TILens Daily Edition 2026-10-09 Filters: topic=ai-research, github=hidden Stats: 927 articles, 6 sources, 923 research papers Top topics: AI Research, AI, Information Retrieval ## News - 😺 Claude Dashboards + Motion launched Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/claude-dashboards-motion-launched/ - The Future of Coding Agents, According to Microsoft Research: How to Actually Trust AI-Written Code Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/explainer-articles/ai-coding-agents-verification-engineering-alex-lavaee/ - Anthropic Says You Can't Abuse Claude. But Can AI Be Harmed? Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/anthropic-claude-abuse-policy-ai-welfare/ - Could AI Beat Scientists to Their Own Research? Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/could-ai-beat-scientists-to-their-own-research/ ## Research - Can TypeSafe's Jev Make AI Agents Safer Without Another LLM? Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/can-typesafes-jev-make-ai-agents-safer-without-another-llm/ - Where Does the Money Go Across Long-Running Coding Agents? Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/where-does-the-money-go-across-long-running-coding-agents/ - Build Your First AI Agent with One Tool Call Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/build-your-first-ai-agent-with-one-tool-call/ - Stop Using AI. Start Hiring It. Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/stop-using-ai-start-hiring-it/ - Remember to Forget: Gated Adaptive Positional Encoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10414 - Selective Listening: Mechanism-Guided Control of Audio Influence in Large Audio-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11196 - Spectral Weight Decay: Inducing Low-Rank Structure in Neural Network Weights Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11730 - DEX: Digit-Level Early Exit for Energy-Efficient MSDF Neural Network Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11748 - PageWeaver: KV-Guided Query Unions for Sparse Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11201 - Puffin: Probabilistic Learning of Spatial Detail From Coarse Observations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11914 - A Balanced Data Diet: Addressing the Exploration Bottleneck in Mega-Scale RL for Robot Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12465 - Visible Reasoning Is Not a Universal Optimizer: Persona- and Thinking-Dependent Effects in Analytics Code Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10639 - When Routing Reveals Membership: Privacy Leakage from MoE Router Telemetry Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10616 - Controlled Acquisition and Abstention in Three-Channel Score Conflicts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10808 - Optimally Pacing Budget Spending and Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11074 - Heterogeneous-Modal Unsupervised Domain Adaptation via Latent Space Bridging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.15971 - Examining Social Attribution in LLM Reasoning: A Theory-Guided Probing Methodology Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12022 - The Ball and the Box: Two Geometries of Computation in Superposition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11744 - Parameter-Free Zeroth-Order Optimization with Ellipsoidal Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38561 - Credal Machine Learning for Risk-Averse Decision Making Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12115 - The Red Queen G\"odel Machine: Co-Evolving Agents and Their Evaluators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.26294 - StoreBench: A Live-Commerce Environment for Evaluating and Training Autonomous Operator Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10942 - Virtual Smart Metering in District Heating Networks via Heterogeneous Spatial-Temporal Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.10166 - Higher-Order Morphology Priors for Quadruped Reinforcement Learning Under Actuator Degradation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10934 - Minimax Gaussian Mechanisms for Continual Machine Unlearning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11628 - CausalDreamer: Learning Predictive World Models with Latent Disentanglement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12016 - Graphons of Line Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2409.01656 - Rehearse Everything, Remember Nothing: Attic-KV Rehearses What Will Be Read Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12133 - Clarify, Then Focus: Statement Normalization for Conversation Analytics at Scale Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10758 - Closing the Horizon Gap in Policy Optimization for Adversarial MDPs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12362 - AgentHorizon: Evaluating Agentic Judges for Long-Horizon Computer-Use Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11050 - Verification with Transfer: Exact Information Frontiers and Their Price in Calls Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12211 - Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11794 - Read What Matters: Query-Adaptive Quantization for KV Caches Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11245 - Universality and Convergence of Generative Flows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05490 - Bilevel optimization for data-driven learning of Koopman embeddings using kernel-based autoencoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12370 - Towards Scalable Meta-Learning of near-optimal Interpretable Models via Synthetic Model Generations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.04000 - One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.13892 - Could LLM Watermark Detection be Public? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12106 - DivMoE: Fine-Grained MoE Upcycling via Cross-Domain Expert Composition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11317 - InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.13878 - S4oP: Operator-level Pruning of Structured State Space Models for Resource-Constrained Devices Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18096 - Toward Optimal Regret in Adversarial MDPs with Stochastic Hard Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12153 - MemCalib: Benchmarking and Optimizing Memory Use in LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24259 - Machine Learning Optimization for Enhanced OS Fingerprinting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11133 - Uncovering and Fixing Collider Bias in Bayesian PINNs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11737 - SPD-MetaFormer is what you need for small-data brain decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10952 - Test-Time Compute for Tabular Foundation Models: Mechanisms, Gains, and Limits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12005 - Fast Adversarial Attacks with Gradient Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.14868 - From a Prompt to Repertoires: Evolving Functional REpertoires Enable LLM Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11373 - ASPIRE: Saddle-Point Discovery through Set Prediction and Physical Refinement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10969 - SciTBERT: A family of chronologically consistent language models for scientific and technological language processing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12207 - Strategic Governance of AI Models in Earth Science Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10560 - Stability-Plasticity Balance via Singular-Vector Selection in LLM Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11076 - Softmax Attention on Gaussian Mixtures: Linear When It Can, Selective When It Must Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11798 - Invariant-Measure Reasoners: Stable Representations for Latent Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10996 - Early Signatures of Memorization in Diffusion Models via Basin Geometry and Cyclic Denoising Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11670 - Beyond Action Entropy: Quotient-Space Exploration for Genome-Scale Metabolic Model Repair Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11627 - Prior or Feedback? What an LLM Uses When Adapting Neural Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12325 - Label-free steering: Compressing test-time reinforcement learning into bias-only subspaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18587 - ELF-REG: Scaling Continuous Diffusion Language Models to Reasoning Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29102 - Can a System-One LLM Perform Knowledge Tracing When Few or No Learners Are Logged? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11135 - Estimating great expectations under autoregressive language models with potentials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11399 - Class Machine Unlearning for Complex Data via Concepts Inference and Data Poisoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2405.15662 - Enabling Preference-driven Unlearning in Few-step Distilled Text-to-Image Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10859 - Just for FUNS: LLM-Guided Spatio-Temporal Graph Node Generation for Forecasting Unobserved Node States Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08818 - GRPODropout: Less is More for Online Reinforcement Learning Rollouts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11854 - Keeping Score: Adaptive, Tuning-Free Loss Weighting for Score-Augmented Neural Ratio Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12118 - Overcoming Prior Barriers: Supervised Fine-Tuning under Long-Tail Distribution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12345 - V-CoLA: Vision Token Compression with Linear Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11251 - When Lower Reconstruction Loss Hurts: Distributionally Robust Refinement for Low-Bit LLM Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11226 - FedAlphaEdit: Null-Space-Aligned Merging for Collaborative Knowledge Editing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11033 - ReCodeAgent: A Multi-agent Workflow for Language-Agnostic Translation and Validation of Large-Scale Repositories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.07341 - Leakage-Controlled Multimodal Learning for Diagnosis and Progression Prediction in Alzheimer's Disease Research Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10648 - Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.16204 - MC-TRCM: Observation-Aware Recursive Fusion for Incomplete Mobile and Wearable Mental-Health Feature Views Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11408 - Gen-PINNs: Generative Adversarial Physics Informed Neural Networks for solving partial differential equations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10897 - Budgeted Multi-Source Counterfactual Annotation for Off-Policy Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10974 - Transfer Learning of Multiobjective Indirect Low-Thrust Trajectories Using Diffusion Models and Markov Chain Monte Carlo Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09125 - Noise Your Prompt: Noising Conditioning Tokens in Continuous Diffusion Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09145 - LIME: Link-based User-item Interaction Modeling with Decoupled XOR Attention for Efficient Test Time Scaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.18239 - Policy Alignment: New Signals for Membership Auditing in On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11423 - Origins of Universal Machine Learning Force-Field Errors in Multicomponent Materials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09837 - Implementation Guidelines for Data Quality Metrics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10919 - Task-Centric Personalized Federated Fine-Tuning of Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.00050 - HAND: A Biologically-Inspired Activation Function that Improves Generalisation and Sample Efficiency in Image Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11534 - RAGenome: Scaling Retrieval-Based Genomic Language Models to Long Contexts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11761 - Dissecting Representation Structure in Vision Transformers: A Rigorous Architectural Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11205 - Omni-Diffusion-Distill: Few-Step Distillation of Unified Multimodal Diffusion Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10990 - Neuro-Memory Fuzzy Inference System for Mimicking Human-like Car Following Behavior Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11252 - Conditional Residual Prediction: Improving Autoregressive Video Diffusion without a Bidirectional Teacher Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11479 - Prospective Prediction of OOD Degradation from Source-Side Training Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12397 - Road Maps as Free Geometric Priors: Weather-Invariant Drone Geo-Localization with GeoFuse Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.14925 - Being-M0.7: A Latent World-Action Model for Humanoid Robots Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11283 - On the Clock: Towards Punctual and Productive Time-Budgeted AI Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10833 - Multi-Bandwidth Distribution Matching Distillation: On the Equivalence of Distribution Matching Distillation and Drifting Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10989 - Conformal Prediction under Partial Verification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10829 - Gated Memory: Admission-Controlled Memory Formation for Conversational AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11270 - AdaSwitch: An Adaptive Switching Meta-Algorithm for Learning-Augmented Bounded-Influence Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.02302 - AdaptLSTM: Efficient Adaptive Online Learning for Cloud Workload Forecasting under Distribution Drift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12265 - Stop Probing, Start Coding: Why Linear Probes and Sparse Autoencoders Fail at Compositional Generalisation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.28744 - How to post-train on a surrogate: Envelope sampling mitigates reward hacking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11281 - RideBench: A Large-Scale Exogenous-Aware Benchmark for Ride-Hailing Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11164 - Whose Ground Truth? Embracing Ambiguity in Human-Centered AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10805 - VFold: Symmetry-Aware Cross-Layer Value Cache Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12338 - A structure-preserving neural density functional for the ions of a polymer electrolyte Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12132 - Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09701 - PSI-SINDy: Post-Selection Inference for Sparse Identification of Nonlinear Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11486 - Agentic Critical Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.08706 - Predictive Inorganic Synthesis based on Machine Learning using Small Data sets: a case study of Hydrodynamic Diameter-controlled Cu Nanoparticles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.16545 - PhysMoDPO: Physically-Plausible Humanoid Motion with Preference Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.13228 - MPGE: A Multi-Perspective Graph Explainer for Molecular Classification Explanation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12039 - Learning structured linear dynamical systems from missing observations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11869 - Residual spectral instabilities in representation learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11257 - Soft Tournament Equilibrium: Differentiable Set-Valued Inference for Non-Transitive Pairwise Comparisons Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.04328 - A General $\widetilde{\Omega}(\sqrt{T \gamma_T})$ Lower Bound for Kernel Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11082 - Conditional Kernel Stein Discrepancy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11863 - Freeze the Decoder, Heal the Encoder: Parameter-Efficient Adaptation for SVD-Based KV-Cache Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10552 - A Geometric Approach to Soft Actor-Critic with Zonotopes for Locomotion Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12113 - An Accuracy-Information Tradeoff for Loss-Difference Conditional Mutual Information Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09206 - Is Real-World Training Data Necessary for Generalist Graph Anomaly Detection? