TILens Daily Edition 2026-10-23 Filters: topic=ai, github=hidden Stats: 912 articles, 24 sources, 872 research papers Top topics: AI, AI Research, Information Retrieval ## News - Web Search on Amazon Bedrock now supports domain filtering and user location controls Source: aws-whats-new Topic: AWS (+AI) URL: https://aws.amazon.com/about-aws/whats-new/2026/10/bedrock-web-search-domain-user-location/ - Rapidly scaling online storage to serve over 1 billion ChatGPT users (Part II) Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/scaling-storage-one-billion-users-part-two - LitPivot: Developing research ideas through dynamic contextualization within the literature landscape Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/allenai/litpivot - Securing our frontier model training environment Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/securing-our-frontier-model-training-environment - Spring AI 2.1.0-RC1 and 2.0.2 Available Now Source: spring-blog Topic: Java (+AI) URL: https://spring.io/blog/2026/10/23/spring-ai-2-1-0-RC1-available-now - Anima helps clinics cut call waits by 75% with GPT-6 and GPT-Live Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/anima - OpenAI and Poland’s NASK partner to advance AI safety and security Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/openai-nask-ai-safety-security-partnership - Does Your Model Run on AWS Trainium? Look It Up Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/torch-neuronx-model-support - OpenAI says it will no longer train its AI models on the live internet, citing “significant risks” Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/10/23/openai-says-it-will-no-longer-train-its-ai-models-on-the-live-internet-citing-significant-risks/ - OpenAI disables internet access during model training while Anthropic issues another mea culpa Source: theregister Topic: General (+AI) URL: https://www.theregister.com/ai-and-ml/2026/10/23/openai-disables-internet-access-during-model-training-while-anthropic-issues-another-mea-culpa/5305238 - I Tested Microsoft's Surface Laptop Ultra. The Local AI Performance Is Remarkable. Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/guides/microsoft-surface-laptop-ultra-review-the-local-ai-performance-is-remarkable/ - Red-team report found OpenAI utterly failed to monitor its agents during Hugging Face attack Source: theregister Topic: General (+AI) URL: https://www.theregister.com/ai-and-ml/2026/10/23/red-team-report-found-openai-utterly-failed-to-monitor-its-agents-during-hugging-face-attack/5305200 - Create an AI Podcast Generator with ElevenLabs Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/voice_developer/create-an-ai-podcast-generator-with-elevenlabs-1gfl - Empty AI observability panels: a product teardown of SigNoz Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/k-kj0/-empty-ai-observability-panels-a-product-teardown-of-signoz-3e99 - The main WebDev conference is back in Amsterdam! 🎉 Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/gitnationorg/the-main-webdev-conference-is-back-in-amsterdam-28o8 - AI models describe humans as a bunch of amoral sheep Source: theregister Topic: General (+AI) URL: https://www.theregister.com/ai-and-ml/2026/10/23/ai-models-describe-humans-as-a-bunch-of-amoral-sheep/5305123 - What some of Anthropic’s backers are worth before its IPO Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/10/23/what-some-of-anthropics-backers-are-reportedly-worth-before-its-ipo/ - Palmer Luckey’s gene-edited war dogs Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/palmer-luckey-gene-edited-war-dogs - Presentation: Move Fast, Don’t Break Trust: Shipping Constantly with Humans and Beyond Source: infoq-architecture Topic: Architecture (+AI) URL: https://www.infoq.com/presentations/monzo-microservices-devex/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Architecture+%26+Design - I scanned 100 apps built with Lovable. 14 were already dead. 1 leaked a live API key. Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/rasberryx/i-scanned-100-apps-built-with-lovable-14-were-already-dead-1-leaked-a-live-api-key-1f3j - U.S. banks catch AI agents going off-script Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/us-banks-catch-ai-agents-going-off-script - 😺 Microsoft AI scored 83% where doctors got 36% Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/microsoft-ai-scored-83-where-doctors-got-36/ - The Catch Behind Microsoft's Medical Superintelligence Breakthrough Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/the-catch-behind-microsofts-medical-superintelligence-breakthrough/ - Who Is Responsible When AI Agents Start Moving Your Money? Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/who-is-responsible-when-ai-agents-start-moving-your-money/ - Can AI Companies Trust Their Safety Monitors When Agents Can Bypass Them? Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/can-ai-companies-trust-safety-monitors-agents-bypass/ - Everything That Happened in AI Today (Friday, October 23, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-today-friday-october-23-2026/ - 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-2d05 - OpenAI Signal leaks 💬, Alexa Tablet 💻, formal software verification 👨‍💻 Source: tldr-tech Topic: General (+AI) URL: https://tldr.tech/tech/2026-10-23 ## Research - Bringing foundational models to the front lines of TB screening Source: google-research-blog Topic: AI Labs (+AI, AI Research) URL: https://research.google/blog/bringing-foundational-models-to-the-front-lines-of-tb-screening/ - Don’t Let Messy Data Bend Your Curves Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/dont-let-messy-data-bend-your-curves/ - Skewness and Kurtosis: From Moments to Machine Learning Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/skewness-and-kurtosis-from-moments-to-machine-learning/ - Why Parameter Count Is Not Model Complexity: An Introduction to Effective Dimension Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/why-parameter-count-is-not-model-complexity-an-introduction-to-effective-dimension/ - Your Six AI Models Are Really Two: The Math of Correlated Mistakes Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/your-six-ai-models-are-really-two-the-math-of-correlated-mistakes/ - One Pretrained Decision Model Is Enough for Training-Free Generalist Graph Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30777 - Measuring Pretraining Contamination in Public Medical Vision-Language Benchmarks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10066 - Automated screening of privacy risks in medical AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30229 - FreeEvolve: Learning to Evolve Beyond Fixed Loops Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09197 - QuaNAS: Uncertainty-Aware Reuse of Earlier Searches for Query-Efficient Neural Architecture Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31251 - Random Remasking Scales Masked Diffusion Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30744 - Questioning Instrumental Convergence in RLVR: Checkpoint Evidence from OLMo-3 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31624 - Graph Memory Transformer (GMT) Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.23862 - ACTIVA: Amortized Causal Effect Estimation via Variational Autoencoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.01290 - Evaluating the Applicability of LLM Inference Optimizations on Apple Silicon Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31479 - Amplifying Latency and Cost of LLM Inference via Rowhammer Attack Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30798 - Revisiting GAN with Bayes-Optimal Discrimination Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.25609 - Energy and Latency First: How Deployment Constraints Reverse Time-Series Model Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30965 - On the Gradient Domination of the LQG Problem Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.09026 - Penalized Fair Regression for Multiple Groups in Chronic Kidney Disease Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.17340 - Decision Making and Ride Comfort Evaluation Based on Lane-Change Prediction for Autonomous Vehicles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30528 - Redundancy Meets Synergy: Dependency-aware Expert Selection for MoE via Submodular Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00558 - Bridging the Data Gap: Source-Informed Task-Space Transport for Few-Shot Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31323 - Same molecule, Different Knowledge: Cross-Identifier Binding Failures in LLMs For chemistry Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30903 - MoEZip: Routing-Aware KV Cache Compression for Sparse Mixture-of-Experts LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30206 - Parallel gradient boosting for flexible estimation of conditional distributions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.13550 - Do Machine Learning-Guided Proactive Full Capacity Protocols Mitigate Emergency Department Overcrowding? A Simulation-Based Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30148 - LACToS: Local Anomaly Detection via Conditional Typicality of Superpixels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31538 - Metric Conformal Prediction via the Conditional Expected Local Radius Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31336 - To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.03207 - RaSFNet: Ray-aligned and Scan-aware Fusion Network for LiDAR Semantic Segmentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31186 - What Comes Next and Why: Interpretable Next-Event Prediction with Neuro-Symbolic Rules Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31114 - Deep ReLU Networks Can Fail the Best Approximation Property for Continuous Target Functions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31264 - Towards Field-Deployable Wearable IMU Systems for Occupational Activity Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31160 - Meta-learning of Gibbs states for many-body Hamiltonians with applications to Quantum Boltzmann Machines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.16373 - When Self-Consistency Backfires: Majority Vote Hurts the Majority of Hard Science Problems for Small LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11403 - SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30329 - Shift-aware score transport for privacy auditing without retraining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31549 - Poisoning-Based Backdoors Are Not Cryptographic Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28045 - SIGNN++: Robust Graph Neural Star Identification on Earth Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30186 - Bayesian Fixed-Confidence Best-Arm Identification with Abstention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30384 - Kernel-Managed Shared Memory for System-Wide Personalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10144 - Deficit-Driven Stratified Acquisition for Building STRATA-S12: An Open SAR-Optical Corpus for Self-Supervised Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17680 - Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31670 - AtManRL: Towards Faithful Reasoning via Differentiable Attention Saliency Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.16158 - Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06145 - Aggregation of Published Non-Uniform Axial Power Data for Phase II of the OECD/NEA AI/ML Critical Heat Flux Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.00034 - Interface-Induced Trajectory Censoring Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03966 - Primal-Dual Representation Learning for Low-Rank Constrained MDPs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30756 - Post-Audit Mirage: Identifiability Limits of Offline Agent Verification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31130 - AIRO: A Streaming-Based Machine Learning Framework for Threat Detection and Security in Industrial Internet of Things Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30713 - Learning Discrete Riemannian Metrics for Physical Fields with Cochain-Frame Equivariance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14556 - Would an LLM Match into a Residency? Uncertainty, Reasoning and Image Use of Open Language Models on the Spanish MIR Examination Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31586 - Gandalf: Flash Shall Not Die! Increasing Flash Storage Lifetime for KV Cache Offloading in LLM Serving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30791 - Visualizing and Interpreting Temporal Care Team Dynamics for Cancer Survival Risk Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30748 - Code Comprehensor: Hierarchical Documentation and Cross-Modal Retrieval for Large Repositories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30016 - Wavenumber-Aware Deep Learning for Robust Analysis of Raman Spectra Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30746 - When News Gets Old: Portfolio Allocation with Reinforcement Learning and Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30564 - Extreme Compression of Per-Layer Embeddings via Cross-Layer Latent Vector Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31309 - Agentic Verified Optimization of Real-World Software Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30188 - Lifetime-valid decisions by continually evolving AI analysts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30562 - Structure-preserving reduced-order models of thin panels in supersonic and hypersonic flow Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31504 - Do Tabular Foundation Models Know Physics? Contamination, Units, and the Deterministic Limit Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02766 - Future of Time Series Anomaly Detection: From Historical Review to Unified Outlook Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30628 - Short-to-Long: Detached Features for Long-Horizon Value Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30461 - Projecting Latent RL Actions: Towards Generalizable and Scalable Graph Combinatorial Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19721 - MOER: Mix-Policy Optimization under Expert Prefix Guidance with Selective Rollback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30873 - Generative Retrieval for Reverse Target Fishing with a Proteome-Scale Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24458 - Advances in Machine Learning for Directed Evolution: A Five-Year Retrospective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03046 - SDS-LoRA: Overcoming Anisotropic Gradient Scaling in Low-Rank Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16454 - DIAL: Steerable Language Models with Distilled Instruction-Adherence Levels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31438 - Measuring Model Robustness via Fisher Information: Spectral Bounds, Theoretical Guarantees, and Practical Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04767 - DISC: Domain-Integrated Similarity Cost for Time-Series Dataset Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31288 - Nonparametric autoregressive estimation of probability distributions with parallel gradient boosting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31524 - Efficient and Optimal Learning of Discrete Distributions with Person-Level Privacy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31612 - UnlearningSoup: Is Repeated Tuning Necessary for Large Language Model Unlearning? