Similarity Search with Scan-Only Sampled Inverted Lists Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.02387 - Simple analysis of an algorithm for multiple-source shortest paths in planar graphs Source: arxiv-cs-ds Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2610.02371 - GISTBench: Evaluating LLM User Understanding via Evidence-Based Interest Verification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.29112 - AptMQL-Bench: From Text-to-SQL to Text-to-MQL via Access-Pattern Schema Design and Data-Preserving Migration Source: arxiv-cs-cl Topic: AI Research (+AI, MongoDB) URL: https://arxiv.org/abs/2610.02770 - Structured Composition of Verifiable Atomic Insights for Table-to-Report Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03525 - BioMol-MQA: A Multi-Modal Question Answering Dataset For LLM Reasoning Over Bio-Molecular Interactions Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2506.05766 - StanceEval 2026: The Second Stance Detection Shared Task Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03215 - Sensory-Aware Sequential Recommendation via Review-Distilled Representations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.02709 - Ask, Relax, or Act? Evaluating Actionable Indeterminacy in LLM Preference Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03102 - Learning from Repaired Reasoning: Root-Cause-Guided On-Policy Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03515 - You Only Align Once: Propagating Cooperative Behaviors in Multi-Agent Systems through Seed Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.27586 - RT-SFT: Text Style Transfer from Non-Parallel Corpora by Roundtrip Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.15013 - A Near-Zero Monitor Readout Is Not Evidence of Behavioral Control Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03458 - Authorship Verification of Transcribed German-Language Videos Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.29168 - HyperLogic: A Hard, Forward-Authored Chinese Logical Reasoning Benchmark with Execution-Derived Answers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19597 - Text-Centric Post-Training for Omni-Modal Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02819 - trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00038 - ConvoDrift: A Multi-Turn Conversational Dataset for Modeling Stylistic Tone Evolution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02873 - TomasuLLM: Out-of-Order Speculative Execution for LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38201 - Large language models exhibit unreliable updating of clinical judgment as patient evidence evolves Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02684 - Rank-Turbulence Delta and Interpretable Approaches to Stylometric Delta Metrics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.19499 - Where Do Apparent LLM Clinical Triage Failures Arise? Localizing the Multiple-Choice Format Effect Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29889 - A Multi-Timescale Recursive Self-Improvement Engine for Open-Ended Persona Growth Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.08252 - Silent Dissent: LLM Agents That Yield to the Majority Still Represent Their Original Premise Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02702 - KV$^2$: A Self-Refining KV Cache Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03198 - Coding Agents with Harness for Safe Robot Control Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20822 - Single-Pass Uncertainty Heads for Claim-Level Hallucination Detection in Persian Medical Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03482 - Emergent Structure in the Marginal Attention Space of Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03109 - Output Language Confusion under Multilingual Prompt Contamination Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02926 - How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.22750 - Writerslogic at the CLEF 2026 SimpleText Track: Multi-Candidate LLM Simplification and Stacked Complexity Spotting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03567 - Recursive Self-Improvement in Unified Multimodal Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03002 - Misinformation Without Triggers: From Factual Answers to Downstream Decisions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02886 - Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03195 - Last Layer Logits to Logic: Empowering LLMs with Logic-Consistent Structured Knowledge Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.07910 - Will the User Ever Know? Covert Indirect Prompt Injection Attacks on Tool-Using LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2608.30362 - SiDiaC-v.2.0: Sinhala Diachronic Corpus Version 2.0 Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.10861 - Social bot detection in the age of ChatGPT: Challenges and opportunities Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02386 - Writerslogic at PAN 2026: Process over Content for Robust Detection under Domain Shift Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03565 - Gaokerena: A Small Persian Medical Language Model Family Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00932 - Audio-Visual Turn-taking Prediction in Cocktail Party Scenarios Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17056 - Automatic register identification for the open web using multilingual deep learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.19892 - Improving Atomic-Fact Recall via Focused Views in Unstructured Knowledge Editing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02772 - MGhana-ST: A Low-Resource Speech Translation Dataset for Ghanaian Languages and an Analysis of Multilingual Training Trade-offs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.40041 - Finding the Move Is Not Winning the Game: XiangqiBench for Closed-Loop Evaluation of LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02425 - Evaluating VQA in Vision Language Models using Cooperative Principles Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02878 - Continual Graph Memory for