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12167 - JevForest: Path Voting for Budgeted Feature Acquisition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10615 - PlanWAM: Planning-Shaped Future Representations for End-to-End Autonomous Driving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11382 - The Score Is Not the Structure: Brain Alignment and Cross-Lingual Transfer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03827 - Recurrent Self-Improvement: Dynamic Cross-Loop On-Policy Distillation for Looped Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10623 - Cross-species representation learning aligns mouse and human neural dynamics and tracks clinical drug efficacy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11222 - K\"ahler landscapes for complex neural network descents and guarantees including a search and destroy of the Calabi-Yau manifold Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19584 - RouterInterp: Understanding Superposed Specialisation in Mixture of Experts Routing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11775 - TraceRelay: Attention-Aligned Recurrence over Rolling Traces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11743 - Do LLMs Learn from Rewards in Context? : Rethinking the role of reward in In-Context Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11152 - SpectralCache: Accelerating Diffusion-Based World Models via Spectral Feature Caching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02660 - Directed Temporal Representations for Offline Visual Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08960 - SMAT: Simple and Efficient Merge-Aware Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33437 - Salesforce Koa: An Enterprise Language Model for Agentic Tool Use Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15066 - The Truth Was Never Gone: Perfect Aliasing in Compliant-Context Truth Probes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10739 - SR-TTA: Spatial-Redundancy Test-Time Adaptation for Interference-Robust Respiration Sensing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11755 - Learning Kilometer-Scale Weather Prediction with Global-Regional Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12401 - SOL: Measuring Gaps between Text Distributions by Double Sliced Wasserstein Metrics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06513 - When to Intervene? State-Aware Sparse Manipulation in Federated Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11523 - Open-Vocabulary Audio-Visual Event Localization via Complex-Valued Fusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11846 - D-SLR: The Disjoint Row-Sparse plus Low-Rank Decomposition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10636 - Phonological Interference in Multilingual Speech Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11275 - KDFP: A first-principles approach to knowledge distillation in large language models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10854 - Prediction-Powered Data Fusion for Treatment Effect Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12332 - Toward Joint Optimization of Circuit Depth and Training Data Size in Adaptively Grown Quantum Classifiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12428 - HRIL: Learning Multimodal Synergy via Higher-Order Tensor Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12393 - Coverage, Not Difficulty, Sets How Much Synthetic Data an Activation Probe Needs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10594 - Stochastic Grouping Conformal Prediction for Effective Subgroup Reliability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11957 - Coverage-Aware Reasoning with Medical Tokens for Diagnosis Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10641 - BEAT: Balanced Frequency Adaptive Tuning for Long-Term Time-Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.19065 - RL-ARC: Calibrating Large Reasoning Models via Reasoning-guided Uncertainty Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11352 - AI4Fire: Evaluating Large Language Models on Wildfire Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10946 - When to Evict, Not What to Keep: Draft-Guided Eviction for Training-Free KV-Cache Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33334 - Trust, Don't Trust, or Flip: Robust Preference-Based Reinforcement Learning with Multi-Expert Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.18751 - Compactness and Consistency: A Conjoint Framework for Deep Graph Clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11506 - Language Models for Page-Level Layout Decisions in E-commerce Search Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.10920 - How Long, Not How Close: A Learned Temporal Metric for Planning in Latent World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04988 - Calibrating Ambiguity Set via Diagnostic Transport for Distributionally Robust Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10793 - Bridging KV-Cache Quantization and Linear Attention: From Theory to Pretrained Weight Migration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11214 - Scalable Hierarchical Graph Generation via Soft Community Structure Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12163 - Reconstruction of Multiscale Plasma Dynamics Across Operating Regimes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11004 - The Sample Complexity of Membership Inference and Privacy Auditing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.19458 - Amortized Off-Policy Evaluation for LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10848 - Rare Gate Disagreements Can Limit Plasticity: When Gradient Flow Mispredicts Finite-Batch SGD Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11475 - Bernoulli Flow Models: Self-Consistent Generative Modeling for Binary Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11362 - Conformal Data Contamination Tests for In-distribution Data Acquisition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.13835 - DaCe-DT: Data-Centric Offline Multi-Task Reinforcement Learning via Adaptive Prompts and Trajectory Correction for Heterogeneous Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11085 - MemoWM: How World Models Change What Agents Need to Remember Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10778 - CTRL: Control-Based Time Series Forecasting with LLM-Guided Residual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23257 - GHARP: Real-time Gaussian Head Animation from Large-scale Reconstruction Prior Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10945 - Evaluating Rubric Generation with Interventional Transfer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10809 - Population Scaling or Data Dilution? Dynamics of Local Topology Evolution in Decentralized Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05476 - F$^3$NO: Frequency-Decomposed Finite-Time Flow-map Neural Operators with Cross-Scale Conditioning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10998 - Trust Region Q Adjoint Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.27079 - Do Flatter Minima Drive Better Generalization? An Algorithmic Separation in Grokking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11206 - Embedding-Bias in Conditional Independence Testing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11584 - Beyond Accuracy: Robustness, Interpretability and Expressiveness of EEG Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.17562 - MoEMB: Scaling Universal Multimodal Embeddings with Efficient Mixture-of-Experts Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08663 - SFT-as-Context Mitigates Forgetting in Supervised Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11132 - DYSANOS Generative Dynamic Smooth Arbitrage-free Non-parametric Option Surfaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12587 - Embedding Models Measure in Peculiar Ways Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20821 - Learning to Emulate Chaos: Adversarial Optimal Transport Regularization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.21097 - FloorSAV: Elucidating Spatial Audio-Visual Context with 2D Floormap for AV-LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11310 - Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18810 - Learning Implicit Bias in Generative Spaces for Accelerating Protein Dynamics Emulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01833 - When Post-Processing Fairness Constraints Help and When They Harm: Evidence from Eight Cross-Domain Evaluations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26955 - A Unified Bellman Operator for Safety-Critical Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12420 - Region-Aware CLS Token Augmentation for Fine-Grained Image Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10991 - Score-Based Learning of Cluster DAGs from Interventions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11947 - $C_4$-Equivariant Flow Matching on Anisotropic Power-Diagram Graphs for Microstructure Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11549 - Diffusion-2BC: Hybrid Diffusion and Regression Training for Offline Behavior Cloning in Autonomous Driving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38472 - Why On-Policy Distillation Sometimes Fails: Vanishing Learning Signals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11247 - Bi-FORK: Generative Modeling of High-Dimensional Bifurcating Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12449 - Reward Observability and the Limits of Offline Checkpoint Selection in RSSM World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.01736 - PXtal: Learning to Align Powder X-Ray Diffraction and Crystal Structures under Information Asymmetry across Modalities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10653 - What is the goal of unsupervised machine learning? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11697 - Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.10169 - Stochastic Rounding in Low-Precision Transformer Inference: A Variable-Precision Emulation Study of a Small GPT-2 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01889 - Don't Get Your Kroneckers in a Twist: Gaussian Processes on High-Dimensional Incomplete Grids Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08036 - Towards Reasonable Concept Bottleneck Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.05014 - Lapras: Latent Reasoning for Time Series Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11111 - How Hackable Is Your Speech Quality Metric? A Corrected Protocol, a Benchmark, and What Patching Buys Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10899 - Perception Test 2026: Challenge Summary and Extension to City-scale Audio-Visual Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12081 - Ambient Discrete Diffusion: Using the Wrong Data at the Right Time for Data Efficient Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12340 - CARE: A Lightweight Plug-in Gated Correction and Uncertainty-aware Module for Long-term Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11165 - Beyond QAOA: A Review of AI and Quantum Computing for Adaptive Combinatorial Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11759 - One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12448 - When Should an In-Context Learner Expand Its Hypothesis Space? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09471 - Recovery Guarantees for Posterior Sampling of One-Bit Compressed Sensing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11834 - Plan-and-Patch: Diffusion Language Models for Agentic Planning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10786 - Transferability of Learned States in Neural PDE Solvers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10972 - NEMORA: Neural Equivariant Multipole Operators for Long-Range Atomistic Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10776 - Sample-Efficient Generative Conformal Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11349 - Conversational Voice Aesthetic Model with Reinforcement Learning from Human Listeners Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10868 - RH-Detect: A Unified Benchmark for Reward Hacking Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10947 - Automated Assembly Instruction Generation from CAD Models Using Grounded Large Language Models: A Human-in-the-Loop Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11896 - Diagnosing and Recovering from Observation-Space Shift at Long-Horizon Skill Seams Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10810 - Learning to Decide, Not to Reason: Parameter-Efficient Decision Operators via Low-Rank Activation Steering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06950 - Best of Both Worlds in Federated LSA: Speedup When Possible, Personalization Always Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11555 - AdaCast: Conditional Parameter Generation for Adaptive Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12240 - Long Text to Predictive Features: LLM-Guided Blockwise Feature Engineering via Executable Program Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12390 - Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12421 - An Investigation of Robustness of LLMs in Mathematical Reasoning: Benchmarking with Mathematically-Equivalent Transformation of Advanced Mathematical Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.08833 - State Stream Transformer (SST) V2: Parallel Training of Nonlinear Recurrence for Latent Space Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.00206 - Evi-VN: Hard Region Guided Virtual Node Evidence Injection for GNN-Based Fraud Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11665 - RiCo: Neural Simulation of Rigid-Body Interactions via Local