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37076 - LSVD: Loss-Aware Low-Rank Approximation for Efficient Low-Precision Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00573 - Are Two LLMs Better Than One? A Student-Teacher Dual-Head LLMs Architecture for Pharmaceutical Content Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.11957 - Causal Chain of Thought: Mitigating Attention Leakage via Context Isolation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31639 - baseVultra: Compact Nonlinear Recurrence with Reallocated Capacity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30154 - Optimistic Policy Regularization: Elite-Statistic Reward Shaping Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.06793 - MarkTune: Improving the Quality-Detectability Trade-off in Model-Embedded LLM Watermarking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.04044 - Bayesian Ambiguity Contraction-based Adaptive Robust Markov Decision Processes for Adversarial Surveillance Missions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.01660 - Same Beliefs, Different Policies: Learning Reusable Representations for Early Stopping in LLM Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30450 - FIGFLEX: A Mixed-Precision FP-INT GEMM Accelerator Co-Designed with Low-Bit LLM Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30480 - AQL-Lite: Enabling Efficient Knowledge Acquisition for Arabic LLMs via Data-Centric Continual Pretraining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30344 - Inside-JEPA: From Prediction to Relational Grounding in Latent World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31194 - How Prompt Style Affects AI Accuracy and Speed in Competitive Programming Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30223 - GateFormer: Forecast-Space Decomposition for Intra-Hour Solar Irradiance Prediction from Sky Images Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30942 - CoarseSoundNet: Building a reliable model for ecological soundscape analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21143 - The Fenchel-Young Generalization of Bayesian Principles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.10295 - Training Small Language Models for Transferable Tool Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31483 - RheOPT: Few-Shot Non-Newtonian Flow Prediction via Newtonian Pretraining of RheOFormer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31465 - Robust Tangent Space Estimation via Laplacian Eigenvector Gradient Orthogonalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.02308 - Transformers with CoT Discover Heavy-Ball Acceleration Through Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31089 - Random Projections for Spectral Algorithms: Optimal Rates in Sobolev Norms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30948 - Diffusion Language Models for Perplexity-Aware Black-Box Attacks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31558 - Verification of Unknown Dynamical Systems via Autoencoder Latent Space Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.13593 - Super Agents and Confounders: Influence of surrounding agents on vehicle trajectory prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.03463 - A Quadratic Lens on Muon's Polar Update: Benefits, Pitfalls, and the Role of Newton-Schulz Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30280 - Action Learning for Scientific Simulations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31585 - Energy Estimation for Virtual Servers Using Resource Utilization and Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.09991 - AI Mindmeld: A Latent Interconnect Protocol Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30215 - Show Me What You Don't Know: Efficient Sampling from Invariant Sets for Model Validation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.21782 - FLAWS: A Benchmark for Error Identification and Localization in Scientific Papers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.21843 - Spike-Aware Gradient-Based Mixed-Precision Quantization of Spiking Neural Networks for Vision Applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30339 - Memory before Goal: Role of Pre-History Memory for Humanoid Loco-Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31166 - Learning Robot Behavior Priors from Non-Robotic Synthetic Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31275 - The Bayesian Learning Rule Beyond KL Geometry Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31308 - DiffLTM: Continuous Diffusions Large Tabular Models for Conditional Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30472 - LLM-Guided Transportation Hub Capacity Planning with Textual Business Inputs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.03651 - Drift Says When, Budget Says How Much: Rate-Controlled KV Re-selection for Long-Form Multimodal Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31433 - On Sex, Evolution, and the Multiplicative Weights Update Algorithm Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/1502.05056 - A Transformer-based Approach for Real-time Multi-agent Path Planning with Varying Initial/Final Conditions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30388 - AgenticEvolve: Evolutionary Program Search with Persistent Language Model Agents that Design and Run Experiments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31326 - Building Presentation Intelligence for High-Quality Slide Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30888 - Parameter Learning in Active Inference via Variational Message Passing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30899 - Equilibria and Learning in Competitive Market Making Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30891 - Tractable Inference with Kolmogorov-Arnold Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29909 - Present but Hard to Read: Probing Latent Reasoning with Minimal Pairs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28498 - RiboBridge: protein-conditioned de novo RNA binder structure design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30668 - How Depth Growth and Looping Shape In-Context Learning in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31421 - AfterDeleteBench: Auditing Post-Deletion Information Persistence in LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31366 - Adaptive Deadline- and Energy-Aware Caching Algorithms in Dynamic Multi-UAV Edge Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30768 - Beyond Accuracy: Disentangling Decomposition from Typed-State Quality Assurance in Multi-Agent LLM Pipelines Source: arxiv-cs-lg Topic: AI Research (+AI, FastAPI, Python) URL: https://arxiv.org/abs/2610.31280 - One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06166 - Measuring, Localizing, and Reducing the AI-Like Writing Style of Post-Trained LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30526 - Benchmarking Compositional Generalisation for Machine Learning Interatomic Potentials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08988 - Semantics Delivery Network: Rethinking Web Retrieval Infrastructure for LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22486 - SleepMaMi: A Universal Sleep Foundation Model for Integrating Macro- and Micro-structures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.07628 - Residual Correlation as a Diagnostic for Joint-Uncertainty Gains from GP Coregionalisation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30085 - OP-Print: Tracing Membership Imprints in On-Policy Self-Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31616 - MAVOS-DD: Multilingual Audio-Video Open-Set Deepfake Detection Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.11109 - Fixed-Dimensional Latent Flow for Generating Variable-Size 3D Molecules Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08333 - Convex Equilibrium Potentials for Monge--Amp\`ere: Curvature Bounds and A Posteriori Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31386 - What Does It Take For A Generalist Robot Policy To Adapt Using Minimal Data? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11363 - Memory-Augmented Online Test-Time Adaptation for EEG Motor Imagery via Perturbation Consistency and Confidence Calibration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30422 - METTA: Memory-Enhanced Test-Time Adaptation for Meta-Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31656 - Exact and Asymptotically Complete Robust Verifications of Neural Networks via Ising Solvers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.00408 - Towards Faithful Data Selection: Statistical Limits and Scalable Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30442 - PROACT-Agent: Progressive Runtime Oversight and Active Circuit-breaking for Real-Time Safety Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34415 - An Optimal Control Approach To Transformer Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.09571 - AirPASS: Over-the-Air Federated Learning via Pinching Antenna Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.06768 - Unrestrained Simplex Denoising for Discrete Data. A Non-Markovian Approach Applied to Graph Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.28572 - Benchmarking Model Compression Techniques Across Heterogeneous Edge Platforms: A Predictive Maintenance Use Case for Rotating Machinery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30228 - Data-Driven Vision-Language Models for Remote Sensing: A Survey Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31304 - Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12122 - Bridging Number-Theoretic Primality Testing And Algorithmic Optimization: An Adaptive Cryptographic Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30935 - Semi-Linear Gaussian Bayesian Networks: Enhancing Flexibility in Node Dependencies via penalized B-Splines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30838 - Pathways of Visual Information Flow in Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.03358 - Are EEG Sequences Time Series? EEG Classification with Time Series Models and Joint Subject Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2404.06966 - Inherited, Not Invented: Tracing the Provenance of Wait in Reasoning Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30882 - Trace2World: Reconstructing App Worlds from Real Interaction Traces for Scalable GUI Agent Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30792 - High-Value Training Data from Noisy, Diverse Sources Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30421 - Local Discrimination of Binary Classifiers via Localized AUC Functional Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31216 - EEG-Captioner: Grounding EEG-to-Language Generation in Fundamental Signal Properties Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30995 - aggmetrics: Aggregating Classification Performance Measures for Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30456 - Escaping the Phylogenetic Trap: Persistent Homology Enables Cross-Species Ion Channel Classification via Multimodal Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30394 - Bifurcations from Weight Space: JEPAWG on Parametric Dynamical Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30847 - SWE-VERIFIER: Selective Verification for Cost-Efficient Coding Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30284 - Structured Unitary Tensor Network Representations for Circuit-Efficient Quantum Data Encoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.16266 - Diagnostic Loss: Asymmetric Supervision for Radiology Report Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30980 - Fast Iterative Combinatorial Auctions via Deep Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30667 - Few-shot Classification as Multi-instance Verification: Effective Backbone-agnostic Transfer across Domains Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.00401 - Is the Judge Its Twin? Post-training makes a model's writing more predictable but barely moves its taste, as a judge, toward predictable writing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32196 - Joules-to-GDP: How Much Economic Value Do AI Systems Produce per Unit of Energy? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30858 - Neural Spectral Capacity with Residual Context for Heterogeneous Resource Allocation within Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30823 - Post-Hoc Feature Selection Layer for Neural Networks Interpretability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31420 - ShIOEnv: A Command Evaluation Environment for Grammar-Constrained Synthesis and Execution Behavior Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.18374 - Rethinking Sequence Compression with Test-time Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31574 - GANet: A Lightweight Group Attention Network for Plant Disease Identification on Embedded Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30225 - EgoHand: Monocular 3D Hand Reconstruction from Egocentric Video Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30293 - Decoupling candidate dual AGN from chance superpositions in the GOTHIC survey via a deep-learning framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24164 - nnInteractive Agent: General-Purpose AI Agents as 3D Image Annotators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31080 - Same Luck, Different Choice: Twin-World Credit Assignment for Agentic Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31544 - Evolving Federated Density Peak Clustering with Shuffler-Based Anonymization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31211 - SpectralCanary: Embarrassingly Simple Low-Frequency Traces for T2I Dataset-Use Auditing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31659 - Conservative Meta-Agent Search: Architecture Adaptation under Non-Stationarity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31436 - How to Backdoor Image Knowledge Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.21323 - Predictable Scaling: Efficient Model Exploration via Scaling-Law Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23453 - Markovian Generation Chains in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.11228 - When Forgotten Facts Return: Relearning-Aware Unlearning of Knowledge Graph Embeddings via Tangent Kernels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31075 - Joint or Per-Option? Compact Encoders for Closed-Set Decisions from 17 Million to 1 Billion Parameters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30970 - Random Initialization as a Baseline for Time Series Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30950 - Lean Finder V2: Semantic Search for Mathlib That Disambiguates User Queries Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30843 - Risk-Aware Alignment Must Incorporate Reward Uncertainty Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.23726 - Multi-View Causal Discovery without Non-Gaussianity: Identifiability and Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.20115 - When Should LLMs Reason? Adaptive Inference Routing via Entropy Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22873 - EpiSEM-Bench: Evaluating Safety and Evidence Recovery in LLM Agents under Missing Evidence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31650 - NEST: Nested Embedding Representation for Multiscale Clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30520 - A Fix for Softmax and Cross-Entropy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31642 - An Agent Architecture with Tools and Memory for Selective Correction of Wrist PPG Heart Rate Estimates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30688 - Closed-Loop Dual-Reference Guidance for Accent Control in Cross-Lingual Voice Cloning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29351 - Manifold Sampling via Entropy Maximization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12338 - Multi-Token Prediction and Alternative Tokenization Improve Learning Latent Multi-Hop Graph Search at