Mathematical Research Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02945 - Evaluating LLM-as-a-Judge Beyond Score Alignment: A Psychometric Analysis of Residual Judging Difficulty Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02877 - World Embedding Benchmark Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03632 - AstroAgentBench: Evaluating Agentic Planning on Space Mission Planning Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.11354 - LLMersion: A Local-First AI Agent Framework for Low-Cost Home Language Learning toward Educational Equity Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29672 - GAW-PO: Preference Optimization with Gradient-Aligned Token Weights Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01511 - LLM Anonymization Against Agentic Re-Identification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30848 - Many Preferences, Few Policies: Compact Portfolios for Multi-Objective LLM Alignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.04144 - Enrich-on-Graph: Query-Graph Alignment for Complex Reasoning with LLM Enriching Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.20810 - Predicting Steering Vectors and Adapter Weights for Few-Shot Author-Style Transfer Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03163 - Adaptive Mutual Distillation for Balanced Multi-Task Post-Training of Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02856 - Can We Trust LLMs on Memristors? Diving into Reasoning Ability under Non-Ideality Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.13725 - Who Guards the Benchmarks? Automated Auditing of LLM Agent Benchmarks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.24955 - Morpheus: A Morphology-Aware Neural Tokenizer and Word Embedder for Turkish Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18717 - Evaluating the Retrieval Robustness of Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.21870 - TPBench: A Turning-Point Benchmark for Dialogue Compression Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02736 - Investigating the Role of Reasoning-Language Alignment in Monolingual Retrieval-Augmented Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03136 - Specializing Without Forgetting: Analyzing Knowledge Preservation in Multilingual Model Adaptation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00284 - Cross-Lingual Alignment for Decoder-Only Models using MoE Routers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01921 - HARPO: Hallucination-Aware Reinforcement Learning for Faithful and Creative Language Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03063 - Personalized Automatic Speech Recognition for a Dysarthric and Tracheostomic Speaker using Artificial Conversations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03017 - From Positionwise Confidence to Prefix Scheduling: Verifier Skipping in Speculative Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14787 - WAON: A Large-Scale Japanese Image-Text Dataset for Cultural Adaptation in Contrastive Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.22276 - Hindsight-Guided Rationale Distillation for Rare Disease Diagnosis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03176 - Benchmarking Candidate Coverage in Typed Decision Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03387 - An automated pipeline for standardised speech-unit annotation in spontaneous dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03078 - OverdoseMoE: A Multi-Expert Framework for Opioid Overdose Risk Prediction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.40108 - OmniConfess: Eliciting Token Confessions to Mitigate Omni-Modal Hallucination Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02999 - Unmasking Propaganda: A Comparative Analysis of Masked and Causal Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03077 - ETHER: Aligning Emergent Communication for Hindsight Experience Replay Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2307.15494 - Counterfactual Evidence Audits Predict LLM-Agent Susceptibility to Ranked Context Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00914 - A Unified BERT-CNN-BiLSTM Framework for Simultaneous Headline Classification and Sentiment Analysis of Bangla News Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.18618 - FinDialogLens: Event Extraction over Multi-Party Dialogue for Missed-Trade Identification in Financial Chatrooms Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02455 - SEDIMA: Cross-Run Hierarchical Insight Memory for Evolutionary Search Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02361 - Language Models that Play Chess and Explain Their Moves Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03695 - CLIMB: Confidence-Guided Complementary Evidence for Multimodal Retrieval-Augmented Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03421 - The Geometry of Knowledge Accessibility in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03052 - A Guideline-Augmented Multi-Agent Framework for Schema-as-Code Biomedical Named Entity Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02970 - Talked Out of the Truth: Sycophancy in the Reasoning Chains of Multimodal Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.28623 - Passing the Test You Trained On: Re-evaluating Prompt-Injection Detectors for LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03448 - Understanding Clinical Cognitive Dialogues Using Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34125 - Multilingual GSM-Symbolic: What determines capability transfer across languages? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03367 - APDMem: Agent-Controlled Progressive Disclosure for Query-Adaptive Long-Term Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02472 - Is a Picture Worth a Thousand Words? Adaptive Multimodal Fact-Checking with Visual Evidence Necessity Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.04692 - SecJev: Bringing Security Expertise to System One Decision Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03073 - Author Representation Strategies for Zero-Shot Authorship Attribution: A Comparative Study of LLM-Based and Embedding-Based Approaches Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03531 - Automatic Evaluation of Mental Health Stigma in Online Communication Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02775 - Understanding Why Language Models Hallucinate: Testing Reasoning Against Priors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.00447 - Counterexample Generation via Per-Theorem Symbolic Verifiers: When Imitation Hurts and Reinforcement Repairs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02444 - A generative-informed neuro-symbolic framework for syntactic ambiguity resolution: Evidence from Arabic DPs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02529 - To Jev or Not? Evaluating the Accuracy and Efficiency of Structured Decision Models for Hate-Speech Moderation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03324 - Ontological Instability and Statistical Amplification: The Paradox of "Humanizing" LLM-Generated Text Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03110 - From Retrieval to Typed Decisions: Calibrated System One Models from Biomedical Sentence Encoders Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02486 - Hint-Guided Diversified Policy Optimization for LLM Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03021 - Gains and Collapse in On-Policy Distillation:A Reinforcement Learning Perspective Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03185 - Last But Not Least: Boundary Attention CalibratiON for Multimodal KV Cache Compression Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.14782 - Peer Influence across Heterogeneous AI Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03095 - Building Interpretable Feature Representations for Resume-Vacancy Matching by Distilling Production LLM Signals Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03112 - How Robust Is Multimodal Claim Verification to LLM Rewriting? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02841 - Shrome at Touch\'e: Soft-Vote Ensembling and Counter-Causal Augmentation for Causality Extraction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03268 - Encoded but Not Routed: Explaining the Table-Chart Gap in Scientific Claim Verification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01679 - Learning When to Commit from Partial Speech for End-to-End Simultaneous Speech Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02612 - EpiWorld: Grounding LLM Policy Agents in Epidemiological World Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02744 - Enhancing Biomedical Named Entity Recognition via Multiple Programming Languages Instruction Tuning and Ensemble Method Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02949 - Code2Math: Can Your Code Agent Evolve Math Problems Through Exploration? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.03202 - HakemBench: A Turkish Benchmark of Typed Decisions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02293 - Beyond Correctness: Resolving Underspecification in Agentic Text-to-SQL Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02739 - When History Fails to Become Experience: Action Calibration in Language Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02769 - ReSCUE: Re-translation with Sentence Commitment for Unsegmented Long-Form Simultaneous Sign Language Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03022 - CoLMbo-SV: A Grounded Language Model for Explainable Speaker Verification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33212 - How Far Can You Get Without a GPU? A Systematic Benchmark of Lightweight Hallucination Detection Across Question Answering, Dialogue, and Summarisation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.29809 - Stratified Consistency Distillation for Natural Language Formalization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30258 - Anthropomorphism in the age of Large Language Models: An overview of potential risks and mitigations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38486 - CUEing User Simulators: Calibrated User Embeddings for Multi-Turn Benchmarking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02460 - Evaluating Multi-Dimensional Generalization of Large Language Models in Temporal Extraction Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02549 - OLMo-Detect: A Multi-Stage, Confounder-Controlled Benchmark for Membership Inference on Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02986 - The Percept-V Challenge: Can Multimodal LLMs Crack Simple Perception Problems? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.21143 - FrugalEvo: Towards Cost-Aware LLM-Guided Program Evolution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03675 - Framing the Narrative: Ideological Mimicry in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38256 - Mawqif-XT: An Arabic Benchmark Dataset for Cross-Target Stance Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09539 - EchoDistill: Robust Large Audio Language Models via Noisy-to-Clean Self-Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23954 - Collective Bias Mitigation via Model Routing and Collaboration Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03240 - Assessing Rule Adherence of LLM Adjudicators in Call of Cthulhu TRPG Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.02802 - A Language Model from 1913: Pretraining on Historical Text Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02991 - LiBRA: Detection-Aware Image Watermark Removal via Bidirectional Latent Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03166 - Detect and Suppress: A Mechanistic Defense against Adversarial Patches in VLA Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03498 - HASTE: Evolving Agent Harnesses Against Emerging Attacks Using Sparse Evidence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02920 - EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02298 - Reasoning Models Are Accurate but Unsound on Identification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03519 - Becoming Suspicious Across Borders: Algorithmic Extraterritoriality