Contact Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12333 - Decidable By Construction: Design-Time Verification for Truly Fearless Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.25414 - When KL Regularization Misfires in Group Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12161 - Teaching PPG How not Who: Fixed-Effects Distillation from ECG Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10662 - PIVOT: Perplexity-Informed KD-to-RL Transition Scheduling for Vertical-Domain Few-Shot Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11167 - Agentic-TTT: Training test-time policy for test-time training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12002 - 3BASiL: An Algorithmic Framework for Sparse plus Low-Rank Compression of LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.01376 - Accelerating Non-Smooth and Heavy-Tailed Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11139 - VioLA: Learning Generalist Humanoid Control Policies from Human Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12435 - Adaptive Multi-Discriminator WGAN Framework for Resource-Constrained Internet of Vehicles Using Reinforcement Learning and Game Theory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10926 - Empirical Evidence for Simply Connected Decision Regions in Image Classifiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06380 - SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11366 - Who Verifies the Verifier? Co-Evolving Inspectable Graders with Self-Improving Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11464 - ROAR: Retrieval Opportunity-Aware Refinement for Zero-Shot Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24911 - Q-Capsule: A Localized Capsule-Based Quantum Neural Architecture for Barren Plateau Mitigation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11261 - Differentiable Systematic Resampling for Variational Sequential Monte Carlo Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12094 - Unlocking the Regulatory Genome by ARGUS: An Evidence-Constrained Agentic Framework for Interpreting Single Nucleotide Variants Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12281 - SCORE: Spectral Correlation Estimation for Multivariate Gaussians Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12096 - Expected Batch Optimal Transport Plans and Consequences for Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12174 - SPIN: Shadow Predictive Indexer for Sparse Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09025 - Conditional Transfer from Controlled Pretraining Mixtures to Code Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11548 - Generative Spatiotemporal Intent Sequence Recommendation via Implicit Reasoning in Amap Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28888 - Cost-Aware Mixture-of-Experts Coordination for Model Markets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11908 - When Listening Becomes Easier: Scrubbing Visual Cues for Shortcut-Free VLAs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10912 - TACROSS: An Efficient and Low-Cost Scalable Human Touch System Across Heterogeneous Tactile Sensors for Dexterous Robot Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11945 - Large-Scale Benchmarking of Quantum Neural Network Configurations for Financial Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12148 - Marformer: A Transformer for Predicting Missing Data Distributions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12379 - SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12327 - Randomized Transport Maps for Model-Free Policy-Gradient Mean-Field Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11619 - How Many Directions Must a Truncated Diffusion Sampler Retain? Matching Bounds Under Power-Law Spectra Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10640 - PRAXIS: Learning Dynamics of Self-Improving Models with Symbolic Archives Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11803 - Robust and Efficient Noisy-Label Time-Series Classification via Dynamic Time Warping Based Granular Ball Computing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11704 - Few-Step Generation via Data-Space Iteration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12102 - Real Long-Term Memory for AI: A 50-Million-Token Window That Is Faster and Cheaper Than Recompute Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10845 - Composite Online-to-Nonconvex Conversion with Optimal Oracle Complexity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12328 - Coefficient Calibration as Selection Pressure in Symbolic Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10931 - Koopman operator theory: fundamentals, control, and applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.01819 - Measuring and Mitigating Solution Mode Collapse in RLVR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11064 - Solving the Offline and Online Min-Max Problem of Non-smooth Submodular-Concave Functions: A Zeroth-Order Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21243 - CityDeploy-Bench: Benchmarking Physics-Grounded Spatial Set Planning for Multi-Transmitter Network Deployment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11065 - Multi-Agent Coordination via Support-Preserving Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10087 - MaRK: Markov-adapted Recurrent Kernels for Dynamic Operator Conditioning in State Space Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09092 - Do Sheaf Neural Networks Use Holonomy? A Measure--Intervene--Control Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.19514 - A samplewise backpropagation method for neural networks driven by fractional Brownian motion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.29438 - Timer-M1: A Multivariate Time Series Foundation Model via Learning Primitives Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11734 - Sample-Efficiency of Kolmogorov-Arnold Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10627 - Self-Organization from Constrained Geometric Radiation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10621 - Interval-valued SHAP in Tree-Based Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11953 - 4-Tensor Attention Model for Semantic Physical Reality Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11716 - Causal-fate dynamics of unrealized influence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11422 - A mesh-based neural energy method for the simulation of heterogeneous composites Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10862 - Can Jev be Your Q or Policy in Reinforcement Learning? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11692 - Rethinking the Tradeoff Between Temporal Encoding and Nonlinear Computation in Spiking Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10933 - RaReCache: Bridging the Gap in Cross-Model KV Cache Reuse via Rank disagreement-based Selective Recomputation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11358 - Identification of Bivariate Causal Directionality Based on Anticipated Asymmetric Geometries Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.26024 - Learning from Hetero Density for Cryo-EM Protein Reconstruction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11403 - BEANS-Next and ROOTS: Broadening Audio-Language Capabilities for Bioacoustics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10663 - MA-JEPA: Joint-Embedding World Models for Multi-Agent Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33563 - PaReGTA: A Temporally Aware LLM-Based Patient Representation Framework for EHR Analytics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.19661 - Optimizing Large Language Models with Chained LMOs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10975 - What can linear attention learn from nonlinear teachers in-context? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10761 - Local Timescale Gates for Timescale-Robust Continual Spiking Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.12843 - Emergent Inverse-Depth Scaling From Nonlinearity In Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11063 - V-ECE: Estimating General Expected Calibration Errors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.24230 - CPU-Auth: Device Fingerprinting for Authentication via DVFS Side-Channel Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10766 - Beyond Distributional Fidelity: Causal-Penalized Diffusion for Synthetic Tabular Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11407 - Temporal transformer CAN encoder with federated lightweight heads for anomaly detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10613 - SplitJEPA: Learning Invariant and Variant Latent Worlds without Reconstruction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12349 - Multimodal Graph Retrieval-Augmented Sequential Recommendation via Collaborative Filtering Paths Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11228 - Learning What to Trust in Multimodal Learning under Noisy Supervision Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11057 - Data-Free On-Policy Distillation: How Far Can We Go Without External Data? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14193 - Inverse-LLaVA: Rethinking Multimodal Alignment via Text-to-Vision Mapping Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.12466 - Barron Optimal Transport I: Generative Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10875 - Quickest Change Detection with Diffusion-Integrated Scores Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12200 - Neuromotor Hierarchy Network: Physiological Inductive Biases for Robust Generalization in sEMG Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07713 - Directly Optimizing Mean Demographic Parity for Nonlinear Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.05098 - Feature Space Adaptation for Effortless Gaussian Process Flows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11459 - Example-driven Parametrisations for Bayesian Shape Optimisation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11984 - Evaluating and Improving the Robustness of Large Language Models to Input Sequence Variations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02432 - Just Weather Scoring: Efficient End-to-end Nowcasting with Distributional Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12189 - NP-Hardness of Minimizing Neurons in Two-Hidden-Layer ReLU Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11313 - Phase-HDC: Replacing Optimizer History with Gradient Thresholds in Discrete Phase Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10630 - Safe at One Loop, Risky at Another: Aligning Safety Across Recurrent Depths in Looped Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10625 - Self-Supervised Speech Representations for Cross-Speaker Dysarthria Detection During Awake Craniotomy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11825 - Compile the Table: Query-Calibrated Operator Compression for Tabular In-Context Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11784 - QUILT: Rethinking Sparse-Attention Prefill through Shared Query Execution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11134 - RIFT: Relative Isolation From Trees For Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12244 - Evaluating Local Language Model Agents for Reproducible Data Engineering: An Empirical Software Engineering Study of Mobility Workflows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11482 - Efficient quadratic entropy with distance sketches Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11976 - OnTrack: Real-Time Monitoring and Intervention in LLM Agent Trajectories via Streaming Structure-Aware Optimal Transport Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12375 - Memorization and Malign Generalization in Conditional Diffusion Models with Random Features Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11288 - Transformed Samplers with Variance Reduction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10870 - Policy Learning with a Language Bottleneck Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2405.04118 - Revisiting Identity and Spectra Dispersion in Media-Bridged Time Series Forecasting: Linking Multivariate Signals and Narrative Flows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11924 - Constructing Structured Decision Sources for Consensus-Based Pseudo-Label Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11621 - CSF: Contextual Safety Filtering for Motion Generators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12467 - NOMOS: Compiling Written Policies into Statically Verified Tool-Call Gates for LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11030 - TRACE: A Governance Framework for Measuring Explainability Debt in Production AI Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10957 - Shared Geometry As A Rosetta Stone: Cross-Modal Alignment Without Paired Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09411 - CAPABLE: Capability-Aware Policy Adaptation via Behavioral Latent Encoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11971 - Low-Cost Sensor Calibration for Indoor Air Quality Monitoring: A Dataset, Evaluation Scenarios, and a Lightweight Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11236 - Uncertainty Quantification in Federated Granger Causality Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.13004 - LAIR-Net: Leaky Alignment-Impulse Residual Networks for Tabular Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11538 - Quantum Multi-Armed Bandits and Linear Bandits: Lower Bounds and Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14319 - Refinement as a Service: Algorithmic Predictor Refinement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11415 - C-LoRA: Continual Low-Rank Adaptation for Pre-trained Visual Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.17920 - Capacity Confounds and Coverage Guarantees in Adaptive Sub-model Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.07157 - Conversational Task Disambiguation over Tabular Data: Leakage-Aware Formulation, Benchmark Suite, and Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10740 - CAF\'E: Causal Black-Box Testing of Machine Unlearning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.16525 - Zatom-2: Multitask Pretraining on Atomistic Data for Generative Modeling across Domains Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11454 - \$OneMillion-Bench: How Far are Language Agents from Human Experts? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.07980 - An Empirical Study of Agent Skills' Downstream Utility Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08875 - A Graph Neural Network for Global Daily Fire Radiative Power Prediction at Medium-Range Lead Times Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11022 - LM-X: Explainable Vision--Language--Action Modeling via Progress, Event, and Uncertainty Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25757 - SteerCast: Retrieval-Based Latent Steering for Decoder-Only Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11229 - GRASP: Geometry-aware Residual Alignment for Scalable Pretraining Data Attribution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.06892 - Learning infinite context windows in recurrent architectures via spatial neural computing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10690 - The Lattice of Transition Laws Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11216 - Reliability-Aware Future Conditioning for Temporally Robust Robot Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11956 - Symbolic Density Estimators for Unnormalized Distributions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10807 - Phonologically Informed Tokenization for German Speech Recognition: A Cross-Domain Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11646 - MotiveMob: Motivation as Semantic Action for Closed-Loop Human Mobility Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11442 - Density Ratio Estimation with Stein Displacement Fields Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12437 - How Much Does Message Passing Matter? A Drop-In Study of GNN Layers for Neural Network Graph Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.26404 - From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10642 - Explanation Multiplicity in SHAP: Characterization and Assessment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.12654 - Caught in the Act: Probes Effectively Detect Sabotage and Catch Unverbalized Deception Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12445 - Predicting Alignment Generalization with Value Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12410 - Ranking Prior Alignment for Credit Risk Modeling: When Do External Priors Matter? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11146 - Conditional Flow Matching for Visually-Guided Acoustic Highlighting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.03762 - Learning qBIC Resonances across Metasurface Families in Dielectric Fourier Space Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11500 - Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01081 - Optimal random quantisers for spherically symmetric distributions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11772 - $\sigma$Transfer: Uncertainty Transfer from Small to Large Networks under $\mu\mathrm{P}$ Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11668 - Minimax PAC Bounds for Learning in Exogenous Contextual MDPs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.25170 - Budgeted Cache Repair for Cross-Context KV-Cache Reuse Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02233 - Foundations of Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.09223 - BioBigBird: A Sparse Attention Model for Long-Range Dependency Processing in Biomedical Text Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11430 - ISBO: Scalable Spatio-Temporal Bayesian Optimization with Log Gaussian Cox Process Models via the INLA-SPDE Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12213 - Fractional Heat Kernel for Semi-Supervised Graph Learning with Small Training Sample Size Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.04440 - Beyond the Ergodic Wall: A Discrete Geometric Physics Sandbox for Analysing AI Scaling Limits and Complexity Collapse Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10651 - Low-rank tensor structure of precipitation and its application to satellite-reference merging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11000 - Generative Adversarial Loops Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11458 - Have I Seen Enough? Frozen Video-Language Models Encode Evidence Readiness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08560 - Jailbreak Scaling Laws for Large Language Models: Polynomial-Exponential Crossover Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.11331 - Exploiting Gradients in Bayesian Inference of Expensive Simulators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12076 - A Survey on Archetypal Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.12392 - Diffusion Removes Langevin's Conditioning Dependence: A Sharp Gaussian Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12052 - Dynamics as Code: On Model Compression via Dynamic System Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11115 - Harness Evolution Hits a Ceiling: When Weight Training Should Begin Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11655 - Power Side-Channel Membership Inference Attack on Embedded Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10909 - Deflating the Hessian: Rank-4 W4A4 Quantization for Multimodal Diffusion Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11315 - A Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12183 - asdex: Automatic Sparse Differentiation in JAX Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12336 - MRCert: Towards Post-deployment Patch Robustness Certification for Adversarially Patched Samples via Type-specific Masking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10617 - CMGL: Confidence-guided Multi-omics Graph Learning for Cancer Subtype Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.24201 - Training on the Future: A Delay-Aware Audit of Test-Time Adaptation for Time-Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12232 - Does an Illumination Prior Help Face-Swap Detection? A Controlled Study of Temporal Self-Blended Images Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11706 - RobustLDS: Learning linear dynamical systems under adversarial corruptions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11906 - Correlational Training of Morphological Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11740 - Retrieval-Augmented Generation for Predicting Cellular Responses to Gene Perturbation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.07233 - Internalizer: Portable Context-to-Parameter Mapping for Very Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11715 - The Distillation Game: Adaptive Evaluations & Efficient Defenses Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22737 - Exact SO(3)-Equivariant Isotropic Kernels for Rotation-Robust Neural Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10626 - Addressing Overcommitment in the Reasoning of Gendered Economic Memes under Multimodal Ambiguity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11724 - ActiveMedAgent: Cost-Aware Trajectory Learning for Multimodal Medical Diagnosis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11140 - Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08077 - SkillContrast: Difference-Guided Text Selection for Agent Skill Reranking Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.11650 - EVIE: Evidence-Vector-Informed Embeddings for Visual Document Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.11553 - Syn-Omni: Structured Specialization and Progressive Collaboration for Omnimodal Embeddings Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.12256 - RIT-RAG: Navigating Document Corpora with Retrieval-Induced Trees Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.11370 - CompOrca: Corpus-Scale Compliance Labelling of Instruction-Tuning Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37807 - CoPoE: Multimodal Fusion via Decomposable Disease-Coordinate Product-of-Experts for Missing-Modality Alzheimer's Diagnosis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11394 - Closed-loop evaluation of LLM agents for embedded software development Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11447 - An Efficient Quantum Circuit for Flow Model Execution Using Quantum Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11537 - BRACE: Differential Privacy for Dense Associative Memory with LSR Energy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11218 - Using Weisfeiler-Leman Features for Algorithm Selection in Constraint Optimisation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12119 - Spatial Pattern Formation from Multi-Agent Learning in Public Goods Dilemmas Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12321 - Networks with Finite VC Dimension: Pro and Contra Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.02679 - Risk-Conditioned Fine-Tuning of Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08064 - Curating Always-Loaded Context for LLM Agents: A Capacitated Assortment Model with Censored Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11007 - The Geometry of Empowerment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07796 - Efficient and Generalizable Archetypal Analysis for Discrete Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12035 - Are Near-Tied LLM Rankings Robust to Family-DIF-Guided Benchmark Recomposition? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00482 - Subspace Uncertainty and Sharp Sampling Thresholds on the Boolean Cube Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12358 - Interpretable Memory Models for Spaced Repetition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10548 - Smoothing the Top-k Exposure Boundary for Sparse Mixture-of-Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11575 - Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06152 - Similar Predictive Fit but Different Latent Dynamics: Characterizing Learned Dynamical Structure in Personalized Models of Brain Disorders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10850 - The Minimax Rate of Perturbed Second-Order Calibration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07808 - MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28732 - Sera: Semantic Representation Aggregation for Reliable and Interpretable Battery Health Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11567 - The Polytopal Neural Network Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12004 - GaussianBench: Physics-Fidelity Evaluation for Gaussian Scene Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10554 - RFChipAgent: Multi-Agentic AI Flow for Analog/RF Chip Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10858 - On linearity or non-linearity in machine learning for quantum chaotic dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10697 - Beyond Owls: Subliminal Learning Can Transfer Learned Capabilities and Backdoors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10657 - From Geometry to Generalization: Why Row Normalization Can Beat Adam and Muon Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11309 - MotherTree: Meta-learning on synthetic data improves decision tree training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10832 - Bayesian Optimisation under State-Preservation Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12150 - NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime Source: arxiv-cs-lg Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.10787 - LiteGUI: Lightweight GUI Agents via Multi-Solution Guided Distillation and Dual-Level Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07505 - New Lower Bound and Upper Bounds on the Regret for Online Sparse Linear Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11551 - Brain foundation model-guided source-selective domain adaptation for cross-subject EEG decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.21037 - Spectrally Targeted Muon Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10965 - Nullify: Null-Space Activation Steering for Training-Free LLM Unlearning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10655 - Mid-Training Language Models on Raw Video Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11019 - Uncertainty-Aware Optimization for Physics-Aware Highway Trajectory Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11580 - Ghost tasking for parametrized Gaussian Processes solving linear differential equations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12009 - Altered Thoughts, Altered Actions: Reasoning Chain as Control Surface for a Vision-Language-Action Policy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.12717 - FeatCal: Feature Calibration for Post-Merging Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13030 - Learning to Plan by Looking Back: Hindsight Hierarchies for Training Reasoning Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12168 - Predictive Multiplicity in Cell-Fate Assignment: Label-Free Rashomon Sets and the Limits of Per-Cell Certification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11185 - WOVEN: Weaving Visual World Modeling into Multimodal LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12417 - Provably Efficient Offline-to-Online Value Adaptation with General Function Approximation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.13966 - Delphos: A reinforcement learning framework for assisting discrete choice model specification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.06410 - Self-sufficient Independent Component Analysis for Demixing Flows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.00665 - Batch Before You Lift: Scalable Topological Deep Learning on Large Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12247 - Strategic Investment Decision Making for Value Creation in Energy Transition: A Reinforcement Learning Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10768 - How Many Repeated Pairwise Comparisons Are Needed for Ranking under Heterogeneity? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10795 - LLM Persona Unlearning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39882 - Group Invariant Spectral Embedding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.08987 - Dynamic Free-Rider Detection in Cross-Silo Federated Learning via Simulated Attack Patterns Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.04611 - Neural Conjugate Aggregation: Identifiable Unsupervised Multi-Sensor Regression under Heterogeneous Sensor Bias Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.22200 - DADP: Dynamic Activity-Dependent Pruning, A Reverse Hebbian-Inspired Structural Pruning Method Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11853 - The optimal information complexity of VC learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10600 - System-Prompt Conditioning and Hidden-State Geometry in Four Open-Weight Models: Corrections and What Survives Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.09842 - Equilibrium Distribution for t-Distributed Stochastic Neighbor Embedding with Generalized Kernels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.24311 - Transmission Neural Networks: Inhibitory and Excitatory Connections Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.04246 - Shape irregularity of Life-Like Network Automaton rules as an indicator of classification performance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10867 - Understanding Latent-Dimension Scaling in Dynamical-System Learning through Spectral Reliability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11866 - Measuring Learned Monotone Temporal Aggregation at Matched Admissibility Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05196 - Inference-Time Machine Unlearning via Gated Activation Redirection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12765 - LadderEdit: Edit-Level Residual Compression for Memory-Efficient Lifelong Editing of LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11160 - FAITH: Feasibility-Aware Safety-Filtered RL for High-Dimensional Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12432 - Rounding in Preconditioner Space: Redesigning 4-bit AdamW Optimizer-State Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12444 - BrainATCL: Adaptive Temporal Brain Connectivity Learning for Functional Link Prediction and Age Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.07106 - Explaining the Saliency Map Sparsity of Adversarially-Trained Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10666 - NanoProof: Open and Efficient Automated Theorem Proving in Lean 4 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11605 - Beyond Sample Copying: Structural Memorization in Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.13419 - MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22949 - Synthetic Time Series Generation via Complex Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.22879 - SACQ: Structured Decoding with Memory-Conditioned Refinement for Long-Horizon Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11170 - Deep Learning vs. Statistical Models for Multi-Horizon Price Forecasting of Second-Hand Electronics: A Systematic Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10727 - World-Model Policy Arbiter for Goal-Conditioned Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10932 - Mechanistic Evidence for Spectral Structures in Prior-Data Fitted Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21731 - Poster: A Preliminary Study of LLM Distillation Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12137 - Camera-Noise Residuals for Face-Swap Detection: Redundant, Not Complementary, and Why Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11683 - In-Ride Alcohol-Impairment Detection in E-Scooterists with False-Alarm Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11783 - Memory by Design: Probabilistic Sequence Layers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.31163 - DVLA-RL++: Dual-Level Vision-Language Alignment with Reinforcement Learning Gating for Few-Shot Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12095 - WAM-Cache: Staleness-Bounded KV Reuse for Efficient World Action Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11401 - DataSense-Bench: The First Step Toward an AI Scientist Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12190 - SPERA: Spherical Prior EEG Foundation Model with Geometry- and Frequency-Aware Latent Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10571 - Cova-PINN: Cross-Domain Conservation Physics-Informed Neural Network for Fluid-Solid Conjugate Heat Transfer in Complex Geometries Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11108 - Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.22871 - When History Helps and Hurts: Selective History Use across Multimodal Turns Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11948 - SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12402 - How Much Do Circuits Tell Us? Measuring the Consistency and Specificity of Language Model Circuits Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08348 - Disentangling Linguistic and Paralinguistic Information with Routed Sparse Autoencoders Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10865 - TRACE: Diagnosing Verifier Brittleness in Agentic Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11678 - Opera: A Verbal Critic Framework for Long-horizon Coding Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33987 - GUI-KV: Efficient GUI Agents via KV Cache with Spatio-Temporal Awareness Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.00536 - How Do LLMs Change Predictions Under Negation? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09571 - SERL-SQL: Selective Hindsight Distillation for Text-to-SQL Reinforcement Agentic Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00485 - Fact over Fiction: Detection of Pathological Hallucinations in Sinhala-to-English Neural Machine Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11389 - Local Prototype Reconstruction for Text-Compatible Speech-to-LLM Bridge Pretraining Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11159 - Latent Core Tokenizer: Compress, but Meaningfully Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12376 - SAGE: Sink-Aware Guided Emphasis for Visual Grounding in Vision-Language Decoders Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11469 - Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39578 - When Citations Mislead? A Claim-Level Benchmark for Legal Hallucination Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10971 - Limited Stereotype Control Through Routing Reweighting in MoE Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.27141 - Prosody-to-Text: Predicting text from low-pass filtered speech Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11544 - Adversarial Cues in Decision Models Used as Judges: The Role of Request Presentation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11436 - Language-Specific Effects of Tokenizer Choice in Multilingual Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12144 - Beyond Preset Identities: Selective Stance Accommodation and Interaction Reorganisation in Generative Agent Societies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.23406 - Residual Advantage: Student-Relative Teacher Guidance for RL with Verifiable Rewards Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11519 - An Explainable Header-Centric Framework for Large-Scale Semantic Table Interpretation and Data Quality Assessment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10541 - Which Skill to Distill? SGUID: Selecting a Compact Skill Bank for Model-Skill Co-Evolution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12367 - InterviewPlayground: A Simulation Environment for Evaluating AI Interviewers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12023 - Diffu-LoRA: A Novel Low-Rank Adaptation for Personalized Diffusion Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10550 - Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12341 - Scaling Verifiable Environments for Long-horizon Work Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04906 - Type-Checking for Pattern-Based Tree Transformations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11337 - Incremental Open-Ended Deep Research with Structured Harness Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11566 - SteerablePlex: Can We Steer Full-Duplex Models? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12201 - Measuring Cultural Alignment Beyond the Average: A Framework for Evaluating Maternal-Health LLM Interactions in Indian Contexts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11586 - SlideLab: Audience-Centered Scientific Slide Generation and Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30294 - Judging in Latent Space: Efficient Generative Reward Modeling via Semantics-Preserving Compression Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09788 - Large Language Model-Assisted Preparation of Transportation Management Plans: A Case Study with WisDOT WisTMP System Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10650 - DIAL-OPD: Learning More from Fewer Tokens in On-Policy Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11659 - What Transfers from Text to Vision? Capability Scaling Laws and Transfer Dynamics for VLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00013 - Audio-Visual Turn-taking Prediction in Cocktail Party Scenarios Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17056 - Language Models as AI Research World Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12235 - WorldBench: Evaluating LLMs on Three.js Voxel World Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10622 - Imperative Interference: Social Register Shapes Instruction Topology in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.25015 - Easy to anticipate, hard to compute: boundary dependence finds the computed outputs that entropy patching misses Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11790 - Large Language Model Turnover Undermines Screening for Artificial Intelligence-Assisted Scientific Writing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11599 - Large Language Models for Machine Translation Quality Annotation: Humans and Models Are Both Challenged Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10918 - LMSpell: Spell Correction with Pre-Trained Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.05414 - AdaptEvo: Adaptive Agent Learning with Evolving Supervision Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11354 - MindFlow: Mind Supernet Powered Thinking Flows for Research Idea Innovation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11966 - Constitutional Gating and Deterministic Recovery for Multi-Agent LLM Negotiation: Ablations Against a Stateful Adversarial Gatekeeper Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11542 - EconSkills: Studying Skill Transfer and Retrieval for Web Agents on Live Economic Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19523 - MiniVer-V: Identifying Minimal Sufficient Evidence for Short Video Verification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11233 - JevOut: Natural Context Can Flip Decision Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30243 - Thinking Inertia: LLMs Keep Thinking When Told Not To Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11765 - TokenRouter: Efficient Serving System for Token-Level LLM Routing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12242 - Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12360 - When Should Agents Think? Adaptive Reasoning via Cross-Turn Estimation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12061 - Beyond Sequences: Distilling Structured Decision Memory for LLM Recommendation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11501 - EgoVoice: Proactive Spoken Assistance from Egocentric Multimodal Streams Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12248 - AyurParam: A State-of-the-Art Bilingual Language Model for Ayurveda Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.02374 - Beyond Speech Captions: Speech-Rewarded Style Planning for Conversational Text-to-Speech Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11461 - Quantifying Retriever-Generator Alignment in RAG with Local Explanations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21803 - Structured Sentiment Analysis Using Sequence Labeling as Dependency Graph Parsing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11695 - MetaEncoder: Exploring the Limit of Bi-Encoders for Multimodal System One Decision Making with Natural Language Interface Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11316 - A persistent accuracy ceiling in automated verbal deception detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12118 - Leveraging LLM-Generated Explanations for Detecting Emotionally Rewritten Fake News Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08835 - Cited but Not Consulted: A Counterfactual Audit of Legal Chain-of-Thought Faithfulness Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12361 - PlurVA-LLM-2026 Shared Task Track-1: Pluralistic Value Alignment in LLMs via Multilingual Fine-Tuning and Threshold Calibration Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32382 - RAG-Stress: Probing the Limits of Evidence Reliance in Retrieval-Augmented Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11183 - ILM: An AI-Powered Storytelling Educational Tool Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12064 - Grammar Concept Annotation at Scale: Deployed Fine-Tuned Small Language Models Outperform Prompted Frontier Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10827 - When Can You Prune Your Network? A Study of Intermediate Neurons in Multilingual Speech Parsing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11520 - Probing for Long-Horizon Deductive Reasoning Capabilities in Language Models with Prolog Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11592 - Right Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2606.10388 - Project Greenhouse: Progress Toward Fully Open and Sovereign Agentic Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.11922 - On-Chain Archaeology of Bitcoin Oracles: Evidence of Use under Limited Observability Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.11439 - SAIL: Scientific Agentic Intelligence via a Science-Aware Loop Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.11451 - Learning Multi-Step Query Rewriting via Corpus Feedback for Conversational Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.10955 - RecToolBench: Benchmarking Recommendation-Specific Tool Orchestration under Fuzzy User Intent Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.30717 - GLM-RAG: Graph Language Models for Graph-Based Retrieval-Augmented Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2607.28397 - Chaos in the Text: Revealing the Modality Preference in Mixed-Modality Retrievers Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.11816 - Efficient and Scalable Provenance Tracking for LLM-Generated Code Snippets Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2605.28510 - H2CE: Modeling Geo-Semantic Interactions for POI Reranking with Heterogeneous Two-Stage Cross-Encoders Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.11277 - Beyond Resolution: Object-to-Image Ratio Mismatch in Instance Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.11489 - Compact and Efficient Indexes for Learned Sparse Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.12300 - MERGED: Multimodal Entity Resolution via Generated Expert Reasoning Distillation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.01913 - NativeScope: Relation-Localized Retrieval over Native Topology with a Correct Anchor Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.12243 - Overview of the NTCIR-19 Automatic Evaluation of LLMs 2 (AEOLLM-2) Task Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.11598 - LIFT: A Lifecycle-aware Interaction Factorization Transformer for Unified Retrieval and Ranking Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.10556 - Autoregressive Retriever: Improving Query Understanding from Item Feedback for Universal Multimodal Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.11666 - Intervention anchors and scientific verification in synthetic vascular predictive representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11704 - Ecology of AI Agents: Collaboration Creates a Population Threshold for Takeoff Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12436 - From Suppression to Repair: Mitigating Object Hallucination in Large Vision-Language Models via Localized Distribution Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11826 - Arbiter: Detecting Interference in LLM Agent System Prompts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.08993 - FactorizedHMR: A Hybrid Framework for Video Human Mesh Recovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.14854 - Beyond Type-checking: Towards Holistic Evaluation of Formal Specification Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10604 - VICO: Visual Environments Co-Evolving for Vision-Language Model Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10782 - VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26144 - SAFETY SENTRY: Context-Aware Human Intervention via EXECUTE-ASK-REFUSE Routing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.13594 - Is Memorization Context-Sensitive? Prefix-Based Extraction Beyond