Scale Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31439 - Semantic Optimal Transport for Sparse Autoencoder Feature Matching and Circuit Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28567 - Piano2Pop: Expanding Piano Demos into Pop Productions Without Aligned Supervision Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31510 - Continuous-depth Deep Gaussian Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30890 - Near-Optimal Regret for KL-Regularized Multi-Armed Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.02155 - PYTHIA, a transferable machine learning framework for simultaneous defect and adsorption site optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31539 - FlowCritic: Bridging Value Estimation with Flow Matching in Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.22686 - Solvable models of learning to pursue a moving target Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30721 - Fragility-aware Classification for Risk Characterization and Robust Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.13024 - Prompt Sensitivity in Tool-Augmented Model Comparisons Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31148 - Reverse-KL Policy Distillation: Statistical Guarantees and Limits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30844 - IGADA-IoT: IoT Sensor Energy Optimization in Wireless Sensor Networks Driven by Automatic Data Augmentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.27397 - Extending FunctionGemma for Practical On-Device Mobile Function Calling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.25373 - CRANE: Post-Hoc Counterfactual Retrieval for Multimodal Classifiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31594 - Stability Analysis of Signed Graphs under Structural Perturbations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30444 - Generalizing Metropolis-Hastings for DAG Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30291 - When More Metadata Misleads: Probing Field-Level Grounding in LLM-Generated Museum Descriptions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31193 - Analysis of On-policy Policy Gradient Methods under the Distribution Mismatch Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.22244 - Optimal Multitask Representations Under a Rate Constraint: An Information Bottleneck Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30493 - WhatIf-Bench: Benchmarking Intervention-Aware Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26582 - Rethinking Molecular Text Representations for LLMs: An Empirical Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03057 - xVGAE: A Hierarchical Variational Graph Autoencoder for Exchangeable Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30815 - DetoxAI: a Python Toolkit for Debiasing Deep Learning Models in Computer Vision Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.05492 - Detecting AI Training in Datacentre Power Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30182 - TabClustPFN: A Prior-data Fitted Network for Tabular Data Clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21656 - Dimension-free regimes for unadjusted Langevin in ridge-separable models: A subspace robust Wasserstein analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31431 - Stochastic Matching Bandits with Rare Optimization Updates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.04194 - On the Token Collapse Phenomenon in Textual Graph Soft Prompting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31572 - Width and Depth Limits Commute During Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30729 - Ground-Truth-First Benchmarking of Reinforcement Learning via Converse Optimality: From Smooth, Fully Observed Systems to Non-Smooth or Partially Observed Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30954 - OpenAttention: One Percent Is Enough with Tail Proxies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30951 - Evolutionary Deep Nets for Non-Intrusive Load Monitoring Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2303.03538 - Bridging the Closed-World Gap: Interpretable Anomaly Detection via a Hybrid TSK-FCM Ensemble on the BETH Dataset Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30576 - What Lies Beyond Perception: A Partition Theory of the Limits of AI Evaluation and Oversight Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30803 - Parallelizable Probabilistic Latent Reasoning for Diverse Reasoning Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29385 - Differentially Private Synthetic Data via Generalized Moment Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30196 - NADS: Navigator-Guided Data Selection for Mitigating Catastrophic Forgetting in Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.25751 - High-dimensional learning dynamics of multi-pass Stochastic Gradient Descent in multi-index models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21093 - Why Constrained Updates Still Forget: A Functional-Path Analysis of Continual SFT Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30191 - Graph-Recurrent Learning of Emergent Collective Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31350 - Learning Domain Trajectories with Flow Matching for Gradual Domain Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30685 - The Cost of Saying Hello: An Empirical Study of Handshake Overhead in AI Agent Communication Protocols Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30151 - Federated Graph Retrieval-Augmented Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30728 - DRAFT: Decoding and Reconstructing 3D Room Layouts from fMRI and Camera Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31108 - GFlowPO: Generative Flow Network as a Language Model Prompt Optimizer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.03358 - Specter: Fast MoE Inference via Quantization-Enabled Multi-Step Speculative Offloading Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.14102 - Eluder-Dimension-Free Regret for Stage-Wise Constrained Contextual Bandits via Offline Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.07101 - ShlokaDhara: A Multi-Speaker Sanskrit Speech Corpus for Learning Meter-Aware Prosody in Text-to-Recitation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26929 - Spectral Uncertainty Decomposition for Sparse Bayesian Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30207 - CTRL-FM: Inference-Time Structural Control for Flow-Based Virtual Sensing under Long-Horizon Node Outages Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30362 - On the Adversarial Vulnerability of Neural Receivers with Unrolled LDPC Decoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30345 - Flow-based Spectral Kernel Learning for Nonstationary Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30465 - BeNice! Closing Looping's Inference-Memory Gap via KV-Sharing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31633 - How Far Can Sharpness and Complexity Jointly Explain Generalization? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.29043 - How Does RL Post-training Induce Skill Composition? A Case Study on Countdown Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.01775 - HERD: Harness-Evolving Recursive Distillation for Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31401 - Brittlebench: Quantifying LLM robustness via prompt sensitivity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.13285 - SAHG: Sector-Anisotropic Hyperbolic Graph Model for Social Bot Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30166 - Phase Transition from Random Features to Fully Trainable Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31663 - Evaluating Neural Probabilistic Forecasts of Sparse Earthquake Counts: What Survives a Careful Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21437 - Prediction Is Not Calibration: Item Parameter Recovery and Representation Coupling in Knowledge Tracing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30211 - The Mathematical Theory of Double Descent as Shrinkage, not Overfitting: Matching Bounds for Path-Regularized Multilayer Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.02129 - When Reconstruction Is Not Enough: Doubly Robust Counterfactual and Interventional Mediation Analysis with Learned Multimodal Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30220 - FlashBoB: I/O-Efficient Exact Backward-over-Backward for Softmax Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24089 - An Adaptive-Horizon Graph Neural Operator for coupled surrogate morphodynamic modelling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22432 - GAV: A scientific experimentation environment for PDE agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30292 - TerraTransfer++: Demonstration-Free End-to-End Planner Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30319 - Mostly Reading: What Open-Book Scores Measure in Document-Level LoRA Adapters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31017 - Mixing Matters: Evidence Position Bias Across Sequence Mixers in Long-Context Question Answering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31135 - LLM2Cert: LLM Synthesis of Certificates with SMT/Lean Verification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30524 - Learning Unbiased Permutations via Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16755 - Trajectory Learnability for Offline On-Policy Distillation with Imperfect Teachers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18321 - The Value of System 1 Models in Medicine Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31315 - Consistency Is Not Validity: Self-Rewarded Moral Argumentation Makes Language Models Decisive but Pliable Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30349 - When Prediction Error Is Not Enough: Evaluating Nuisance-Function Prediction for Causal Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00071 - SciFusion: Physics-Guided Compositional Diffusion for Multimodal 3D Scientific Image Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30313 - DashVMC: Real-Time Discrete World Model Control in Geometry Dash Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.40003 - Predictable performance is suboptimal, and what it means for model routing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31428 - TraceForge: Distilling with Your Own Thinking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29680 - How to Teach Large Multimodal Models New Skills Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.08564 - Rethinking SAE Evaluation: An Atomic Interpretable Unit Framework Reveals Hidden Polysemanticity and Redundancy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30474 - RangeNav: Task-Aligned LiDAR Range-Image Pretraining for Robot Navigation Source: arxiv-cs-lg Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.29845 - When to Follow the Teacher: Advantage-Based On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31563 - Automatic Fine-grained Segmentation-assisted Report Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.16623 - Efficient Adjoint Matching for Fine-tuning Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11480 - Learning to Drive in New Cities Without Human Demonstrations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.15891 - Can Entry-Wise Clipping Give Spectral Control of Stochastic Gradients? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.27733 - A Computationally Efficient and Rate-Optimal Algorithm for Adversarial Linear MDPs with (Aggregate) Bandit Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30801 - Beyond Best-of-$k$: Prior-Consistent DAPS for Ambiguous Nonlinear Inverse Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31592 - Giskard : Byzantine Robust and Private Aggregation for Large-Scale Decentralized Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.19129 - Disclosure Begets Disclosure: A Self-Reinforcing Privacy Loop in LLM Agents with Persistent Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28315 - Optimal Clustering of Multi-layer Networks under Mixture Block Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2311.15598 - Probing and Steering for Safety-Relevant Behaviours in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30363 - SABLE: Scalable Affine Bayesian Latent-space Exploration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31495 - Cost-Aware Abstention for LLM-Based IT Ticket Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31657 - Soft Ontology Priors over Latent Concept Posteriors for Weakly Supervised Neuro-Symbolic Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30391 - Prediction Uncertainty Controlled Computer Model Calibration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31163 - Scaling Laws for Safety Probes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30678 - Harmful Responses Are Jailbreak Templates: Transferring Autoregressive Jailbreaks to Diffusion Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31331 - Prompting Strategy Effects Depend on the Judge: A Multilingual Study of LLM-as-a-Judge Robustness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31172 - Diffusion-Based Hypothesis Testing and Change-Point Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.16089 - ReDence: A Hybrid Agentic and Decision-Model Framework for Rapid, Evidence-Grounded Detection of Modern Social Engineering Scams Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30963 - PAIR: Preference-Aligned Intent Retrieval for Premium People Recommendation at LinkedIn Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30941 - Federated Differentially Private Optimization via Low-Rank Preconditioning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31069 - GM-GReFEL: Geometry-Guided Spatiotemporal State-Space Learning for Robust Dynamic Facial Expression Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31140 - MoG-VLM: Efficient Video Anomaly Detection through Motion-Guided Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31478 - Sparse Equation Matching: A Derivative-Free Learning for General-Order Dynamical Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.20072 - Rubric Dropout: A Simple Way to Mitigate Reward Hacking in Rubric-Based RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11669 - Evaluating Type-1 Diabetes Digital Twins by Decision Quality Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30577 - K-Means as the Zero-Temperature Limit of Normalized RBF Assignments: Rates, Trajectories, and Exact Recovery with Entmax Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.04625 - Does More Compute Make Every Adversarial Attack Transferable? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.20310 - Muting Tokens: Exploring Token Sparsification for Efficient Audio Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31235 - Behavioral Consistency in Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07581 - Reliable AI-Assisted Decisions via Selective Auditing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31662 - Direct Inference on Admissible Sets (Diona) Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31526 - Interpreting Model Reasoning through Behavioral Counterfactuals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30630 - Doubly Robust Distributionally Robust Offline Contextual Pricing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30957 - POI Recommendation with LLM-Augmented Multi-Graph Learning and Contrastive Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16407 - Vision Transformers for Estimating Irradiance Using Data Scarce Sky Images Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30940 - Delta N-gram: Forward-Only Continual Writing into a Language Model's Native N-gram Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31125 - Reducing QPU Calls in Variational Quantum Algorithms via Classical Offloading of Gradient Computation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.16361 - Can Entanglement-Induced Feature-Map Designs Improve Projected Quantum Kernels? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31260 - SQuAT: Spherical Lattice Vector Quantization-Aware Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31412 - Moving the Mean Toward the Known Good, Not Beyond It: What Inference-Time Interventions and Weight Consolidation Buy in Open-Ended Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.28886 - One Teacher, Many Views: Reducing Reference Sensitivity in On-Policy Self-Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30880 - Fine-Grained Analysis of Catastrophic Forgetting in Continual Learning via Algorithmic Stability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31551 - PriMa-Causa: Causal Prescriptive Maintenance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31147 - Route-and-Generate: KL-Regularized Router Improvement for Reasoning Routing in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30351 - ATTUNE: Agentic Throughput Tuning for LLM Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17528 - MIG-COW: Transferable Adversarial Attacks on Deepfake Detectors via Gradient Decomposition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30914 - Learning to Incentivise: Using Reinforcement Learning for Sustainable Urban Mobility Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30469 - Reinforcement Learning and Operational Research: A Review of Methodological Integration and Research Directions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24750 - AcoustiPrint: Physics-Guided Neural Design of Manufacturable Acoustic Structures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30411 - NN-Based Transistor Modeling for Ultra-Fast SPICE Simulation and Standard Cell Library Characterization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31024 - Edit, Don't Imitate: Minimal-Edit On-Policy Distillation for Multimodal Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30231 - Is spectral predictability enough? Testing {\Omega}-matching for synthetic pretraining under distribution shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30802 - Track finding and particle identification performance with particle physics foundation models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31180 - PACT: End-to-End Learning of Human Pose, Contacts, and Forces from Video Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00451 - Operator Packages, Proposer Strength, and Construction-Family Plateaus in Office-Scale Verified Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29636 - Identifiability from Stationary Covariance in Linear SDEs with Reciprocal Interactions and Latent Variables Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31310 - Is High Local Accuracy Enough? Geometric Consensus with Support-Adaptive Statistical Personalization for Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31133 - Multi-center Medical Data Mining with FL-Net - A One-stop Shop for Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20650 - Training Mixed-Monotone Neural Networks for Verification Without Set Propagation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30853 - IRAH: Hierarchical Agentic Tree Search for Retrieval Pipeline Optimization Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.30167 - XALIGN: A Human-centric Visual Analytics Approach to Understanding AI Explanations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31015 - Adversarial Reinforcement Learning for Robust Planetary Landing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20252 - Tracing Subliminal Learning Through Pretraining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30884 - Deep Learning for Random Objects in Metric Spaces: Beyond Manifold Assumptions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31328 - LLM-Auction: Generative Auction towards LLM-Native Advertising Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.10551 - GIFT: Gradient Informed Filtering for Distillation Augmented Reasoning RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30796 - Formal-Informal Mathematical Alignment through and beyond Human Annotations Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.31011 - FAIRGate: Agentic Runtime Policy Selection and Verified Repair for Fairer Recommendation Delivery Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.30359 - Deep Search in Real-World Web Environments Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.30181 - When Agentic Retrieval Fails Silently: Framework and Production Evidence from a Creative AI Assistant Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.30423 - FormBench: A Benchmark for Fine-Grained Retrieval in Formulation Patents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.30175 - Compiling Autoregressive LLM Control into Policy-Exact Parallel Inference for Hierarchical RAG Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.30664 - Data-Void Exploits in Web-Searching LLMs Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.30365 - A Memory-Efficient Distributed Algorithm for Approximate Nearest Neighbour Search with Arbitrary Distances Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2405.13795 - Getting a GRIP on Graph-Based Search for Learned Sparse Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.30425 - Better Reasoning, Not Just Bigger Models: A Structure-Grounded Framework for Efficient and Reliable Inference Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.30611 - FlexVDR: Learning to Allocate Matryoshka Representation Budgets for Visual Document Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.30177 - Structure then Query: Enabling Precise Analytical Queries over Unstructured Documents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.13384 - WhisperRec: Latent Reasoning for Efficient Foundation Recommendation Models Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2607.26621 - Automated Enrichment Analysis with GraphRAG: Efficient Multi-Database ORA Extraction and Biological Interpretation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.30710 - A Task-Centric Survey of Long-Document Visual Question Answering: Taxonomy, Evolution, and Future Directions Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.31385 - Xetrieval: Explaining Dense Retrieval through Feature Elicitation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2605.29507 - Bezier-Guided Adaptive Flow for Cross-domain Sequential Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.30825 - Chunk Recomputation under Real Document Revisions: Measuring Update Cost and Retrieval Quality of Fixed, Recursive, and Content-Defined Chunking Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.31019 - The Delayed Countdown Method for Validating Review-Oriented AI Workflows in eDiscovery Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.31311 - Journal Basket: Supporting Cross-Disciplinary Literature Searching and Methodological Transparency Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.30544 - UserArena: Benchmarking Interactive User Simulation for Long-Horizon Shopping Agents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.30932 - The Fusion Tax: A Diagnostic Analysis of When Hybrid Retrieval Hurts Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.30612 - Lychee: Certified Screening of Inverted Lists for High-Recall Vector Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.30697 - SurveyGraph: Generating Academic Surveys via Methods-Entity Knowledge Graphs Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.31317 - Protection Is Not One Event: A Survey of RAG Protection Research by Measured Endpoint Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.30193 - Association between Player Perception and AI Disclosure on Steam: An Exploratory Study Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.30178 - OneLatent: Latent Reasoning for Efficient Foundation Recommendation Models Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.30675 - QProtFuse: Query-Guided Layer Fusion for Retrieval-Augmented Protein Function Prediction Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.30180 - Truthful by Omission: Click Thinning for LLM-Native Advertising Source: arxiv-cs-ds Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2610.30999 - When LLMs Forget What They Believe: Characterizing State Integrity Collapse in Long-Horizon Dialogues Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31314 - ChemBART: Pre-training a Reaction Language Model for Comprehensive Synthesis Planning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.02915 - MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.06473 - Verbalizing Activation Differences with Natural Language Autoencoders Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30934 - Social Life Simulation for Non-Cognitive Skills Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2405.00273 - Beyond Naturalness: Probing Automated Text-To-Speech Evaluators on Linguistically Grounded Dimensions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09930 - Behind Aggregate Scores: What Systematically Varying Arena-Hard's LLM Judge Reveals Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30512 - VEILED-SH: Vulnerability Expression through Indirect Language Evaluation Dataset (Self-Harm) Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26190 - IfcLLM: Natural Language Querying of IFC Models through Complementary Relational and Graph Representations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13236 - Hierarchical Fine-Grained Cross-Modal Alignment via Dynamic Granularity Discovery and Optimal Transport Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30912 - IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30949 - TutorCaseBench: A Case-Grounded Benchmark for Evaluating LLM Tutors in Supporting Students with Challenging Behaviors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30828 - Padding to k: A Minimum Count in the Schema Makes Open-Weight Models Pad Their Extraction Lists Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30997 - Context-Aware Subtitle Translation on CPU: Deployment-Driven Training, Evaluation, and Latency Design Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.09957 - From Perpetrators' Digital Footprints to Behavioral Communities: An Ontology-Driven Framework for Bengali Cyberbullying Analysis--- FULL VERSION Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30885 - Disentangling Robustness and Sycophancy in Multilingual LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30696 - TauIndianBankBench: Procedure-Aware, Action-Oriented Evaluation of Tool-Using Conversational Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30161 - From Structured Records to Patient Narratives: Preserving Clinical Alignment in LLM-Generated Health Summaries Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31467 - Semantic Deception: When Reasoning Models Can't Compute an Addition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.20812 - CARTE: A Benchmark for Mapping Language Model Knowledge Across France Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01995 - Where meanings converge and diverge: Revisiting linguistic relativity across 81 languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30778 - Tracing Hallucinations in LLM Reasoning for UML Class Diagram Generation: An Empirical Taxonomy and Mitigation Study Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30946 - IndoNutriQA: An Indonesian Clinical Nutrition Question Answering Benchmark Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31256 - Beyond Attack Success Rate: Cost-Aware Metric for Evaluating Iterative LLM Jailbreaks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26589 - Memory-Aware Reward Modeling: Learning Human Preferences for LLM Memory Use Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31272 - Protegrity-PII Technical Report Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30518 - RetiJev: Fast and Source-Grounded Ophthalmic Decision Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30947 - IFC-MCQ: Automatically Generating Multiple-Choice Benchmarks for Evaluating LLM Agents on IFC Data Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30533 - Group Relative Policy Optimisation Improves Multilingual Speech Recognition in Low-Resource Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30663 - Sharp Degree Bounds for Putinar Certificates in Terms of the Positivity Margin via Analytic Sums of Squares Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26976 - Memories That Outlive Their Reasons: Dependency-Tethered Memory for Tool-Using LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.25123 - Direct cueing of word identity through word duration: evidence from Mandarin homophones Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30682 - In-Context Learning Beyond Copying: A Training-Time Analysis of Abstractive ICL Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.05743 - How Different, or Different How? Stance Granularity in Viewpoint Selection for Dialog Systems that Engage Users with Alternative Views Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31459 - SyRA-CS: Synthetic-to-Real Adaptation for Code-Switched ASR with Meta-Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31415 - Latent Bridges for Multi-Table Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.28916 - CrisiLangs: A Multilingual Resource for Crisis Warning Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31356 - GoiBERT: Compact Vietnamese Language Models via Two-Stage Knowledge Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30067 - Language Models as Higher-Order Planning Formalizers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.23844 - Through a PRISM, Clearly: Step-Sequence Reasoning for Mistake Recognition in Procedural Videos Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31117 - Overview of CHIP 2026 Shared Task 1: Patient-Specific Phenotype Concept Recognition in Full-Text Biomedical Literature Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29606 - SCOPE: Compiling Natural-Language Policies into Neurosymbolic Predicate Programs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31062 - On the Behavioral Traits of LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32776 - X-pressing Intimacy: Mental Health Disclosure After Twitter Acquisition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30413 - Silicon Samples Match the Answers but Not the Respondents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30900 - Rethinking the Evaluation of LLM Fact-Checkers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30504 - RIFT: KV Cache Compression for Draft Models with Complementary Compressibility Training Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31098 - A Grammar of French Civil Cassation: A Ground-Level Dataset and Tool Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31116 - Abstract Priorities, Concrete Rewards: How Stated Preferences Relate to What People Reward in AI Responses Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30763 - Artificial intelligence is creating a new global linguistic hierarchy Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.12018 - WaxalNet: Benchmarking and Adapting Speech Recognition for Spontaneous Speech in 19 African Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02375 - Cola2: Co-Adaptive Hierarchical Language Modeling with Continuous Semantic Compression and Balanced Discrete Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31305 - Evolving with Open Worlds: Towards Recursive Self-Improvement for Future Forecasting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29784 - An Empirical Study of