and AI-Driven Financial Surveillance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03425 - Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02826 - Preserving Anatomical Continuity: Three-Stage Pipeline for Colon Segmentation in 3D Abdominal CT Scans Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03467 - LoGo: Local-Global Rewards for Consistent Long-Horizon Video Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03636 - Jumping the Line: Exploiting Length Predictions in LLM Scheduling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03430 - HXAI: Hierarchical Privacy-Preserving Explainable AI in Distributed Energy Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02504 - SafeCoEvo: Co-Evolving Safety Harnesses and Guards for LLM Agents at Test-Time Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.36580 - 4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03715 - ADATEX4D: adaptive texture capacity allocation for 4D gaussian splatting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29963 - DyadMem: A Long-Term Memory Benchmark of How Agents Work with Users Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03020 - WISE-ATTA: When to Ask for Labels in Budgeted Active Test-Time Adaptation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37687 - ClarifyCodeBench: Evaluating LLMs on Clarifying Ambiguous Requirements for Code Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.00711 - Fold'EM: Direct atomic structure inference from Cryo-EM particles Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01358 - Bounded Reachability & Jailbreak Detection via Contraction-Constrained State Space Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02853 - Ego2World: Compiling Egocentric Cooking Videos into Executable Worlds for Belief-State Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02715 - DNAlign: Dynamic Null-Space Safe Alignment for LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02844 - GUI Agents for Continual Game Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28258 - WebUIProof: Benchmarking WebUI Code Generators with UI-Agent Execution Harness Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02617 - Equivariant Visual-Tactile Diffusion Policy for Contact-Rich Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03333 - TACD: Distilling Efficient Text-to-Motion Models via Terminal Amplification Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02867 - One Hypothesis Is Not Enough: Abductive Reasoning with Agentic Hypothesis Refinement over Knowledge Graphs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.31370 - Learning to Assess Heartbeat Observability for mmWave Heart-Rate Sensing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03570 - When to Compile a Computer-Use Agent? Measuring Payback and Making Compilation Decisions for Token Efficiency Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.02932 - The Effective Depth Paradox: Topology and Trainability in Deep CNNs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.13298 - Positive-Unlabeled Learning for Agent Safety False Alarm Auditing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02925 - EyeRobot 2.0: Active Gaze for Precise Manipulation without Wrist Cameras Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03710 - Self-Supervised Scaling of Terminal Environments for Scientific Domains Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02710 - Autoresearch in Mixed-Integer Linear and Nonlinear Programming Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39360 - PLCWorld: Benchmarking LLM-Generated PLC Programs in Closed-Loop Plant Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02982 - Tactile Curiosity Drives Robot Interaction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.40134 - When Terminal-Agent Training Stalls: Demystifying Data Generation and Verification Challenge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02405 - Information Limits of Low-Rank Approximation Certification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03321 - Relevant Evidence Decoding for Audio-Visual Hallucination Mitigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02976 - NARA: Anchor-Conditioned Representation Learning for Heterogeneous Vector Geoentities Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12276 - CreateScore: Domain-Theory-Informed Bayesian Routing for LLM-Based CV Screening Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02972 - Harness-Aware Distillation for Small Language Model Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02858 - Detect Before You Leap: Mirage Detection in Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00435 - Rethinking RAG in Long Videos: What to Retrieve and How to Use It? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.13141 - EviDent-CBCT: Evidence-Bottlenecked Report Generation from Dental CBCT under Non-Exhaustive Report Supervision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02375 - Securing Computer-Use Agents Against Branch Steering Attacks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03089 - Pincer: Resource Authorization for Agents using a Digital Twin Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02569 - Hypothesis-guided discovery of cognitive algorithms via program refinement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02523 - Improving the Energy-Efficiency of the Code Generated by LLMs through Effective Prompting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02571 - Trading Strategy Optimization via Textual Gradient Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03128 - Multi-Modal Environment-Aware Beam Management for Massive MIMO: A Geometry-Driven Virtual Base Station Framework Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.26567 - Evaluation format, not model capability, drives measured triage failure in the assessment of consumer health AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.11413 - MLCommons Jailbreak Benchmark v1.0 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02827 - LUMOS: Tracing Parametric Knowledge from Training Data to Behavioral Outputs