Isolated Prefixes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12085 - Cross-Provider Review as a Runtime Contract for Coding Agents: A Controlled Pilot and Fault-Injection Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10961 - Neural Decoding as Cognitive Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11923 - RISR: Residual-Informed Scientific Equation Discovery with Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11387 - Missing Modality-Aware Calibration for Trustworthy Brain Tumor Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11419 - PulseBound: Future-Beat State Forecasting Under an Explicit Information Boundary Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12010 - PMTRM: Pseudo-Memory Temporal Re-encoding Module for Embodied Policy Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11168 - A PDE Perspective on Generative Diffusion Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.05940 - EvoRubric: Self-Evolving Rubric-Driven RL for Open-Ended Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29847 - Back in Style: A Sociolinguistic Approach to Authoring and Measuring Persona Fidelity in User Simulation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10988 - Gaokerena: A Small Persian Medical Language Model Family Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00932 - HarnessSQL: Harness-Native Training for SQL Agents in Realistic Database Environments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12274 - AI Appeals Processor: A Deep Learning Approach to Automated Classification of Citizen Appeals in Government Services Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.03672 - Scaling Native Multimodal Pre-Training From Scratch Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22043 - Adapting English Quality Classifiers for Multilingual LLM Pretraining Data Selection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11585 - SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12039 - Forms of LLM-Integrated Applications from LLM-Chats to Autonomous AI Agent System Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11899 - Is Peer Review Really in Decline? Analyzing Review Quality across Venues and Time Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.15172 - Clinician use of language models diverges from how the models are evaluated Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11069 - All Verdicts are Not Equal: Rethinking LLM Judge Reliability Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12083 - Natural Language to First-Order Logic LLM-based Autoformalization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12030 - Optimal Transport Depth Up-Scaling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.08011 - Uncertainty-Aware Budget Allocation for Adaptive Test-Time Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26849 - Cognitive Thermometers: Machine Learning and Logical Complexity Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10724 - Marking Contour Tones in Yor\`{u}b\'{a}: A Typographic and Computational Proposal Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38627 - Deception by Omission: Language Models Knowingly Hide Their Mistakes Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11351 - GameCommBench: A Unified Benchmark and Type-Aware Evaluation for AI-Generated Game Commentary Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11129 - SafeInferCom: Safe Inference-Time Compute via Verifier-Guided Mid-Generation Intervention for Robotic Task Planning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11223 - Single-Pass Uncertainty Heads for Claim-Level Hallucination Detection in Persian Medical Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03482 - ReCal: Calibrating Structured Pruning for On-Policy Distillation Recovery Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11332 - A Formative Study of Brief Affective Text as a Complement to Wearable Sensing for Longitudinal Student Health Monitoring Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.14360 - Wieszcz-XIX: A 3.1-Billion-Word Corpus of Pre-1918 Polish and Temporally Bounded Language Models Trained From Scratch Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10592 - DPPM: Dual-Path Parametric Memory for Personalized Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11776 - Learning the Loop, Not Just the Page: Execution-Grounded Loop Learning for Web Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11543 - The "10th Juror": Open-Set Standpoint Screening for Bureaucratic Bias Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11136 - How Much Human Label Variation Does Formal Semantic Structure Explain? Group-Level Effects and Item-Level Ceilings in NLI Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.15870 - Verdict Without the Rule: Diagnosing and Auditing Regulatory Rule Sensitivity in LLM Compliance Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12313 - FA-Bench: A Benchmark for Phone- and Word-Level Timestamp Accuracy in Forced Alignment and ASR on Clean and Noisy Speech Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32396 - Using LMs to Model the Effects of Context and Coreference during Sentence Comprehension Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32119 - More Than Meets the Eye? Uncovering the Reasoning-Planning Disconnect in Training Vision-Language Driving Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.04532 - Empty Commitments: When Agents Promise What They Cannot Deliver Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01045 - Introducing Human-Centeredness in AI-Assisted Lexicography Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.11808 - Stochastic Teacher Intervention for Agentic On-Policy Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10878 - When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11291 - SWE-Journey: Towards More Realistic Evaluation of Coding Assistants through Long-Horizon, Multi-Turn Interaction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11559 - UXBench Pro: Benchmarking Personalized User Experience in Multi-Turn Dialogue Interactions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11638 - LoRi: Low-Rank Distillation for Implicit Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05315 - Not Every Change Is Necessary: Recoverable Drift in Large Language Model Unlearning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11915 - Black-Box Forensics for Conversational LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.22698 - Sparse Attention Is Matrix Approximation, Not Choosing from a Bag of Values Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10871 - UniData: Universal Multimodal Instruction Generation Pipeline Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11363 - CPR for LLMs: Critical-Point Routing against Catastrophic Forgetting in Domain Adaptation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30158 - Same Outcome, Different Evidence: Intent Recovery in LLM Safety Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11766 - REMORY: Learning Residual Memory for Context Compaction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11287 - UniDataAgent: An Ontology-Grounded Agent for Enterprise Question-to-Report Automation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27257 - SignRAG: Unified Retrieval-Augmented Gloss-Free Sign Language Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11371 - FastBench: Can Streaming VLMs Perceive High-Dynamic Real-World Streams? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12427 - Prompts versus Rules: Auditing and Controlling Speech Naturalness Behaviors in Voice User Simulators Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11015 - From Retrieval to Reconstruction: Constructing Evolvable Cognitive Memory for Long-Term Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11314 - DataVista: Diagnosing Multimodal LLMs on Data Video Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11993 - The One-Word Census: Answer-Choice Conformity Across 44 Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.12796 - Thought-Like-Pro: Enhancing Reasoning of Large Language Models through Self-Bootstrapped Prolog-based Chain-of-Thought Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2407.14562 - Pretrained Persona Mixture Models and Tandem Models for Human Simulation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22607 - Enabling Quantum Natural Language Processing for Hindi Language Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2312.01221 - Lossy Compressive Text Autoencoders Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10738 - Fair-GPTQ: Bias-Aware Quantization for Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.15206 - ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30199 - DiffuPlex: Accelerating Full-Duplex Spoken Dialog Models via Rolling Masked Diffusion Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12214 - Event-Centric Memory with Query-Aware Graph Augmentation for Long-Term Conversational Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11920 - Chronos Enables Code Agents to Reason over Software Evolution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11578 - Specialized Decision Models vs. General-Purpose LLMs: Benchmarking Jev Across Knowledge, Reasoning, and Multilingual Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11978 - CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12882 - ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12403 - Detecting Spin in Clinical Trials with Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11845 - From Sparse Representations to Behavioral Insights for Multimodal Depression Assessment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11787 - BeliefScope: Diagnosing Evidence-Driven Revision and Pressure-Induced Shifts in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11305 - Pretrained self-supervised speech models can recognize unseen consonants Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11542 - Obscuring Data Contamination Through Translation: Evidence from Arabic Corpora Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.14994 - A Ticket from Marginals to Joints: Coupled-Noise Distillation for One-Step Block Generation in Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06324 - Meddies-PII: A Multilingual Framework for Personally Identifiable Information Extraction in Clinical De-identification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.12544 - Does Modern Standard Arabic (MSA) Dominate Arabic Dialects in LLMs? A Representation-Level Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11510 - MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11959 - Can Decision Models Understand Stance? Evaluating Jev Against General-Purpose LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11901 - RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01780 - Can Large Language Models Reinvent Foundational Algorithms? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.05716 - MultiWorldBench: Do Independently Controlled Views Describe One Shared World? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11723 - MAMHOI: Factorizing Scene-Aware Human-Object Interaction through Affordances Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12416 - A Dual-Hypothesis Reasoning Framework for LLM Guardrails Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.17575 - DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11015 - Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06213 - Multi2AV-Safety: Benchmarking Safety in Multimodal-to-Audio-Video Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26535 - ActionCodec: What Makes for Good Action Tokenizers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.15397 - Multi-Task Evolution for Zero-Shot Cross-Problem Generalization using LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03316 - Conversational versus Dashboard Explainable AI for UAV Intrusion Detection: An Empirical Study of Operator Trust and Reliance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.10434 - Probability-Signature Dynamics: Unpacking Modular Addition Learning Within Two-Layer Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11833 - BridgeGuard: Explicit Safety Drift for Diffusion-based Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11483 - Does Rank Still Matter? Position Bias When AI Agents Shop on Our Behalf Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22697 - From Prompting to Composing: A Spatial Canvas Interface for Poster Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12230 - Looking Inside LLMs: Small-World Connectivity as a Signature of Reasoning Performance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12304 - Open-ended Scientific Discovery with Possibilistic Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11289 - From Pixels, Without Pre-training: Joint Generative and Self-Supervised Representation Learning in One Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05711 - On the estimation and validity of AI time horizons---a statistical look at the METR plot Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12466 - ProtoSemImage: Image-Valued Prototypes with Deformable Row Alignment for Interpretable Document Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11460 - VINCIE-NExT: Unlocking Video Editing from Images via In-Context Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12104 - From Surface to Depth: Towards Cognitive Appraisal Reasoning in Multimodal Emotion Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11918 - READ-Bench: Benchmarking Historical Instance Retrieval for Time-Series Diagnosis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32123 - Pretext: Defeating Malicious Skill Detection Frameworks for AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39607 - Traceable World State: A Provenance-Aware State Representation and Deterministic Replay Framework for Robotic Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12033 - SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07604 - Where Draft Trees Lose Target Mass: Exit-Guided Speculative Decoding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11750 - CoToGrasp: Contact-Topology-Conditioned Dexterous Grasp Synthesis via Canonical Workspace Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19776 - SparKV: Overhead-Aware KV Cache Loading for Efficient On-Device LLM Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.21231 - How Much Audio Is Left In An Embedding? An Inversion Audit Of Audio Encoders Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12250 - The Harness as the Only Mutable Surface: Compliance-Bounded Self-Evolution of LLM Agents in Credit Pipelines, with a Measured Admission Gate Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10629 - DynaTE: Accelerating Diffusion LLMs via Dynamic Token Execution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11284 - What to Admit and How to Present: Governing Persistent Memory in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11188 - Safe Actions Alone Do Not Ensure Safe Agents: Identifying Unfulfilled Obligations with Guard Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11773 - When Plans Change Answers: Formalizing Cost-Accuracy Optimization for Semantic Queries Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08089 - When Has a Bayesian Neural Network Sampled Enough? Adaptive Inference Time with Statistical Guarantees Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12212 - When AI Finds Hidden Messages, Does It Report? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10620 - Scalable AI Uncertainty Quantification via Generalized Laplace Active Subspaces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11738 - Beyond Direct Access: Resource Hijacking in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15108 - Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistency Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18162 - TAM: Task-Aware Memory Distillation for Efficient Spatiotemporal Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11617 - Evaluating Budgeted Context Projection with Unexecuted Companion Runs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31381 - Machine learning and information theory concepts towards an AI Mathematician Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2403.04571 - An Interpretable Approach to PDE Solution Discovery via Structural Experience Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12003 - Beyond the Remembered World: Predictive 4D Belief for Persistent Navigation in Evolving Worlds Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39166 - Compute Globally, Materialize Locally: The Memory Contract of Sparse Event-KV Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.23693 - Searching for "Harmful Refusal": A Psychometric Audit of an AI Safety Benchmark Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12409 - Bi-temporal Image-driven Acute Stroke Evolution Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.07535 - LeWAM: A JEPA World Action Model with Diffusion-Steering-Based MPC Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12407 - Humanoid World Action Model With Joint State--Action Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12026 - Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12299 - MIMESIS: Learning User Simulators as Training Environments for Interactive Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09484 - What Output-Only Review Cannot Verify: Study Contracts for Research Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11754 - RoboTalk: Learning Multi-Robot Communication and Coordination from Multimodal Demonstrations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23997 - Rethinking Latency Denial-of-Service: Attacking the LLM Serving Framework, Not the Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.07878 - GPF-Net: Gated Progressive Fusion Learning for Polyp Re-Identification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.21476 - OA-MAP: Evidence-Grounded Multi-Agent Multimodal Framework for Interpretable Knee Osteoarthritis Progression Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12134 - Language Modeling is Monotone Compression Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11031 - mAVE: A Watermark for Joint Audio-Visual Generation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.07090 - AI-Based On-Board Maritime Object Detection for Earth Observation Payload Data Reduction on Versal Embedded Hardware Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12182 - Distillation for Incrimination and Distillation for Capabilities Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11012 - SAVU-BENCH: A Real-World Benchmark for Spatial Audio-Visual Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10624 - Environmental Feedback Modeling Matters: Rethinking Feedback Treatment in Agentic Hindsight Self-Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11384 - Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2407.00079 - Design Creativity Bench: Measuring creativity in LLM-Generated UI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11539 - SDPAD: A Fully Spike-Driven Pipeline for End-to-End Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11583 - Elucidating the Space of Enzymatic Reaction: A Unified Benchmark and Pretrained Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11694 - Balancing Reference Guidance and Free Generation in Trajectory Rollouts for Reasoning RL Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11128 - ORDO: Operation-level Round-aware Dynamic Ordering for MIP Presolve Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11294 - VibeEdit: Image Editing with Canvas Instructions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12229 - Masked Generative Motion Planning with Geometry-Guided Token Search Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10646 - Real-Time Motion Planning with Dynamic Hazards: Classical vs. Learning-Based Methods Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12249 - Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11552 - Use and Disuse: Intent-Structured Experience Consolidation for Memory and Learning in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12124 - Type-Safe Is Not Error-Free: Typed Decision Models Follow the Option Name, Not the Definition Bound to It Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26758 - Deconstructing Off-Policy Ratios: Entropy-Normalized Trust Regions for Asynchronous Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22186 - REACT: Rolling Denoising and Dual Decoupling for Reactive Robot Control with VLA Models Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.12007 - Growing an Agent/Prover Interface: Evolutionary Tool Design for Cost-Efficient Theorem Proving in Rocq and Lean Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39544 - Beyond Report Imitation: Clinically Aware Multi-Image Ultrasound Report Generation from Visible Evidence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11610 - AtomWorld-Mirror: Macro-Step World Modeling of Critical Evolution Backbones for Materials Dynamics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11527 - Memory Type Varies: Empowering LLM Agents for Long-Term Memory with Diverse Strategies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11573 - One Word Opens the Gate: The Option-Channel Attack on Typed Decision Models as Agent Guardrails Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12292 - ACID: Action Consistency via Inverse Dynamics for Planning with World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.02403 - MAST: Motif-Augmented Diffusion with Search Tree for Spectroscopic Molecular Structure Elucidation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12067 - CRISP: Fixing Flying Pixels in Latent LiDAR Generation via Diffusion Decoding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11376 - Constrained Command-Conditioned Reinforcement Learning with Bandit Strategy Selection in Real-Time Strategy Games Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11663 - SynCo: Data Synthesis Co-Training for Self-Evolving LLMs via Multi-Agent Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11345 - Epistemic Disturbance in the Graph Model for Conflict Resolution: State-Preserving Actions, Four-Valued Assessments, and the Distinction between Capability and Intention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11690 - Universal Textual Teaching for LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12114 - The Review Lottery: Benchmarking an Observational Estimator of Peer-Review Noise (ICLR 2017-2025) Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06591 - RoboRSI: Stable, efficient, and reusable robot self-evolution in complex real-world environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12424 - Continuous Ground-Truth Construction and a Recovery Policy for Air--Water Robotic Tracking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11096 - ReCast: Attribution-Oriented Step Representation Learning for LLM-Based Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11334 - Recursive Self-Improvement through Multi-Agent Self-Supervision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12176 - Characterizing Overconfident Failure in LLM-Based Code Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11300 - MedBenchAgent: Towards Systematic Automation of Medical VLM Benchmark Construction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11312 - ParanoiaEval: Benchmarking Unnecessary Defensive Work in Agentic Coding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08662 - Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11570 - How Narrative Wrapping Affects LLM Refusal: A Cross-Language Benchmark and Defense Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11005 - Q-Shaped Options for Hierarchical Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12135 - Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19227 - Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08215 - AuraLuxMuse: Adaptive Fusion Modeling for Aesthetic Stage Lighting Design with Music and Expert Guidance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11792 - Agent-Controlled Forgetting for Tool-Using Agents: Reversible Context Curation in Practice Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10590 - Attention when you need Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.07440 - IAD-Unify: Task-Specific Interfaces for Industrial Anomaly Understanding, Segmentation, and Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.12440 - MAPF-World: Action World Model for Multi-Agent Path Finding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.12087 - LEVER: Adaptive Cost-Aware Proof Search Over AND/OR Graphs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11862 - BrickBench: Evaluating Agentic Brick Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12452 - OpenProblemBench: Benchmarking AI on Open Problems in the Foundational Theoretical Sciences Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11118 - EvoKnow: Continual Knowledge Evolution for AI-Generated Image Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11381 - IndustrialVLA-Bench: A Traceable Multi-Axis Evaluation of Open Robot Policy Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.25562 - Machine Learning Meets High-Energy Nuclear Physics: From Pattern Recognition to Physics-Integrated Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12293 - Why machines will still not rule the world Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11424 - SpikeSSL: A Universal Spike Inference Framework with Dynamics-Informed State-Space Layers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11456 - HistCAD: Constraint-Aware Parametric CAD Histories for Evaluating Editability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.19171 - SP-DocReader: Difference-Aware Self-Play for Precise Document OCR Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11148 - Harness Compilation: Which Decisions Should a Small Vision-Language Model Keep? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11231 - MobileWorldBench: Towards Semantic World Modeling For Mobile Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.14014 - Learned Image Compression for Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16253 - X2Streaming-ASR: wait when uncertain, emit when ready for streaming ASR Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08672 - BRANCH: Bypassing Multi-Scanner AI Guardrails Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10742 - How Should a Prompt Optimizer Spend a Tight Budget? BudgetAPO with Noise-Adaptive Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05671 - Workerville: Towards an Organizational Behavior Account of Agent Safety Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11561 - From Reactive Containment to Proactive Assurance: Lessons from OpenAI, Anthropic, and Google Agent Security Incidents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12463 - CRUISE: Vision-Language Model-Guided Uncertainty-Aware Cross-Modal Sensor Fusion for Robust Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09202 - Rewiring Semantics, Dynamics, and Control: A Simple yet Effective Action-Centric Tri-Stream Transformer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11416 - GROB: A Multi-Agent Architecture for Public-Trace Investigation of Candidate Agentic Activity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11467 - VAMR: Multi-Question Agentic Reasoning for Efficient Long-Form Video Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11171 - Neural Networks for Temporal Pattern Recognition and Dynamic Arm Gesture Speed Estimation for Robot Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11631 - FreshMem: Brain-Inspired Frequency-Space Hybrid Memory for Streaming Video Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01683 - Efficient Reasoning via Constrained Optimization in Latent Space Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34181 - AliO: Output Alignment Matters in Long-Term Time Series Forecasing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11213 - Beyond Imitation: A Framework and Benchmark for LLM-Assisted Peer Review Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11087 - Transect: Retaining Observability for Long-Horizon LLM Agent Evaluations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08364 - Simultaneous Computation with Multiple Prioritizations in Multi-Agent Motion Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.10781 - Instruction-Conditioned Electromagnetic Spectrum Understanding via Budget-Adaptive Signal Tokenization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12142 - Can LLMs Fix It Without Code? Toward Automated Verification of No-Code Bug Fixes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11963 - 4D-GSW: Kinematic-Aware Spatio-Temporal Consistent Watermarking for 4D Gaussian Splatting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22342 - Social Pain Disrupts Emotion-Action Brain-State Dynamics in Adolescents with Non-Suicidal Self-Injury Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11155 - A Relative-Computability Theory of Self-Improving Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.27381 - MemTrial: Learning When to Trust Memory in LLM Portfolio Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11732 - Error-Propagation Modeling for Failure Attribution in LLM-Based Multi-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11600 - Unifying Policy Learning and State Prediction through Spatial Language Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12172 - Has LLM Screening Performance Stalled in Software Engineering Systematic Reviews? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10633 - DeltaReplay: Task-Relative Memory Reuse for Mobile GUI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11707 - Structure Tax: How Structured Output affects LLMs Performance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12056 - AgentFly: Scaling Agentic Reinforcement Learning with Unified Resource System Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.14897 - MSGAT: Multi-Head Spiking Graph Attention with Similarity-Space Fusion for Image-Text Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11526 - SpaceFlow: Locally Controllable 3D Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12399 - MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11814 - GeoReform: Reflective Formalization Evolution for Multimodal Geometry Problem Solving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12391 - MetaOPD: Meta-Learned Token Weighting for On-Policy Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11989 - An Autonomous AI Security Agent for Banking: Multi-Vector Fraud and AML Detection Across Retail and Corporate Accounts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17555 - ARC: A Reasoning Recipe for Robot Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12386 - LVS: Local View Synthesis from Relative Camera Pose by Reusing Previous Views Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12127 - La-Ribo: RNA Co-Design via Geometry-Latent Flow Matching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12236 - Beyond Visual Enhancement: Adaptive Multi-Context Steering to Mitigate LVLM Hallucinations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11907 - CARE: Constrained Attention Refinement for Fine-Grained Visual Classification via Teacher-Student Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11153 - TypedBench: A Benchmark for Calibration, Framing Sensitivity, and Cost in System One Decision Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11392 - Defensive Sufficiency in a Stackelberg Model of AI Security Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09892 - UniShield: An Adaptive Multi-Agent Framework for Unified Forgery Image Detection and Localization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.03161 - Characterizing Statistical Separability in TP-CRIV for Probabilistic AI Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11163 - An Investigation of Model Coherence: Narrow Finetunes Contradict Themselves Under Resampling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12129 - DVD: Dynamic Vector Decoding for Efficient MLLM-based Perception Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12266 - LinSlot: Exploiting Linear Representation hypothesis for unsupervised attribute discovery from slot based object representation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10722 - Distilling Routed 3D Privilege for Spatial Reasoning in Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12355 - Reading the Room: Foundations, Design, and Challenges of Normative Competence in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10906 - Synthesis Through Simulation: Generating Coherent Enterprise Data via Scalable Agent-System Interaction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10549 - Neural Network Verification for Deep Joint Source-Channel Coding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11994 - Rethinking Contrastive Loss in CLIP Post-training: A Complementary Framework with Frozen Text Encoder Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11374 - Trajectory-Guided Fault Localization for Agent Skill Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11858 - FlowState: Execution State as Memory for Long-Horizon LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34565 - TokenBank: Financial Infrastructure for AI Services Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11333 - PearlVLA: Progressive Embodied Action-Plan Refinement in Latent Space Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17924 - DENSE: Distilling Agent Trajectories into Evidence-Grounded Shortcut Trees for Self-Refinement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21423 - Where to Adapt Matters: Layer-Selective Fine-Tuning for Capability Retention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11620 - Certified Corruption Budgets: Anytime-Valid Leaderboard Claims under Adaptive Rigging Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10597 - Fed-GRPO: Reward-Signal-Driven Federated Group Relative Policy Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11502 - Cognition-Oriented Emotion Tracing from Causes to Consequences in Real-World Social Scenes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11410 - The Operator Mismatch Problem: Deploying BEV Perception with Portable GPU Compute Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11504 - Speedbumps: Rejection Attacks on Speculative Decoding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10929 - A 3D Characterization Framework for Intelligent Sequential Decision Making Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11696 - Onboard Marine Anomaly Detection on $\Phi$sat-2: From Simulation-Based Development to In-Orbit Demonstration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11735 - Runnable Commit Untangling for Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11593 - Complexity of Grounded Semantics and Preferred Semantics in Finitary Argumentation Frameworks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12008 - Why LLM Agents Favor Their Group: Stakes, Observed Norms, and Reputation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11008 - EvoSim: Learning to Model, Modeling to Learn Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11344 - Recompose and Refine Latent Reasoning Flows for Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12090 - ExecVLA: Following Fine-Grained Execution Constraints in Vision-Language-Action Models with Bi-Level Action Representation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.17524 - AI-Mediated Self: How HCI Defines and Relates to the Self Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10770 - Equal Path Cost, Unequal Output Effects: Understanding Perturbation Propagation in Diffusion Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11380 - Neural Architecture Discovery via Autonomous Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.18074 - Verification and Self-Improvement in Agentic AI: Foundations and Limits Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10611 - Causal Memory Policy: Making Memory Utility Identifiable by Intervening on Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02070 - DuplexAgent-RSI: Recursive Harness Improvement for Full-Duplex Voice Agent Collaboration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11299 - EvoAlloc: A Self-Evolving Resource Allocation Agent for Efficient Program Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12086 - LLM-IDEA: Identifiability-Driven Experimental Agent for Autonomous Discovery of Mechanistic World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11253 - Bridging the Last Mile of Circuit Design: PostEDA-Bench, a Hierarchical Benchmark for PPA Convergence and DRC Fixing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06936 - HI3D 3.0 (Twinkle3D): Object-specific 3D Asset Generation with High Resolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11685 - Discovering Global False Negatives On the Fly for Self-supervised Contrastive Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.20612 - MAP4CS: A Multi-dimensional Data Pruning Framework for Efficient Code Retriever Fine-tuning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11727 - Learning Probabilistic Logic Programs with Functional Gradient Guided Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12303 - From Chain-of-Thought to Loops: Non-Autoregressive Latent Reasoning via Looped Transformers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11472 - World-Ego Modeling for Embodied Video Generation in Long-Horizon Navigation-Manipulation Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19957 - Humanity's Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08966 - SLVR: Structured Latent Visual Reasoning via Human-like Reasoning Flows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10563 - A Structural Theory of Cognitive Representation and Problem Solving,Contexts, Invariance, and the Knowledge Space Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12306 - Intent Graph: Navigating the Analytical Reasoning Space for Exploratory Data Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11025 - Improving Image-Based Nutrition Estimation Through Multimodal Food-Item Verification and Recovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11144 - AgentEvolver: System-Wide Self-Evolution Through Task Execution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11613 - iAm.md: Robot Skill Self-Assessment through Agentic Introspection for Unknown Open-Vocabulary Domains Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10962 - Reading the Whole Heart: Latent-Attention Masked Autoencoders for Multimodal Cardiac Representation Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.12035 - One Skill Too Many: How Co-Installed Skills Conflict in Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11647 - Narrow and Deep: An Ontology Tower as the Knowledge of an LLM Agent for an Industrial Equipment System Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11768 - Higher-Order Action Supervision Makes A Strong Policy Class Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11175 - Probabilistic Sensing, Deterministic Authority: Admitting Model-Produced Observations into Sufficiency-Checked Governance Contracts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10978 - Evidence-Traceable Dynamic Interviewer Architecture for Expertise-Adaptive Qualitative Interviews Using Local LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11651 - Proof-of-Use: Mitigating Tool-Call Hacking in Deep Research Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.10931 - TaReD: Tool-Aware Recursive Decomposition for Long-Horizon Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11268 - VLA Grounder: Language-Conditioning Space Optimization for Black-Box VLA Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04517 - TestJack: Should you trust the results in coding benchmarks? Agentic Coding Benchmarks Auditing via Evaluator Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10619 - Beyond Component Testing: Validating Agentic AI Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.29405 - LTBD: Learnable Trust-Boundary Delimiters for Prompt Injection Defense Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11634 - ContiLNN: Mitigating Slice Sampling Discontinuity with Liquid Neural Networks for Medical Image Restoration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12337 - Phantom Transfer: Data Poisoning can Survive Data-Level Defences Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.04899 - Humanize: Judgement Engineering for Agentic Coding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08900 - HIL-UMI: Bringing Human-in-the-Loop Post-Training of Vision-Language-Action Models to Universal Manipulation Interface Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20659 - From Investigation Failures to Reliable SOC Agents: Understanding and Improving LLM-Based Alert Triage Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10608 - Self-Referenced Social Preferences: Cooperation without Observing Others Rewards Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07881 - A Score Is Not a Policy: Measuring the Value of Adaptive Revision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00874 - RoboAware: Learning to Coordinate Embodied Skills from Counterfactual Outcomes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11480 - APEX: Assumption-free Projection-based Embedding eXamination Metric for Image Quality Assessment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07786 - ReSI: Recursive Safety Improvement toward Resistant and Resilient AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12233 - EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.27820 - Evaluating Exact Output and Checkpoint-State Prediction in Real Programs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11889 - Code Understanding is a Bottleneck for Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10610 - When Interfaces Speak: Data-Aware Generative UI Harness for Active Interaction Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.11123 - SRUG: A Fusion-Driven Generator Network for Medical Image Translation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.04785 - Analyzing and Improving Fine-grained Preference Optimization in Medical LVLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.12590 - MemTrace: State-Consistent Memory for Long-Horizon Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04838 - Finsler Flow Matching: Dynamics-Aware Geodesic Interpolation for Single-Snapshot Trajectory Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11318 - Learning to Orchestrate Evolutionary Search: Progression-Aware Deep Reinforcement Learning for Dynamic DE-CMA-ES Coordination in Optimization and Structural Model Updating Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11546 - ReTeach: Building a Self-Teacher through Multi-Round Reflection and Retry Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11529 - From Pixels to Structure: Lightweight Vision-Language Models for Document OCR and Structured JSON Extraction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11818 - Writing for the Reviewer: Defensive Writing in GPT Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11355 - AffordDrive3D: Affordance-Aware World-Action Modeling with Spatial Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11060 - Speaking the Navigator's Language: Trajectory-Grounded Instruction Translation for Frozen Aerial VLN Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10635 - Mine Odyssey: Benchmarking Spatial Agentic Intelligence in the Wild Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11328 - A Network Science Perspective on Evaluating Deep Graph Generative Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01015 - A Survey on LLM-Integrated Hardware Design Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10580 - Self-Supervised Keyframe Discovery for Horizon-Invariant Behavior Cloning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10857 - How Is Automated Research Evaluated? A Survey of Benchmarks and Evaluation Practices Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11877 - Efficient Dense Crowd Trajectory Prediction Via Dynamic Clustering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18166 - Learning How to Search for Plans with Exponentially Less Space Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10954 - Tracing the Thoughts of a Coding Agent Playing ARC-AGI-3: Lessons for Continual Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11450 - AgentTime: Can Agents Estimate and Control Their Own Runtime? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09944 - Solver-Aware Decompositions for Programming-by-Example: When Dividing Requires Knowing how to Conquer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.03461 - HANS: A Handwritten Answer Sheet Dataset for Noisy Hybrid Document Parsing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12363 - The Missing Fourth Term for the Emulation Tensor Memory Equilibrium (TME) Model: The Residue Deconstruction Cost Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10924 - Agent4RE: A Self-Refining Multi-agent Framework for End-to-End Software Requirements Engineering and Benchmarking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10628 - Lamarck's Driving School: Discovering Autonomous Driving Training Strategies through Evolutionary Competition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11662 - MissMAC-Bench: Building Solid Benchmark for Missing Modality Issue in Robust Multimodal Affective Computing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.00811