Recent Large Language Models for Knowledge Graph to Text Generation on Standard Benchmarks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31529 - How Far Can the Gemma 4 Speech Encoder Go Without Changing Its Weights? Saudi and Gulf Arabic Speech Recognition with a Frozen and an Adapter-Augmented Encoder Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28673 - Synthetic-to-Real Code-Switched ASR: A Spontaneous Nepali-English Podcast Benchmark Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30860 - MemPlan: Memory-Conditioned PDDL Planning for Partially Observable Text Environments Source: arxiv-cs-cl Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.30379 - Investigating the Impact of Learner Errors on Social Bias in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29896 - Bilingual Language Models Capture Cross-Linguistic Influence in Second-Language Reading Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31620 - PsyCLIENT: Client Simulation via Conversational Trajectory Modeling for Trainee Practice and Model Evaluation in Mental Health Counseling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.07312 - Low-Bit N-Gram Embeddings for Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31646 - Learning What to Ask for Tomorrow: Active Preference Acquisition for Long-Term Personalized Web Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31107 - ColaBench: Evaluating Memory-Guided Knowledge Acquisition in Personal Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30989 - TORUS: A Unified Closed-Loop Benchmark for Unified Audio Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.28896 - Harm Is Behavioural, Moderation Is Lexical: How Language and Culture Decide Whom Automated Safety Systems Protect and Whom They Silence Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31047 - Mimir: A Sub-2B Hierarchical Reasoning Model Trained on Permissible Data Punches Above Its Weight Class Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.13517 - CiteAnchor: Source-Aware Grounding for Hallucinated Citation Detection and Resolution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30355 - Why Bother Me Again? Benchmarking Personal Agent Memory for Interaction Preferences Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30485 - SIM-UT: A User Simulation based Evaluation Framework for Medical Triage Chatbots Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30412 - How Firm Are AI Models' Ethical Boundaries? A Pay-Stub Editing Test of 15 Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30751 - FusionEval: Benchmarking Model Fusion for Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30162 - Parameter-Efficient Adaptation of Large Language Models to a Low-Resource Agglutinative Language: A Corpus, Datasets, and a Reproducible Benchmark for the Bashkir Language Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31397 - How Well Do Decision Models Transfer to Vietnamese? An Empirical Study of Text Classification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31422 - Pluralistic Alignment in Large Language Models: Objectives, Human References, and Preference Representations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24471 - Meaning Contracts: Local Semantic Geometry in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30715 - Efficient Best-Of-N with Radial Consensus Score Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.12196 - Invisibilization as a Source of Probability Bias in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30785 - Beyond Watching and Searching: Benchmarking Agents for Video-centered Deep Research Reports Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31158 - Can an Agent Debug a Web Corpus? Agentic Auditing of Slovak FineWeb2 Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31636 - TRIAD: Benchmarking Omni-Modal Ambiguity in Multimodal Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30841 - Evaluating Rational Contracting in Natural Language Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.10475 - What the Specification Did Not Say: Specification-Oracle Gaps in Test-Graded Coding-Agent Benchmarks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30635 - TT-SAX: A Two-Track Time Series Symbolization for Natural Language Shape Querying Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30593 - The Geometry of Metaphor: Probing and Steering Metaphor Representations in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31520 - Domain-Specific Constitutional AI: Enhancing Safety in LLM-Powered Mental Health Chatbots Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.16444 - UniGuard: Multi-View Guardrail Learning for Cross-Interface Safety Generalization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30742 - CoWriter: Guiding Methodological and Synergetic Human-LLM Co-Authoring Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31277 - GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38923 - How Far Will They Go? Red-Teaming Online Influence with Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22880 - Kongzi: A Historical Large Language Model with Fact Enhancement Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.09488 - Text-Only LLM Correctors Break Correct Transcripts: A Repair-Damage Analysis of Audio Grounding in ASR Error Correction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30385 - WikiOriginQA: Automated Construction of a QA Dataset with Knowledge Origins for Analyzing Cultural Bias Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30677 - MixJudge: Learning a Language-Queryable Critic for Vocal Mixing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30783 - Hacking Generative Perplexity: Why Unconditional Text Evaluation Needs New Metrics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.08417 - SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26659 - Uncensored Is Not Unbiased: Abliteration Removes Refusals but Not Script-Dependent Bias About Taiwan Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29342 - Interrupting the Loop: Periodic Subject Changes Raise Judged Surprise and Connection in Base Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19893 - Measuring the Verifier's Floor: How Much Apparent Rare-Word Text-to-Speech Error Is ASR Error? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31470 - Measuring Research Progress and Linguistic Inclusion in Low-Resource Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30296 - Predicting Music Valence and Arousal via Textual and Multimodal In-Context Learning in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31202 - ULME: Predictive Coupling for Mutually Reinforcing Embedding and Language Modeling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30705 - ReflectPO: Reflection-Guided Policy Optimization for Long-Horizon LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30933 - Finitely Verifiable Segmentation: Decidability for Every Tokenizer with a Finite-State Verifier Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30168 - How Well Does Mathematical Reasoning Transfer Across Languages in English-Centric LLMs? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.02272 - MENTOR: A Metacognition-Driven Self-Evolution Framework for Uncovering and Mitigating Implicit Domain Risks in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.07107 - What Pairwise Evaluation Misses: Reward Scores across Prompts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31090 - MoVoC: Morphology-Aware Subword Construction for Geez Script Languages Corrected version Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.08812 - TabAgent: Distilling LLM Agent Components into Cheap Classifiers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.16429 - Direct Pass@$k$ Optimization for Thought Pruning: Balancing Quality and Diversity in Test-Time Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31667 - Same Entity, Different Script: Diagnosing Cross-Script Entity Matching Failures in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31407 - A Systematic Comparison of Search Space Complexity and Efficiency for Time-Synchronous End-to-End ASR Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31259 - When Multiple Choices Are Correct: Asymmetric Probability Allocation in Jev and Other Decision Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29217 - A Reality Check of Inference-Time Context Augmentation Methods Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30983 - Investigating Multi-Cultural Value Selection Biases in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31199 - The Imperfective Paradox in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.09373 - From Clinical Judgment to Checkable Rules: Clinician-Led Guardrails for Mental-Health Chatbots Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30690 - A Sociolinguistic Analysis of Automatic Speech Recognition Bias in Newcastle English Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.24549 - Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26045 - Initial Evaluation of Potential Bias in Coverage of Humans in Wikidata Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.22375 - Self-Assessment Reinforcement Learning for Search-State Awareness in Retrieval-Augmented Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30435 - Beyond Prompt and Parser Engineering: Soft-Prompt Tuning for Automated LLM Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.12117 - Interpretive Variation and Discourse Structure in Detecting Enthymemes in Controversial Political Discourse Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30987 - Spectral Smoothing and Spiking Perturbations Reconfigure Capability Profiles and Selective Task Performance in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30676 - Lighthouse: On Building a Trustworthy Digital Assistant for Exploring History with Civil Rights Archives Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30158 - Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30418 - Once a Tree, Always a Tree? Cross-lingual Transfer of Hierarchical Generalization in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30960 - RiskCueBench: Benchmarking Anticipatory Reasoning from Early Risk Cues in Video-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.03369 - How Ground Truth Shapes Retrieval Scores: Evidence-Aware Evaluation of a Retrieval-Augmented Generation System for Breast Lesions Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.31606 - OACap: Caption-Guided Active Observation for Detailed Video Captioning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29327 - Beyond End-to-End Recovery: Towards a Better Understanding of LLM Steganography via Rolewise Decomposition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30516 - FormalASR: End-to-End Spoken Chinese to Formal Text Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19266 - Beyond Recall Saturation: Scaling Hard-Negative Reranker Training for Industrial Legal Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24478 - Towards User Simulators That Stay On Task And Still Sound Natural Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31512 - The Value of Memory in Language Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31303 - Climbing the Ladder: Automating Data Pipelines and Reproducing Baselines in Low-Resource Settings Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30374 - Governed Self-Evolution for Autonomous Investing: A Multi-Agent LLM System with an Invariant Core Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30557 - UniPrompt-CL: Efficient Single-Inference Continual Learning for Medical Image Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.10954 - Enhancing Cross-Grade Generalization in Banana Variety Classification via Hybrid CNN-Transformers and Knowledge Self-Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29008 - A Large-Scale Evaluation of Role-Enhanced Zero-Shot Chain-of-Thought Prompting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29073 - Memory-Centric Continual Learning for AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29357 - How to Use Parallel Data for Multilingual Pretraining Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28838 - Beyond Small Talk: Modeling Disclosure Trajectories in Human-AI Conversation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29413 - DialFork: Going Beyond Factuality to Evaluate Procedural Hallucination in Conversational Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21561 - Unit-Aware Differentially Private Quantum Machine Learning for Clinical and Wearable Health Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28968 - Back Up Before You Regret: Measuring Backup Awareness and Automating Backup in Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28934 - WindINR: Latent-State INR for Fast Local Wind Query and Correction in Complex Terrain Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09511 - Rethinking Synthetic Rationale Supervision for Disease Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10279 - SSMCGM-Stream: A Streaming State-Space Model for Personalized Diabetes Management Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28976 - Making AI-Assisted Claims Independently Challengeable: Publication Authority and a Protocol for Falsifiable Publication Records Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17631 - Theorem prover Arend Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27264 - To Retain or to Adapt? Generalizing Continual Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.05609 - Sculpting the Latent Space: Disentanglement with WAE-MMD and Programmable Priors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.11953 - Lean4Agent: Formal Modeling and Verification for Agent Workflow and Trajectory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.06523 - Mixture-of-Control: State-Aware Fine-Tuning for Transformer-based Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31397 - TrainBridge: Agentic NPU Training Optimization Guided by GPU Compilation Evidence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29171 - Asymmetric On-Policy Distillation Learns In-Context Exploration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30105 - Behavior Beyond Text: Evaluating Refusal Transfer Failure in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28982 - SkillNEO: Non-Elitist Evolutionary Optimization of Agent Skills Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20926 - Beyond source attribution: Address authorship and comparability decisions in an LLM-built scholarly knowledge graph Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28663 - RegoMender: A Multi-agent Framework for Automated Rego Policy Repair Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29456 - Does Centralized Learning Help Embodied Agents Coordinate, and When Can a Tabular Study Tell? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.17454 - SP-HLM: Sparse-Pose-Driven Motion Generation and Whole-Body Control for Humanoid Loco-Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30044 - On the Expressive Power and Limitations of Multi-Layer SSMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.14501 - HGM-Dual: Lineage-Aware Guided Agent Harness Optimization for Long-Horizon Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30042 - DualView: Adaptive Local-Global Fusion for Multi-Hop Document Reranking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18767 - Disentangling generalization and memorization in large language models using chess Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.16823 - CTBench: Evaluating Troubleshooting Capabilities of AI Agents in Realistic Telecom Network Operations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12002 - Algorithmic Reflectivity in Large Language Models: Methodological Study of Linguistic Structure in Mentalization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.08945 - Dual-Channel Contrastive Encoding of Sperm Whale Coda Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29101 - Energy-Based Transfer for Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.16590 - Metamodel-Guided LLM Decoding for Consistent DSL Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29749 - Charts as Epistemic Actions for Experience-Driven Agentic Data Analysis Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.30072 - Beyond Accuracy: Measuring Logical Compliance of Predictive Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.20208 - A Generalisation Signal Need Not Be a Model-Selection Signal Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39099 - Mitigating Query Shortcuts in Chain-of-Thought with Context-Aware Decoding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29518 - When Form Changes but Logic Doesn't: Building Logic-invariant LLMs through Logical Structure Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.25402 - Allocating Indivisible Goods to Strategic Agents: Pure Nash Equilibria and Fairness Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2109.08644 - Mitigating Reward Hacking in Preference Reward Models with Evolving Penalties Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26496 - LLMSeg: Training-Free Text-Prompted Image Segmentation with B-Splines Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29409 - A Strong MoE Is All You Need for Process Supervision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29498 - Distilling Multi-Teacher Scoring Principles for Unsupervised Time Series Anomaly Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29063 - Correlated Failures of AI Approval Monitors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29178 - SkillEval: Learning Interpretable Ability Profiles of LLMs via Cognitive Diagnosis Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28767 - Quant-Arena: Benchmarking LLM Agents for Quantitative Trading Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30113 - AfriBED: a Speech Recognition Bias Evaluation Dataset for Low Resource African Languages Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26821 - 2-Step Agent: How a Bayesian Decision Maker Learns from AI-Decision Support Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.21889 - HyperDrone: Simulation-to-Reality Transfer at Millions of Frames per Second Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28950 - GPU-Accelerated Construction of the Gabriel Graph: Parallelization Strategies and Applications to Large-Margin Classification and Graph-Based Clustering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28759 - WeGR: Towards Unified Generative Retrieval via Behavior-aware Tokenization and Preference Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16979 - ReAPO: Retry-Aware Policy Optimization for Efficient Exploration in LLM Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28770 - PHD-Hand: A Printable Humanoid Dexterous Hand with Linkage-Driven 3-DOA Digits Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29030 - Biological Context Does Not Reliably Improve LLM-Guided Experimental Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.15341 - SYNAPSE: Framework for Neuron Analysis and Perturbation in Sequence Encoding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.08424 - A General Topological Symmetry Index for Critical Orbits In Neural Network Loss Landscapes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28864 - REMORY: Learning Residual Memory for Context Compaction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11287 - Graph-Theoretic Formulation of Hamiltonian and Ground-State Sign Structures in Heisenberg Antiferromagnets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.04943 - Where Should a Stuck Agent Spend Its Next Tokens? Causal Attribution of Inference-Time Resources Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28834 - What Git Does Not Record: Provenance Legibility in Two AI-Assisted Research Repositories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28655 - SWE-DIVE: Multi-Turn Coding Agent Evaluation with Dynamic User Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30047 - AnnoCaseLaw: Legal Annotation Benchmark of Civil Negligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.00128 - SFT Leaves a Reproducible Signature in Activation Geometry: Calibrating Post-Training Interpretability Against Run-to-Run Noise Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17093 - FaultGene: LLM-Assisted Fault-Augmented Test Generation for Hardware-in-the-Loop Validation of Autonomous Driving Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29969 - Machine Unlearning in Low-Dimensional Feature Subspace Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.22456 - Inheritance as an Admission Test for LLM Prompt Merge Operators Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29023 - Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.16511 - FogTTA: Online Test-Time Adaptation for Robust Transformer-based Object Detection in Foggy Weather Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29618 - Where Do LLMs Learn to Recommend AI? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29785 - An interpretable deep learning method for early hepatocellular carcinoma diagnosis on multiphase CT Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29616 - The Reflexivity Threshold: A Phase Transition for Multi-Agent Performative Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29577 - One-Slide Calibration of Pathology Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08944 - Building Auditable AI Text Detectors with Sparse Autoencoders Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30006 - VeriEvolve: Evaluator-First Evolution for Tool-Using Agents Source: arxiv-cs-ai Topic: AI Research (+AI, PostgreSQL) URL: https://arxiv.org/abs/2610.29005 - DualHeads: Reward-tilted few-step diffusion made simple Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28858 - World Models Under Asynchronous Sensor Observations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07299 - RubricOpt: Self-Revision of Semantic Rubrics for Preference Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29491 - Estimating Great Expectations Under Autoregressive Language Models with Potentials Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11399 - Think Harder Where It Matters: Item-Level Adaptive Recursion for Sequential Recommendation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30128 - Black-Box Red-Teaming of Multi-Agent Systems via Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28966 - Alignment via Training Against Probes Without Losing Monitorability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38645 - AtomicRL: Atomic Reinforcement Learning for Long-Horizon Robotic Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30097 - Fine-Tuning Small Reasoning Models for Quantum Field Theory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.18936 - Path-Coupled Bellman Flows for Distributional Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08253 - What Transfers from Text to Vision? Capability Scaling Laws and Transfer Dynamics for VLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00013 - Self-Improving Agents with World Model Predictive Paths Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28945 - Asking a Multimodal LLM Whether Someone Fell: Zero-Shot Screening of Low-Resolution Thermal Video in a Laboratory and an Occupied Home Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29913 - LOADBench: A Large Open Analog Dataset and Benchmark for Machine Learning in IC Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21591 - VLA-Rolling: Fewer Denoising Steps, Better Control via Adaptive Action Reuse Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.25043 - Steering Black-Box Large Language Model Agents with Pitfall Anticipation World Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29139 - Evolutionary BP+OSD Decoding for Low-Latency Quantum Error Correction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.18273 - Accurate and Efficient Multi-Channel Time Series Forecasting via Sparse Attention Mechanism Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18712 - GRAIL: From Saliency to Semantics in Time-Series Explanation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29036 - PRISM: Prompt-Refined In-Context System Modelling for Financial Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2511.14130 - TNODEV: Toolbox for Neural ODE Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16567 - FoveaVLA: Foveation Actions Replace the Wrist Camera in VLAs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20064 - From Atomic to Agentic: Towards Interpretable Evaluation of LLMs' Agentic Mathematical Capabilities Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26950 - Hierarchical Masked Diffusion Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29255 - The End of Consensus Research? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30114 - Learning Altruistic Collaboration in Heterogeneous Multi-Team Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21723 - World of SWECraft: Agent Collaboration at Scale via Simulated Software Worlds Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24061 - Conflicted Records: Typed Adversarial Contracts for Auditable LLM Output Quality Enforcement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29669 - Rethinking Time Series Tokenization from a Frequency Perspective Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28997 - From Weather to Enhanced Weathering: Weather Foundation Models for Carbon Dioxide Removal at Operational Scale Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28973 - Controlling Output Rankings in LLM-Based Search via Generative Engine Optimization Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2602.03608 - TeachBack: Learning to Teach via Bidirectional Preference Optimization for On-Policy Self-Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29167 - Same Answer, Different Reasons: Trace-Level Divergence in Multilingual Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29092 - HiPPT: Physiology-Grounded Wearable PPG Representation Learning via Multi-Scope Text Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14489 - Combining Long-Term Memory and LLMs Comes at a High Cost: From Prompt Injection to Persistent Compromise Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28810 - SciExam for ENSO: Can AI Agents Build Climate Models? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10513 - Adaptive Entangled Neurons in the Brain and Natural Intelligence Simulations for Artificial General Intelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09226 - RoboCap: A New Platform for Egocentric Robot Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07217 - Minimal Witness Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07226 - From Scores to Safe Sets: Exact Safety--Constrained Decoding for Medication Recommendation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29228 - Mitigating Reward Hacking in Realistic Scenarios Through Representation Engineering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29129 - Protecting De-identified Documents from Search-based Linkage Attacks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.06383 - Our Own Jev: Typed Decisions in One Forward Pass, from an In-House Judge to Open LoRA Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29052 - When Do Gaussian Priors Fail? A Latent Geometry Investigation of RL Fine-Tuning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28849 - Multimodal Embodied Agents: A Unified Capability-centric Perspective from Computer-Use to Robot-Use Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30108 - AgriVLN: Vision-and-Language Navigation for Agricultural Robots Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.07406 - Privacy in Context Is Being Overlooked in the Age of General-Purpose LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29925 - Agent AI Zarz\k{a}dzaj\k{a}cy Sieci\k{a} Open RAN Zorientowana na U\.zytkownika Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28860 - Let It Be Simple: One-Step Action Generation for Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05737 - Evolving Self-tuning Benchmarks for Long-Horizon Tool Use Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27307 - SpatialBrain: Spatial Intelligence Growing from Experience Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29317 - Is a 9B Decision Foundation Model Needed for Symptom-to-Disease Classification? Fine-Tuning Clef-Flash Against TF-IDF Baselines Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15029 - Graph Topology Meets Energy-Driven Pathfinding: Preserving Contextual Consistency in Retrieval-Augmented Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29933 - YingLan: A Multimodal Ocean Foundation Model for Unified Representation Learning from Heterogeneous Observations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29313 - Remote Rowhammer Attack using Adversarial Observations on Federated Learning Clients Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.06335 - Speedrunning Relational Foundation Model Pretraining Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28855 - Brittle by Design? Multi-Scenario Reinforcement Learning for Robust Mission Coordination in Systems of Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28818 - Adaptive auditing of AI systems with anytime-valid guarantees Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07002 - Interpretable but Fragile? Robustness of Concept Bottlenecks under Geometric-Semantic Perturbations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38625 - Which Differences Matter? Controlled Tests of Rule Transfer, Joint Reliability, and Information Use in Decision Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30045 - Incentivizing Tool-Use Reinforcement Learning for Post-Arrival Emergency Care Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21449 - It Takes a Forum: Resources & Stakeholders Sustaining the Online Synthetic Non-Consensual Intimate Image Creation Ecosystem Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.12190 - Who Verifies the Builder? Toward Independent Assurance for Agent-Produced Software Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28667 - Improved Training of Strong Stochastic Flow Maps Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29605 - Broadband Mid-Wave Infrared Imaging Enabled by All-Silicon Hyperboloid Metalens Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29841 - The Stepwise Informativeness Assumption: When Do Entropy Dynamics Track Reasoning Correctness in LLMs? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.06192 - Deep Reasoning in General Purpose Agents via Structured Meta-Cognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11388 - DiffResearch: Accelerating Deep Research with Diffusion Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28909 - RL-IF: Tracking Non-local Training Data Influence for Online Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28883 - inr2action: Encoding Robot Episodes as Neural Implicit Representations for Recall and Action Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28882 - OpenMAP-HIE: Pathology Informed Score-based Diffusion Model for Unsupervised Neonatal Hypoxic-Ischemic Encephalopathy Lesion Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29322 - To Manipulate or Not: Opinion Dynamics in LLM Interactions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28875 - Differentially Private Sparse Reward Estimation with Preference Feedback Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30099 - ChronoSynth: Constraint-Aware Question Synthesis over Temporal Knowledge Graphs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29339 - Huayu-Global: Skillful real-time quasi-global precipitation retrieval Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29213 - Can synthetic data reproduce real-world findings in epidemiology? A replication study using adversarial random forests Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.14936 - Bio-Inspired Auditory Processing: Coupling Parallel Resonate-and-Fire Dynamics with Ternary Recurrent Networks for Speech Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29720 - EHRAdapt: Adapting Pretrained Language Models to Electronic Health Records with Semantic Priors for Rare Clinical Events Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34007 - AFFORD2ACT: How Far Can Sparse Keypoints Go for Robot Manipulation? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.01433 - AgentMonopoly: Behavioral Patterns and Persona Control in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29330 - Latent space configuration for neural network finetuning, fast ranking, and embedding dimensionality reduction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29295 - Robust Soft Skill Adaptation via Behavioral Localization in Tool-Using Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30041 - Simply Logical -- The First Three Decades Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28912 - UserSWE: Evaluating Coding Agents in Multi-Turn Conversations with Dynamic Users Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29822 - Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28763 - Stochastic Pruning of the DPO Computation Graph: 1.4x Faster Training and Lower Peak Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29538 - Recursive Self-Improvement on a Budget: Scoring Code Edits Before They Run Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29121 - NormTune: Norm-Guided Parameter-Efficient Fine-Tuning for Reasoning-Intensive Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29134 - Scaling Verifiable Environments for Long-horizon Work Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04906 - Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07985 - Self-organizing reinforcement learning: a learner-free swarm approaches the explore-exploit optimum Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.25113 - Interaction-Gated Time-Frequency Learning for Parameter-Efficient PPG-Based Heart Rate Estimation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28693 - Scaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual Worlds Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28698 - An auditable conditional-strategy framework for open-ended decision-making in complex lung cancer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29381 - Retrieval Augmented Generation Compositionality Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29722 - On the Complementarity of Quantum and Classical Features: Adaptive Hybrid Quantum-Classical Feature Fusion for Breast Cancer Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.22903 - Environment Duels: A Microcosm of LLM Co-Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30116 - PhysiCalWorld: In-Context Physics Calibration for World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30125 - Beyond Binary Labels: Diagnostic Evaluation of LLM Safety with Prompt-Level Rubrics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29225 - Solving Go under Positional Superko: Sound Proof Transfer and New Board Values Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29414 - Resuming Vision-Language Inference across Onboard Interruptions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29183 - SLoSa: Small, Low-Power, and Safe Foundation Models for Robotic Task Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28955 - FutureLens: Longitudinal Topic Patterns in Scholarly Text and Future-Work References Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28656 - Robot Generalization Beyond Volume: The Diversity Path via Zero-Shot Capabilities Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29829 - RuleSmith: Multi-Agent LLMs for Automated Game Balancing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.06232 - VerifierBench: Benchmarking the Generation of Executable Verifiers for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28679 - Proposals and challenges for zero-knowledge verification of frontier AI training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05433 - Towards Realistic Models of Change: A Causal Perspective on Decision-Making and Dynamical Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28803 - GRAFT: Restoring the Missing Sampling Interface in Continuous Diffusion Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29136 - Analyzing and Improving Chain-of-Thought Monitorability Through Information Theory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.18297 - InfoQuant: Shaping Activation Distributions for Low-Bit LLM Quantization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26175 - Spatiotemporal Reconstruction of Global Radiation from Sparse Sensor Sequences Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.12045 - SAKURA: Serving Attention Key-Value State Under Rate Adaptation for Private Image Editing on Phones Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29733 - HealthMamba: An Uncertainty-aware Spatiotemporal Graph State Space Model for Effective and Reliable Healthcare Facility Visit Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.05286 - ArcFlow: Training Flow Policies for Multiple Solver Budgets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28788 - TrustAgent-RFF: Agentic Diagnostic Planning for Reliable RF Fingerprinting under Domain Shift Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24930 - CountVideoBench: A Benchmark to Evaluate Prediction Biases on the Object Counting task by Video-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28356 - S$^2$-MAS: A Society-Scale Multi-Agent Simulation Framework with 500 Million Household Persona Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27746 - PerMIT: Securing Persistent Memory for LLM Agents via Machine-Checked Integrity Theorems and Scalable Community Trust Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28987 - Why is AI-generated language so hard to understand? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29162 - rMuscle: Robotic Muscle Memory for Efficient Vision-Language-Action Model Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19104 - EyeVQA: Benchmarking Ophthalmic Vision-Language Models from Recognition to Spatial Grounding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32352 - A rubric landscape for evaluating clinical reasoning in large language models: what exists, what is missing, and what needs to be combined Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01938 - Automatic Differentiation with Constraints in Forward and Inverse Problems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27888 - Scaling Multilingual Pretraining of Pixel Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29681 - Every Part Has Its Role: Part-of-Speech Effects in LLM Post-Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29843 - RocketAgent: A Long-Horizon Engineering Agent for Multidisciplinary Design of Liquid-Rocket Thrust Chambers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06044 - Block Diffusion for Longitudinal EHR: Accuracy, Efficiency, and Representation Trade-offs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29533 - DeepLook: Uncertainty-Guided Branching with Lookahead Confidence for Efficient Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22602 - OwlSight: A Panoramic Monitor for Chain-of-Thought Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23670 - Unintended Side Effects of Value Training in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29922 - SUDP: Secret-Use Delegation Protocol for Agentic Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.24920 - The CIDOC CRM Periodic Table: Documentation You Can Test to Support the Adoption of Scientific Research Ontologies for the Humanities Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28650 - Replayable Financial Agents: A Determinism-Faithfulness Assurance Harness for Tool-Using LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.15322 - From AI-Free Gates to AI-First Work: How Engineering Students in India Navigate University Education and Campus Placements Without AI Guidelines Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29140 - Robot Learning with Visual Predicted Force Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04741 - ProMORNA: An End-to-End Generative Framework for Full-Length mRNA Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.01513 - Long-horizon autoformalization of a core theorem underlying MIP* = RE Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19814 - AI-Based End-to-End Automotive Design and Software Development for SDVs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29160 - HybridResearcher: Bridging the Structured-Unstructured Boundary for Deep Research Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24899 - MCLR: Improving Conditional Modeling via Inter-Class Likelihood-Ratio Maximization and Unifying Classifier-Free Guidance with Alignment Objectives Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.22364 - MERP: A Latent-Bottleneck Framework for Robust Multi-Modal Multi-Label Emotion Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29430 - Does Every Instance Count Equally? Order Effects in LLM Multi-Instance Processing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29057 - Agentic Music Post-Production Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29093 - BatchBench: Benchmarking AI Robustness to Batch Effects and Domain Shift in Biomedical Images - A JUMP Cell Painting Leaderboard Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30104 - ToM2Vec: Continuous Theory-of-Mind Tokens for Multi-Agent Coordination Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29934 - S-EDL: Eliciting Self-Evidence from Sequence Likelihoods for Semantic Calibration of LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29832 - Act on Your Behalf, Beyond Your Authorization: Benchmarking LLM Agent Authorization Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27548 - PreCoMem: Predictive Cognitive Memory for Self-Evolving Long-Term Dialogue Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29467 - Every Alarm Has a Cause: An Open Generator of Telecom Alarm Storms with Exact Root Causes, Bound to NORIA-O, RFC 8632 and TMF642 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30004 - MOSAIC: An Omni-Modal Benchmark for Long-Term Memory and Cross-Modal Reasoning in Conversational Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29249 - Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architectures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.25045 - PaceVLA: Adaptive Temporal Action Quantization in Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.25961 - Learning Checklists to Reduce Lottery Effects in Scientific Peer Review Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28666 - ReSeg: Retraining-free segmentation of abdominal organs via generalizable semantic representation learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29090 - LLM-Based Exogenous World Modeling for Dynamic Scheduling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29308 - What the Author Wrote, What the Agent Reads: Silent Cue Loss in Enterprise Document Ingestion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30026 - MemoryTax: The Bitter Lesson of Agent Memory Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.29823 - Context-Augmented, Session-Calibrated Blood Pressure Tracking from Photoplethysmography Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29091 - Zero-Cost Detection of Fabricated Citations: A Staged Heuristic Approach for Computing Dissertation Assessment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28649 - DrugReason: Dynamic Multi-View Reasoning over Knowledge Graph and Language Evidence for Drug Repurposing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06779 - Harness Scaling for Generalizable Agentic Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29458 - DFAH-Bench: What Agreement Leaves Unmeasured in Financial Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.20491 - From Augmentation to Synthetic Evidence: Evaluating Generated Chest Radiographs at Dataset Intake Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29152 - Agent Behavior Maps: Locating Agents by What They Would Do, Without Running Them Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30014 - CrashGym: Measuring the Decision Value of Experimentation for LLM Agents in Counterfactual Market Crashes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29245 - First Passage Attention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22714 - D-Skill: Distilling Teacher Knowledge through Agent Skills Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28914 - GuideEvolve: Self-Evolving Agent Framework with Expert Guidance and 3Ts Mechanisms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30017 - AI-driven Prices for Externalities and Sustainability in Production Markets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2106.06060 - Flat-RLVR: Sharpness-Aware Reinforcement Learning with Verifiable Rewards for Reasoning Capacity in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29281 - From Theory to Decision Rule: Calibrating the Noisy-Label Crossover for Vision-Language Model Weak Supervision Across Three Medical-Imaging Benchmarks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24771 - Second Thoughts: Exploring and Planning through Comparative Imagination in World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28779 - When Agent Evaluation Becomes Unreliable: An Empirical Study of Oracle Failures and Configuration-Dependent Measurement in an LLM Agent Benchmark Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16067 - CompLit: Scientific Literature Search Benchmarks Must Cover Implicit, Cumulative, and Unmet Needs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28658 - From Association to Decision Value: Testing Paired Instruction Dependence for VLA Corpus Selection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29646 - ARCANA: A Benchmark for Abstraction and Analogical Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29271 - Your Benchmark Is an Empirical Measure Over Difficulty Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29927 - Where Does Timbre Hide? Localizing Speaker Information in Speech Signals Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29150 - CPR for LLMs: Critical-Point Routing against Catastrophic Forgetting in Domain Adaptation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30158 - HarnessPAI: An Evolving Harness for Physical AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29166 - Conditional Flow Models Convert Epistemic Uncertainty into Apparent Aleatoric Variance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29172 - OmniSimulator: Aligning Small Language Models for Authentic Heterogeneous Behavior Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29472 - Are Joint-Embedding Predictive Objectives Effective for Longitudinal EHRs? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29528 - Synthesis and Verification of Register Automata over Data Sequences (Technical Report) Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.19100 - Model Capacity Frontier: A Development Framework for LLM-Supported Social Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24168 - Events, Not Pixels: Where World Models Get the Return Wrong Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29435 - On the Role of Citations in Preference Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21376 - Can Quantum Layers offer Performance and Security Advantages in Vision-Language Models? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28964 - ASPIRE: Agentic /Skills Discovery for Robotics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.00272 - Toward Recursive Self-Improvement in Physical AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29677 - Language Models Give Group-Linked Fields the Wrong Weight Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22887 - When Are We Near Nash? Certifying Solutions in General-Sum Games Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29300 - Feedback World Model Enables Precise Guidance of Diffusion Policy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.15705 - Hidden Messages Between Diffusion Language Model Agents: Causal Evidence for Latent Communication Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28905 - JaxMARL-BC: Multi-Agent Reinforcement Learning for Macroeconomic Modelling, in Seconds Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28907 - AssetForge: Asset-Augmented Task Synthesis for Business Automation Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18330 - Automated Materials Data and Knowledge Extraction using Machine Learning and Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29895 - LaVGuard: Selective Decoding for Contextual Value Drift Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29135 - Reinforcement learning for hardware acceleration and system-level optimization on FPGA and integrated-circuit platforms: A survey Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28699 - STAR-XPC: Set Transformer for Estimating X-ray Transmission in Polymer Composites Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28709 - LTEM: LLM-Friendly Table-Enhanced Markdown for Table Understanding and Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29188 - Forging More Tasks into Better Harnesses: Agentic Harness Evolution via Successive Scale Racing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28815 - Data-Free Finite-Volume Convolutional Neural Networks for Steady Compressible Euler Flow around a Circular Cylinder Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.01001 - Agentic Video Understanding: A Survey Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31713 - Optimized Conformal Selection: Powerful Selective Inference After Data-Dependent Score Construction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.17983 - An Eco-Friendly Tourism Trip Planner Driven by Z-Number Uncertainty: Evidence from Baku, Dubai, Abu Dhabi, Tashkent, and Istanbul Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29120 - Reading the Mask: Descriptor-Grounded BI-RADS Rationale Generation for Breast MRI Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29358 - Flout at Your Own Risk: LLMs Struggle with Pragmatic Cooperativity Under Epistemic Asymmetry Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.11053 - Predictor-Guided Latent Space Codon Optimization for Maximizing Protein Expression Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03098 - TIDE: Tree-Induced Fine-Grained Diagnostic Evaluation from Model Behaviors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29985 - EHRNote-ChatQA: A Benchmark for Evidence-Grounded Multi-Turn Clinical Question Answering over Longitudinal Discharge Summaries Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.15735 - RayCo4D: Ray-Conditioned Continuous Motion Model for Monocular 4D Dynamic Reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28351 - The Alien Space of Science: Sampling Coherent but Cognitively Unavailable Research Directions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.01092 - Parallel AI Agent Collaboration as Graph-Structured Distributed Block Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30074 - Closing the Sim-to-Real Gap: An Evaluation Framework for Autonomous Cyber Defense Configuration of Commercial EDR Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.08168 - REFLEX: RNA Ensemble Generation via Flexibility-Calibrated Stochastic Bridge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26261 - Lineage-Aware Search Control for LLM-Based Evolutionary Factor Mining Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29663 - GRAM: Group-wise Rank-Aware Model Merging via Subspace Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29110 - Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14590 - Structure-Aware Message Passing on Petri Nets through Directed Walks and Incidence Diffusion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29725 - Beyond Policy Discrepancy: Capability-Aware Multi-Teacher On-Policy Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26950 - SANE: Automated Scorer-Specific Metamorphic Testing for LLM Judges Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28886 - AdaGuard: An Adaptive Guard Model with User-defined Policies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34241 - UNIVERS: Learning UNIversal Voxel-wise Embedding via Randomized Synthesis for generalizable one-shot landmark localization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29098 - Metropolis-Scale Resilient and Trustworthy Traffic Flow Inference Using Multi-Source Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25004 - VHDLBench: Benchmarking and Fine-Tuning Large Language Models for VHDL-Based Chip Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28676 - Quantifying Symptom Causality in Clinical Decision Making: An Exploration Using CausaLM Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.19394 - Operon: Incremental Construction of Ragged Data via Named Dimensions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.16080 - StyleStream 2.0: Fast and Controllable Streaming Voice Style Conversion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28940 - Offline Apprenticeship Learning for Human-Centric Environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28716 - CAVE: A Structured Credit Assignment Approach for Fragmented Visual Evidence Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16416 - Generative Modeling via Nonlinear Schr\"odinger Bridges and Branching Diffusions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29476 - Rethinking Agentic Model Orchestration for Time Series Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29504 - A Small Model Asks Better: Fine-Tuning Query Clarification for Retrieval-Augmented Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28686 - Align, Don't Blend: Orthogonal Supervision Disentanglement As the Key to Generalizable AI-Generated Image Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.06746 - SpecEvo: Speculative Evolution with Large Language Models for Cost-Efficient Scientific Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28706 - Stationarity Constraints Improve Both Energies and Densities of Machine-Learned Exchange-Correlation Functionals Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30022 - GenXR-Bench: Benchmarking Coding Agents for Interactive XR Development Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29014 - Commit or Abstain? System One Decision Models, LLMs, and Missing Legal Authority Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29961 - Exploring Jailbreak Vulnerability Across Depth-Based Dynamic Inference in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15207 - Same Probabilities, Different Advice: Gain-Loss Framing Effects in High-Stakes LLM Decision Support Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29294 - Generative Artificial Intelligence for Internet of Things Computing: A Systematic Survey Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.07635 - Effects of Theory of Mind and Prosocial Beliefs on Steering Human-Aligned Behaviors of LLMs in Ultimatum Games Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.24255 - Real PMIDs, Wrong Papers: Harness Design for Biomedical Claim-Verification Agents Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.29812 - From Reasoning to Action: Benchmarking Frontier AI Models on LIBERO-10 Robot Manipulation Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30051 - PAUSE: Search-Free Steering of Coding Agents Before Their First Source-Code Edit Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29870 - Parallel Thinking for Large Language Model with Path Diversity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29501 - MADDIE: Multi-Agent Drug Discovery Engine Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16975 - Quality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.07121 - Generalization and Scaling Laws for Mixture-of-Experts Transformers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.09175 - Conditional Optimal Bridge for Riemannian Activation Steering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.10517 - HumanCentric-Scenes-AI: A Human-Curated Multimodal Dataset of AI-Generated Human-Centric Scenes Across Surveillance, Occupational Portraits, AI-Edited Images, and Short-Form Video Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29045 - Keeping Time vs. Understanding Time: Neither Alone Explains Temporal Reasoning in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29507 - CoSec: Benchmarking Agent Security in Communities Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34790 - Learning What to Remember: Resource-Efficient Self-Improvement for Lifelong Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26453 - FactReview: Evidence-Grounded Peer Review with Execution-Based Claim Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.04074 - Quantum-Inspired Optimization Process for Data Imputation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.04841 - An Evidence-Driven Multi-Agent Compound AI System for Head and Neck Proton Radiotherapy Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29010 - AgentPolicyForge: From Executable Environments to Policy Benchmarks and Adaptive Guards Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28989 - DiaLong: Benchmarking Reminiscence in Long-Context Dialogues Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.25463 - AutoFraming: Synthesizing Dynamic Frames of C Code with LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29046 - Value-Rectified Distillation for Flow-based Offline Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29075 - StochIKM: Automated High-Fidelity Reconstruction of Individual Patient Data from Published Kaplan-Meier Curves Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29122 - Formalizing Cooperation and Competition: An AI-Assisted Mathematical Addendum to a 2018 Planning Thesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29637 - Telling FIBS: Probes Effectively Detect Sabotage and Catch Unverbalized Deception Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12445 - From Prompts to Posteriors: Can LLM Agents Perform Bayesian Inference in Context? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29331 - CALLIOPE: Private Insights into AI Use, Without Embeddings Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28797 - Fig: Automated Multiagent Behavior Elicitor Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28891 - HiddenLens: A Multi-Layer LLM Framework for Detecting and Resolving Hidden Assumptions in Software Requirements Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29996 - Causal Discovery via Transformed Low-Rank Quantile Surfaces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.16931 - StructLens: A Structural Lens for Language Models via Maximum Spanning Trees Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.03328 - Just Respect the Semantics: Image-Token Compression via Pre-LLM Semantic Variable-Resolution Tokenization and In-LLM Relevance Pruning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18690 - RubRIX: Rubric-Driven Risk Mitigation in Caregiver-AI Interactions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.13235 - Pessimistic Latent Task-aware Optimization for Robust Offline Meta-Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15428 - An Exact 93-Move Solution to a Nonlocal Crystal-Exchange Puzzle Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29493 - Learning to Interfere in Non-Orthogonal Multiple-Access Joint Source-Channel Coding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.03690 - MICA: Multi-granularity Intertemporal Credit Assignment for Long-Horizon Emotional Support Dialogue Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.06194 - CulturalRiddles: A Multicultural Benchmark of Riddles Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29968 - ORSMT: Unleashing the Potential of Satisfiability Modulo Theories for Semantic Verification and Repair in LLM-Based Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29145 - CRAB: Cuboid-based Representation for As-built BIM from Point Clouds Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29257 - COMET: A coordinated multi-layer runtime monitoring framework for human-supervised AI-enabled safety systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29816 - Decision language models as affordable and rapid alternatives to LLM judges of clinical generative AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28826 - How Representational Priors Shape Generalization in World Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29168 - Sketch2Sim: an end-to-end modular framework for hand-drawn circuit analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28836 - From Fuzzy to Exact: The Halo Architecture for Infinite-Depth Reasoning via Rational Arithmetic Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.18702 - A Theoretical Analysis of Why Masked Diffusion Models Mitigate the Reversal Curse Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02133 ## Community - Quick Study Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Oct/23/quick-study-painter/ - Introducing Kimi K3.1 Pro Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Oct/23/kimi-k31-pro/ - Igor Suhorukov: A knowledge base without a second database: Oxigraph’s SPARQL in PostgreSQL 19 Source: planet-postgresql Topic: PostgreSQL (+AI) URL: https://postgr.es/p/9zI - Securing our frontier model training environment Source: hacker-news Topic: General (+AI) URL: https://openai.com/index/securing-our-frontier-model-training-environment/ - The Signal Chats That Cost OpenAI Researchers Their Jobs Source: hacker-news Topic: General (+AI) URL: https://www.wsj.com/tech/ai/the-signal-chats-that-cost-openai-researchers-their-jobs-594c5853 - An alignment assessment of the UK AISI cybertesting incident Source: hacker-news Topic: General (+AI) URL: https://www.anthropic.com/research/alignment-assessment-ukaisi - Next-Concept Modeling: Fast, Parallel Coarse-to-Fine Text Generation Source: lobsters Topic: General (+AI) URL: https://arxiv.org/abs/2610.14162 - Swedish government offices to ban ChatGPT and Claude Source: hacker-news Topic: General (+AI) URL: https://www.sverigesradio.se/artikel/chat-gpt-och-claude-forbjuder-regeringskansliet - The rise and fall of Jev hype Source: hacker-news Topic: General (+AI) URL: https://blog.alexewerlof.com/p/rise-and-fall-of-jev-eval-hype-vs-llm ## Media - What happens to your AI agent when you close your lid? Source: youtube-googlecloud Topic: AWS (+AI, Cloud, General) URL: https://www.youtube.com/shorts/Rv97mm8CZkw - Do more with fewer tokens: Gemini Smart Routing Source: youtube-googlecloud Topic: AWS (+AI, Cloud, General) URL: https://www.youtube.com/shorts/BQgm_qLll3A - Llama: Local AI on Your Mac Source: youtube-huggingface Topic: Hugging Face (+AI) URL: https://www.youtube.com/watch?v=w6dSNCg9I5k