in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02902 - iS-KV: Online Low-Rank KV Cache Compression via Block-Incremental SVD Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02815 - Learning What to Investigate Next: Meta-Reasoning for Long-Horizon Research Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02525 - ReFract: Benchmarking Perspective Awareness in Language Model Agents with Text World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03356 - Reinforcement Learning Techniques for the Optimization of Target Polarization in Nuclear Physics Scattering Experiments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02452 - Automating the Application of HCI Principles: Skills for On-Demand UI Construction, the Human-AI Space to Think, and the Future of HCI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02369 - How To Train Your World Model: Fine-tuning vs RAG for LM-based World Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02542 - ConfAL-WM: Confidence-Guided Active Learning for Action-Conditioned World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25572 - Keeping JEPA World Models Plannable When Little of the Frame Moves Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03137 - Planning Takes More Than Token Prediction: Causal Plan for Benchmarking and Building Physically Grounded Embodied Reasoners Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01810 - Choosing Before Acting: Comparative Value Estimation for Long-Horizon Tool-Use Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02330 - PAPER2LLM++: Continual Self-Evolution of LLMs from Research Papers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02793 - Automated Feature Engineering, AutoML, and Decision-Focused Learning for Improved Energy Consumption Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35013 - Science Is Falling Behind the Frontier: Foundation Model Adoption Across Half a Million Papers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.21739 - Mental-R1: Aligning LLM Reasoning for Mental Health Assessment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.13176 - AgentTrap: Stateful Feedback Deception against Autonomous Penetration Testing Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02869 - Depth as Time in One-Step Generative Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03626 - Learning to Revise Reasoning with Segment-wise On-Policy Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02703 - When a Correct Reward Is Not Enough: Diagnosing and Guiding PPO in an Analytically Solved Broker-Trader Game Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03598 - hacktrace: behavior-supervised detection of reward hacking during code generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03055 - Open-Endedness Bench: Measuring Epistemic Process from Agent Records Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02588 - Measuring Google AI Overviews: Activation, Source Quality, Claim Fidelity, and Publisher Impact Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.14021 - Multi-Task Evolution for Zero-Shot Cross-Problem Generalization using LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03316 - Correcting Guided Diffusion Trajectories with Spectral Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02753 - Safeguarding Mutual Correction in Source-Free Domain Adaptation via Cut Statistics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02981 - Controllable Accent Normalization via Discrete Diffusion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.14275 - SoftGene: Protein Language Model-Enhanced Soft Prompting for Interpretable Gene Set Annotation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03029 - Rethinking What to Cache in Few-Step Diffusion Transformers: Solver-Aware Target Selection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03577 - MEA: A Reward-Driven Multi-Agent System for Faithful Model Explanations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02480 - Do Large Language Models Know Colombian Law? A Reliability Benchmark for the Colombian Legal System Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03639 - Lost in the Request: How Communication Variation Disrupts Retrieval and Action in Email Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02627 - Transcriptome-informed multi-modal AI for predicting neoadjuvant therapy response from breast cancer biopsies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03693 - Multimodal reasoning for broadly neutralizing antibody discovery from label-free human B cell repertoires across virus families Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03160 - Early Detection of Distributed Backdoors in Multi-Agent LLM Systems: A Characterization Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.24893 - Preserving Mathematical Reasoning in Compressed Diffusion Language Models via Trajectory-Aware Low-Rank Approximation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03326 - EvoRiskBench: An Evolving Benchmark for Runtime Security Risks in Workspace Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03153 - Beyond Single Videos: Benchmarking and Active Evidence Seeking for E-Commerce Cross-Video Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03099 - World Action Planner: Generalizable Robot Decision-Making with Action-Conditioned World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.27599 - GlanceWAM: Sparse Test-Time Imagination for World-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23927 - Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03509 - Hybrid Reasoning Systems That Prioritize and Enhance Human Intelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.13477 - MOF-VERIFY: A Failure-Aware Agentic Harness for MOF Hypothesis Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03056 - DataWeave: Deploying Human-LLM Analytics for Exploratory Structured Data Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02679 - PsyEvo: A Personalized Counseling Agent That Self-Evolves at Test Time Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02885 - "I just assumed that it would translate": examining MT risk awareness among healthcare staff with abbreviations as a use case Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02496 - Law And Order: Tax Law Autoformalization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02792 - CONTRA: Discovering and Qualifying Behavior-Changing Questions for Selective Clarification in LLM Code Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01769 - DuetMoE: Coupling Inter- and Intra-Subgroup Robustness for Fair Medical Image Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10521 - Spend Teacher Tokens Where They Matter: Success-Referenced On-Policy Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02678 - Keep It CALM: Analyzing the Limits of Global Unsafety in Text-to-Image Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02300 - Towards Unified Music Emotion Recognition across Dimensional and Categorical Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.03979 - Rethinking Probability-Based Reinforcement Learning From Posterior Concentration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01458 - Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02967 - Less Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03717 - Revisiting Input Time-frequency Representations in Multi-pitch Estimation for Vocal Ensembles Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03656 - LensVLM: Selective Context Expansion for Compressed Visual Representation of Text Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07019 - KGPFN: Unlocking the Potential of Knowledge Graph Foundation Model via In-Context Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.14907 - WAM-OPD: Joint Video-Action Supervision for World Action Model Post-Training with On-Policy Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22364 - SovereignNegotiation-Bench: Evaluating User-Owned Personal Agents In Delegated Bargaining Under Privacy, Consent, Evidence, And Institutional Pressure Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.02814 - MintFlow: Minimal Trajectory Intervention for Constrained Flow Matching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02260 - Designing the Future of User Feedback for Generative AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02631 - $T^5$: Twin-Critic Training for Token-Level Thoughts in Reinforcement Mid-Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32791 - SovereignPA-Bench: Evaluating User-Owned Personal Agents under Evolving Intent, Platform Mediation, and Consent Constraints Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.05363 - Mitigating Social Sycophancy via Pluralistic Preference Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02568 - What's Missing in Screen-to-Action? Towards a UI-in-the-Loop Paradigm for Multimodal GUI Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.06995 - Reliable Self-Evolution with Imperfect Proxy Rewards Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02975 - Screw Attention: Rigid-Body Algebra Inside a Transformer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00904 - Coherence-Driven Belief Formation and Population Dynamics of Contagion in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02654 - THPL: A Vision-to-Language Decision Support Framework for Rainbow Trout Feeding Management in RAS Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02378 - OmniAct3D: Leveraging Foundation Geometry and Evidence-Grounded Reasoning for Panoramic 3D Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03015 - The Hitchhikers Guide to Rubric Quality Understanding and Enrichment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.01375 - Interrupting the Chain: Human Perception of AI-Generated Disinformation Through a Kill Chain Lens Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21389 - Offline Policy Optimization with Posterior Sampling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07393 - Contextual Flow Matching: Adaptive Step Selection in Flow Models for Efficient Visual Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03202 - Reach or Solve? Deep Diving into Agentic RL Gains with Checkpoint Handoffs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19636 - NeutronGym: Physics-Graded Neutron Instrument Design for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03631 - A GHOST in Long-Horizon Agents: Governance Hazard from Overlooked Safety Constraints across Turns Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02664 - LPA-CWM: A Learned Physical Adjudicator for Motion Reasoning with Counterfactual World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14073 - Refinement Buys Intelligibility, Search Buys Identity: What Test-Time Compute Buys in Masked-Diffusion TTS Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03320 - Embedded Bi-Temporal Building Damage Assessment for On-Board Data Reduction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37013 - Mitigating Private Data Leakage in LLMs with Whiteout Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02418 - SideKernel: A Usable microVM Sandbox for AI Coding Agents on macOS Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02456 - WAMpy: Efficient Synthesis of Prolog Programs in Python Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03234 - Low-Cost Video--Time Priors as a Strong Baseline for EEG--fNIRS Emotion Regression on Familiar Videos Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03618 - LLM-Guided Reinforcement Learning with Representative Agents for Traffic Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.06260 - Hop-Decayed Influence: New Vulnerabilities of Structural Auxiliary Indexing in GraphRAG Pipelines with LLM Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02373 - BusMA: A Bus Communication Substrate for Multi-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15054 - Corrupted but Correct: Why Vision-Language Models Lie to Themselves Internally Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03445 - What do your logits know? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.09885 - Geometry Meets Physics: Data-Efficient Pre-Training for Unstructured Neural PDE Solvers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03363 - MIRROR: Multipath Quorum Integrity for LLM Multi-Agent Communication Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02349 - HyperGuide: Hyperbolic Guidance for Efficient Multi-Step Reasoning in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24140 - When Numbers Start Talking: Numerical Signalling and Strategic Behaviour Among LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03033 - Toward Controlling Biology with Language:Offline Learning of Prompt-Conditioned Interventions for Cells, Organoids, and Biobots Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02247 - Cogentic: Multi-Agent Orchestration for Automated Proof Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.40324 - Equivariant Flow Matching for Electron Density Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02651 - Label-Efficient Time Series Classification at Scale: A Dual-Stream OSSE-LSTM with Counterfactual Attribution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02704 - CORE: COverage CAlibration and Evicted-Mass REdistribution for KV Cache Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02235 - Interpreting at Write Time: A Policy Ablation for Multi-Goal Agent Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02897 - CRAFT: Causal Responsibility and Failure Tracing in Medical Vision Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38810 - Novelty Adaptation Through Hybrid Large Language Model (LLM)-Symbolic Planning and LLM-guided Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.11351 - Traversing the Satisfaction-Diversity Frontier in Text-to-Image Diffusion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02372 - Out of Sync, Out of Sight: Phantom State Attacks against IIoT Intrusion Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02552 - Labels Override Definitions in Jev-Style Typed Decision Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02586 - Toward SLM-based agentic task-tool intent matching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03213 - RxnOptBench: Benchmarking LLMs for Reaction-Condition Optimization in Organic Methodology Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02242 - CVE2AP: Automated Generation of PDDL-Encoded Attack Paths via Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03383 - Assistant or Actor? Student Trust, Control, and Delegation Regret When Using a General-Purpose AI Agent Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.18257 - HazardWeaver: Scientific Route Selection for Hazard Analysis Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03591 - Causal Memory Policy: Making Memory Utility Identifiable by Intervening on Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02070 - How Artificial Intelligence LLM Engines Shape the Global Conflict Information Environment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.14197 - MobiAgent: Dual-Loop Recursive Policy Self-Improvement for Long-Horizon Mobile Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03476 - AMBER: Multi-View Adaptive Budget Allocation for Listwise Vision-Language Reranking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02831 - Coco: An Agentic Copilot for the Hardware--Software Co-Design Lifecycle Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02376 - Lightweight, Rubric-Guided Trajectory Evaluation for Production AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03315 - Time Series Forecasting Benchmarks Need Scenario-Grounded Stress Testing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02608 - Network-in-the-Loop at Scale: GPU-Batched 5G Simulation for Massively Parallel Robot Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02370 - Knowledge or Calculator? Decomposing the Skill Premium in Verifiable Financial Agent Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03564 - Learning transferable human physiology from two million hours of sleep with SleepFM-2 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06849 - World Action Modeling with Progressive Visual Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02508 - Learning a Fact Is Not Learning How to Retrieve It Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03251 - Tropical Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02478 - Rethinking the Evaluation of Harness Evolution for Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.12227 - What Does a Token Cost? A Mixture-of-Agents Measurement of Sufficient Per-Token Compute Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02491 - A Multi Method Importance and Performance Efficiency Analysis of Topological Metrics for Natural Visibility Graph Based Cyber Attack Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02342 - DriftTTS: Few-Step Text-to-Speech Without Distillation via Distribution-Matching Drift Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03390 - Foresight: planning future perception in streaming VLMs without retraining Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03123 - Dynamic LLM Routers are Often Misguided Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02762 - The AI Risk Observatory: What Can We Learn from AI Disclosures in Annual Reports About Societal Resilience? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02281 - Optimal Planning in a Dynamic World Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03312 - ARGOS: Reinforcement Learning-Driven Multidimensional Elasticity for Service Orchestration in the Computing Continuum Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37085 - Extended to Reality: Prompt Injection in 3D Environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.07104 - EVOL: Simulator-Guided Evolutionary Expert Synthesis for Deployment-Free Learning Path Recommendation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03273 - TasteBench: Multimodal Benchmark for Sensory Prediction, from Molecules to Sustainable Foods Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02599 - Weave Forcing: Compositional Memory Routing for Interactive Long Video Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03510 - Learning Low-Frequency Motion Control for Robust and Dynamic Robot Locomotion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2209.14887 - Recursive Harness Self-Improvement for Frontier Reasoning Data Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03548 - Answering clinicians' questions over trial evidence tables with verifiable, feedback-driven language models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02576 - On the Chain-of-Thought Monitorability of Looped Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02741 - CuBEs: Culturally-Situated Behavioral Evaluations and the Limitations of Culture-Blind LLM Judges Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02622 - Consecutive Posterior Fusion for Diffusive Recovery of Unobservable Image Structures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03261 - LPS-Bench: Benchmarking Safety Awareness of Computer-Use Agents in Long-Horizon Planning under Benign and Adversarial Scenarios Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.03255 - Credit Where It Matters: Dependency-Aware Policy Optimization for Terminal Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03634 - RASPER: Reward-Aligned Summarization of Clinical Notes for EHR Outcome Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02979 - Beyond Predefined Sinks: Security-Aware Dependency Analysis for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03014 - Modeling Shared and Individual Structure for Cross-Subject Continuous Affect Regression from EEG-fNIRS Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02796 - From Learner Behavior to Reusable Skills for Effective and Efficient Learner Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37157 - BitNest: Bit-Nested Speculative Decoding for Memory-Efficient LLM Inference Acceleration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02800 - From Fragments to Global Maps: Learning Vectorized Map Aggregation with Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02513 - Reasoning with Evidence, Not Merely Rationales: Verifiable Preference Proofs for LLM-Based Recommendation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02968 - From Migration to Calibration: Preserving Agent Capabilities across Models, Jurisdictions, and Scale Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35149 - RIFAR: Reliability and Forgetting-Aware Replay for Continual Robot Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03079 - MetaRubric: Learning to Reward for Rubric-Based Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02824 - Uncertainty as a Proxy for Semantic Correctness in Diffusion-Based Medical Image Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03224 - Causal discovery identifies pathways linking physical activity to dementia risk in the UK BioBank Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02221 - Batched Speech Decisions Without Decoding: Single-Token Supervision Lets a Frozen LLM Hear Beyond the Transcript Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02638 - World Editing: Intervening on Executable Worlds at Increasing Depth Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02331 - ForestQuery: Boundary-Aware and Spatially Anchored Query Learning for Unified Forest Point Cloud Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03403 - IntentCoding: Amplifying User Intent in Code Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.00066 - EXAM2: Extending Audio Understanding in Multilingual and Multimodal Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23758 - FlashSinkhorn 2: Block-Sparse Entropic Optimal Transport Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02395 - Learning Skills from Historical Action Trajectories: Action Experience Dictionary for World Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.40219 - Revealing Epistemic Uncertainty in MLLMs via Causal-Invariant Masking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02887 ## Community - Quoting Felix Rieseberg Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Oct/5/felix-rieseberg/ - Floci, Great LLM Apps, BCE Outbound Integrations, Hexagonal vs. BCE--Questions for the 151st airhacks.tv Source: adam-bien Topic: Java (+AI) URL: https://adambien.blog/roller/abien/entry/floci_great_llm_apps_bce_outbound_integrations_hexagonal_ - Fragments: October 4 Source: martin-fowler Topic: Architecture (+AI) URL: https://martinfowler.com/fragments/2026-10-04.html - A Series of Unfortunate Events for OpenAI Users Source: hacker-news Topic: General (+AI) URL: https://insufferable.dev/posts/a-series-of-unfortunate-events-for-openai-users/ - OpenAI "rogue" agent activities found on Wikimedia projects Source: hacker-news Topic: General (+AI) URL: https://diff.wikimedia.org/2026/10/05/openai-rogue-agent-activities-found-on-wikimedia-projects/ - Our approach to EU text provenance rules Source: hacker-news Topic: General (+AI) URL: https://openai.com/index/eu-text-provenance/ - GPT-6 Astra cracks 217-year-old Napoleonic code in six hours Source: hacker-news Topic: General (+AI) URL: https://www.tomshardware.com/tech-industry/artificial-intelligence/chatgpt-6-astra-cracks-217-year-old-napoleonic-code-in-just-six-hours-single-prompt-ai-run-solves-24-rows-of-custom-symbols-from-a-single-image-reveals-lost-troop-orders - Anthropic reported diary entry to police, woman faces felony charge Source: hacker-news Topic: General (+AI) URL: https://www.techspot.com/news/114091-florida-woman-used-claude-diary-anthropic-reported-shoot.html - Legal risks pile up for Altman as OpenAI uncovers hacks Source: hacker-news Topic: General (+AI) URL: https://www.ft.com/content/2c24ece3-ac99-43a8-b0e6-4a3867e37ebf ## Media - Agent Evaluation walkthrough Source: youtube-googlecloud Topic: AWS (+AI, Cloud, General) URL: https://www.youtube.com/shorts/H41csOSNLWQ - How Antigravity Evaluates a LangGraph Agent Source: youtube-googlecloud Topic: AWS (+AI, Cloud, General) URL: https://www.youtube.com/shorts/-7GgFPFY4WI - PewDiePie is setting AI free... and OpenAI is furious Source: youtube-fireship Topic: Web (+AI, General, JavaScript) URL: https://www.youtube.com/watch?v=_5p1_TNSWqQ