TILens Daily Edition 2026-11-02 Filters: topic=ai-research, github=hidden Stats: 551 articles, 7 sources, 548 research papers Top topics: AI Research, AI, Information Retrieval ## News - 😺 Microsoft's binding AI school deal Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/microsoft-s-binding-ai-school-deal/ - Everything That Happened in AI Today (Monday, November 2, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-today-monday-november-2-2026/ - AI Weekly Issue #542: AI week ahead: data center pause backers could win 15 governor races Source: ai-weekly Topic: AI (+AI Research) URL: https://aiweekly.co/issues/ai-week-ahead-data-center-pause-backers-could-win-15 ## Research - Credit Risk: What Are We Actually Measuring? Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/credit-risk-what-are-we-actually-measuring/ - Reflection's Beam Is the New Open-Weight Model Everyone Is Talking About Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/reflections-beam-is-the-new-open-weight-model-everyone-is-talking-about/ - Our AI Has an Invisible Footprint — Let's see How to Measure It Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/our-ai-has-an-invisible-footprint-lets-see-how-to-measure-it/ - Let Decision Models Watch Your Agents Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/let-decision-models-watch-your-agents/ - M$^\star$: Every Task Deserves Its Own Memory Harness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.11811 - Generative SDEs with Trainable Diffusion and Density-Based Losses Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41243 - Conditional Neural SDEs for Financial Time-Series Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41405 - Recursive Code Evolution for Task-Oriented Semantic Communications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29641 - h1: A Taste of the Bitter Lesson in Automated Theorem Proving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35962 - 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 - A Nearly Quadratic Lower Bound for Linear Optimization over Convex Bodies in the Membership Oracle Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30215 - Steering Vectors as a Training Signal in LLM Post-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40998 - Understanding the Performance Plateau in Text-to-Video Retrieval: A Comprehensive Empirical and Linguistic Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.00826 - Physiological Trajectories and Observation Patterns in ICU Mortality Prediction: Transportability Under Changing Measurement Conditions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42126 - On the Design Space of Discrete Diffusion Online Adaptation for Molecular Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.02834 - Accurate and Auditable ECG Classification via Visibility Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41795 - Monte Carlo Random Walk Kernel Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40956 - TaxoMFM: A Taxonomy-Aware Foundation Model for the Human Gut Microbiome Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39316 - Normative Deviation Modeling for EEG-based Depression Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37338 - What Standard Evaluations Hide About Detectors of Hijacked LLM Agents: Rare Attacks, Unseen Tools and Benchmark Transfer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41803 - CAMEL: Cross-Architecture Masked Embedding Learning for Ultra-Lightweight Retinal Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40954 - How to Score Experts for One-Shot MoE Expert Pruning: A Systematic Formulation and Selection Principle Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.15716 - Sample-wise Constrained Learning via a Sequential Penalty Approach with Applications in Image Processing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.16812 - Meshless Latent Dynamics Models for Model Order Reduction of time-dependent Partial Differential Equations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41043 - Root Cause Analysis of Measurement and Mechanistic Anomalies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.23026 - CausalGrade: Evidence-Guided Causal Graph Scoring with Jev Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40692 - Certified Behavioral Retention for Continual Adaptation with Held-Out Anchors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40740 - Transport What Shares the Conduction Pathway: Normal-Anchored SPD Geometric Transport for Source-Free Patient Adaptation of Holter and Patch ECG Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24430 - Quantile Propagation Planning for Budgeted Tail-Risk Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41351 - LegoSR: A Unified Framework for Self-improving Agent-Guided Scientific Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33465 - How Fast Should a Model Commit to Supervision? Training Reasoning Models on the Tsallis Loss Continuum Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.25907 - Cost-Aware Stopping for Freeze-Thaw Bayesian Optimization: When Does One-Step Lookahead Suffice? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42085 - When AI Investigators Cannot Trust Their Tools: Conflict-Aware Evidence Verification for Cyber Threat Investigation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41191 - Towards Understanding the Impact of Plasticity Loss on Reinforcement Learning in Stochastic Environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42100 - Deep Neural Sheaf Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19021 - Instance-dependent sequential limits as an exact information ledger Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42133 - Dual-Corrected Stochastic Block Model ($\text{DC}^2\text{SBM}$): A Generalized Structure Detection Method for Attributed Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40676 - Critically-Damped Higher-Order Langevin Dynamics for Generative Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.21741 - From GPU to TPU with Coding Agents: What Works, What Fails, and What It Costs? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34422 - Leveraging Quantum Measurement Randomness for Shot-Efficient Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41721 - There Is No Free Loop: When Does Looping a Trained Model Pay for Its Inference Compute? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42030 - Fusion or Confusion? Multimodal Complexity Is Not All You Need Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.22991 - Omniprediction for All Mixable Proper Losses and Beyond Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41023 - Localizing predictive concepts encoded in neural representations via hierarchical testing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41046 - Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37657 - When Does Jacobian Fine-Tuning Stabilize Neural PDE Emulators? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42013 - Robust Learning of Multi-Index Models under Logconcave Distributions via Weak Partial Learners Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41961 - Non-Asymptotic Stability and Consistency Guarantees for Physics-Informed Neural Networks via Coercive Operator Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.13554 - Query Entity-Oriented Graph Neural Networks for Knowledge Graph Completion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05639 - Certifying Retraining Regret through Residual Structure Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41410 - DeepWeave: Weaving Neural and Symbolic Evidence for ML-Based Network Intrusion Detection System Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41541 - PDE-Residual-Informed Kriging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41590 - Differentially Private Synthetic Data from Sliced Chebyshev Moments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42081 - Expected Harm: Rethinking Safety Evaluation of (Mis)Aligned LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01600 - FGSM Attack Transferability from Simulation to Quantum Hardware in Network Intrusion Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40701 - SparseGDN: Chunk Sparse in Linear Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41420 - Generated storm lifecycles fill the rare-event tail of short rainfall records Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41365 - Latent-Lens: Visual Perception in Small Language Models Through Latent Communication Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41751 - AutoHebb: Self-Modifying Neural Networks that Zero-Shot Infer and Continually Learn Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40757 - Infinite ResNets are Gaussian Mean ODEs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41514 - VitisGP: Multi-Task Benchmark for Genotype to Phenotype Grapevine Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40668 - How Do Video Foundation Models Encode Intuitive Physics? Probing Across Pretraining Paradigms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09646 - Latent Reasoning in Continuous Space for Unified Multimodal Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42149 - Continual Reinforcement Learning Is an Integration Problem Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41809 - Geometry of Relaxed Fair Regression: A Unified Framework for Aware and Unaware Settings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28233 - A Unified Per-Token Gating Family for On-Policy Distillation: FKL/RKL Mixing with Multi-Channel and Bias Coefficients Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.11768 - Repair Brain Damage: Real-Numbered Error Correction Code for Neural Network Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.00076 - GROME: GROunding Factorized MEmory into Video World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39812 - No-Harm Physics-Informed Inverse Learning with Residual-Calibrated Uncertainty Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07153 - TensorSSM: Memorizing Spatial Position in Dynamic State Space for Tensor Core Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40871 - Single-Annotation, Multi-Hypothesis Segmentation with Semantic-Spatial Residual Banks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41069 - DUGO: Dual-Scale Gaussian Memory for Online Temporal Action Localization in Egocentric Procedural Videos Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41402 - Bayesian Complete-Pooling in Cross-Subject Classification for Motor Imagery Electroencephalogram Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22980 - Fair Recommender Systems for Intersecting Groups Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.40936 - Federated learning for unpaired multimodal data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.17986 - Lattice-Based Pruning of Recurrent Neural Networks via Poset Modeling: A Corrected Theory and a Matched-Sparsity Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.16525 - GhostPrefix: Synchronization-Free Universal Prefix Attacks for ASR Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42026 - SmartMeterFM: Flow Matching for Smart Meter Data Generation, Imputation, and Super-Resolution Without Retraining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21706 - SIRF: A Spec-Internalized Risk Foundation Model for Industrial Content Risk Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.11752 - Consensus Within, Competition Between: Decentralized LLM Teams for Perimeter Defense Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41044 - Gaussian Process Upper Confidence Bound Achieves Nearly Optimal Regret in Noise-Free Gaussian Process Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.19006 - Fast Privacy Loss Accounting for Random Allocation via Multiscale FFT Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42117 - Improving the Optimization Landscape of Matrix Completion with $\epsilon$-close Surrogates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41455 - Do Language Models Know What Compelling Scientific Evidence Looks Like? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41015 - Recycle only when you have to! Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40665 - You Only Pass Once: Answering and Abstaining Together in a Single Forward Pass of a Frozen Language Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14465 - Non-Commutative Lie-Algebraic State-Space Models: Finite-Division Variety Laws, Semidirect Cascades, and Gradient Saddle Escape Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00329 - Do LLMs Know When They Are Wrong About Molecules? In-Context Property Prediction with Self-Reported Uncertainty Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41745 - From Training Exposure to Membership Evidence: A Controlled Study of OLMo 2 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41732 - A small HER2 reader for routine H&E slides: real-world deployment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40662 - Bayesian Distribution System State Estimation with Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40728 - Optimal Design for Multinomial Logit Model with Applications to Best Assortment Identification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25592 - Trainable Vector Quantization for Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41822 - Mechanistic Interpretability for End-to-End Self-Driving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41185 - Combinatorial Residual Network: a decay-chain-aware classifier without explicit jet assignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40749 - Estimation of Quantum Umlaut Information Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41282 - Operon-S1: a fast decision controller for long-horizon biomedical agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41350 - TAPE: Learning General Audio Effect Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40759 - NormDetect: Anchored Calibration for Low-False-Positive Detection of Machine-Generated Web Text Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41459 - A Theoretical Framework for Understanding and Building "Any-task inference" Capable Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40934 - Your Group-Relative Advantage Is Biased Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.08521 - DIFFNAS: Predictor-Free Neural Architecture Search via Diffusion Model and Zero-Cost Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41818 - Shifting Focus by Reliability: Geometric Fusion Modulation for Robust RGB-T Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41204 - DNNs, Dataset Statistics, and Correlation Functions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.21715 - Role-Aware Server Optimization for Multimodal Federated Learning with Missing Modalities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41193 - Enhancing Sentiment Classification on Small Datasets through Data Augmentation and Transfer Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41518 - Density-Guided Bootstrap Boundaries for Latent World-Model Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41022 - Model-Agnostic Search for New Physics in the Presence of Imperfect Background by Smearing the Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40734 - From WSIs to Bulk, Spatial and Single-Cell Transcriptomics via Multi-Scale Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41692 - MIRAGE: Auditing Anti-Muslim Bias in Frontier LLMs Across Reasoning, Agentic, and Time-Coupled Conditions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16562 - Learning Nonlocal Interactions in Large-Scale Heterogeneous Metamaterials through Scientific Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41887 - Discovering contemporaneous and lagged causal relations in autocorrelated nonlinear time series datasets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2003.03685 - Hierarchical Cooperative GFlowNets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33968 - Counting on Dummies: Privacy Amplification with Observable Counts and Truncated Batches Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42139 - DAPS: Dependency-Aware Premise Selection for LLM Theorem Proving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41536 - Spectral Haar Binarizer: Compact Boolean Contrast Representations for Hyperspectral Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41478 - Before We Adapt: The Zero-Shot Generalization Bottleneck in Continual World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41041 - Turing LLM Post-Training: Calibrated Distillation and Efficient Dynamic-MoE Execution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39876 - A Neural Network Approach towards Real-Time Knot Point Density Estimates for the Nonlinear Quadrotor Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42027 - Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12388 - Hierarchical Residuals: A Minimalist Decoupling of Residual Width from Compute Width Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41711 - When Does Dynamics Randomization Test Context Inference? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32414 - PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37381 - Conveyance: A Versatile Framework for Learning in Structured Class Spaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28420 - FARO: Function-Space Adaptive Return-to-Risk Optimization via Cross-Block Equal-Risk-Contribution Budget Allocation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40858 - Apriel Voice 27B Preview: An Open Model for Speech, Reasoning, and Tool Use Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40738 - Nonlinear Maps Between Irreducible Representations in Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41059 - Distributed Information Bottleneck Theory for Multi-Modal Task-Aware Semantic Communication Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.04000 - Neural Networks Based on Power Method and Inverse Power Method for Solving Linear Eigenvalue Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2209.11134 - Estimating Performance for Safe Deployment of Machine Learning Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29262 - Learning Clean Generative Processes from Noisy Measurements Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42036 - Safe Reinforcement Learning via Recovery-based Shielding with Gaussian Process Dynamics Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.12444 - SAT-ACT: Learning CDCL Branching from Outcome-Derived Action Preferences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41290 - RetryRoute: Retry-Aware Model Routing for Agentic Image Editing Services Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41460 - A Theory-guided Weighted $L^2$ Loss for solving the BGK model via Physics-informed neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.04971 - Optimizing Stochastic Policy Geometry for Few-Step Flow Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41949 - General Frequency Principle for Linear Approximation Classes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41179 - From fleet trajectories to single-cell promises: hierarchically weighted conformal prediction for battery SOH monitoring Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41696 - Opening the Box Changes the Cat: LLMs Detect Chain-of-Thought Monitoring - What now? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40946 - ORACLE: Anticipating Scams from Partial Trajectories in Streaming App Usage Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16363 - RAMA: Retrieval-Augmented Multi-Agent Routing with Episodic Memory for LEO Satellite Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42068 - AME: A Multi-Type Contributor Attribution Framework in Generative AI Markets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16075 - Corroborative Learning: Mutual Enhancement through Task-Response Reconstruction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41222 - Interpretability-by-Design with Accurate Locally Additive Models and Conditional Feature Effects Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.16503 - TILE: Bridging LLMs and Table Foundation Models for Tabular Learning with Strings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17065 - Characterizing Recoverable Expert-Utilization Signatures in Fine-Tuned Mixture-of-Experts LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41039 - Diversity-Aware Ensemble of Quantum-Classical Models via Combinatorial Fusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13808 - Intervention-Conditioned Counterfactual Human Digital Twin Generator Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40664 - Learning Stabilizing Latent Feedback Controllers via Multi-Step Backward Losses Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40931 - When Does Context Help? A Systematic Study of Target-Conditional Molecular Property Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.06558 - A Positional Realizability Theory of Length Generalization in Single-Head Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41218 - DialFork: Going Beyond Factuality to Evaluate Procedural Hallucination in Conversational Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21561 - SACQ: Structure-Aware Codebook Quantization for Ultra-Low-Bit Vision-Language-Action Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41408 - FlowTouch: View-Invariant Visuo-Tactile Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.08255 - When Is a Game a Markov Decision Process? Correspondences Between Game Theory and Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41962 - Slim attention: cut your context memory in half without loss -- K-cache is all you need for MHA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.05840 - When Links Mislead: Label-Free Structural Polarity for Zero-Shot Classification of Web Pages Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41464 - Learning Robust Social Strategies with Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.19405 - What We Keep of What We Forget: Replacement Operators and Routing Semantics in Training-Free MoE Expert Pruning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41366 - TIRx: A Unified Tile Primitive ML Compiler Across Heterogeneous Backends Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.19092 - Spectral Condition for $\mu$P under Width-Depth Scaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.00541 - WASABI: Wasserstein Sampling via Bridge Interpolants Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41958 - CausalXRL: Explainable Reinforcement Learning through Causal Graph Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42028 - Sharp Non-Asymptotic Analysis of the Penalized Challenger in $\beta$-EB-TCI for Bernoulli Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01951 - $\nabla$Mimic: Ultra-Efficient Humanoid Control with Differentiable Simulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41654 - CodeLift: Your Test Suite Is Secretly a Dense SWE Curriculum Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17224 - Coarse-Graining Optimal Transport for Rollout-Free Post-Training of Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41269 - Adaptive Uncertainty Quantification on Simplicial Complexes with Conformalized Simplicial Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41166 - 4-Tensor Attention Model for Semantic Physical Reality Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11716 - Physics-Audited Agentic Discovery in Scientific Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.07379 - Towards Diverse and Comprehensive Benchmarks for Mutual Information Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.03487 - PrivacyFlow: Privacy in AI Agents through Information Flow Analysis and Consequence-Aware Risk Management Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40714 - Time Will Tell: Harness Time to Denoise Collaborative Filtering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.09181 - Evaluating Rollout-Verified Reinforcement Fine-Tuning of a Reasoning Model for Multi-Zone Variable-Air-Volume Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.27914 - ReBRAC-v2: The Return of the King Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.01205 - Simulation-free Unbalanced Dynamic Optimal Transport with General Growth Penalty Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04710 - When can Optimally Trained Transformers Achieve Near-Lossless Token Prediction for non-Markovian Data? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41038 - GENSTRAT: Toward a Science of Strategic Reasoning in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23238 - Statistical Foundations of Reinforcement Learning: A Non-Asymptotic Perspective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41903 - FOCUS: First-Order Control Using Optimal Transport Supervision for Imitation from Observations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41540 - Reliability-Weighted Direct Preference Optimization: Penalized Weights for Robust Preference Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41588 - New Lower Bounds for Private PAC Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41980 - Who Gets Watched? Allocating Scarce Escalation Resources on Pediatric Wards with Neural Index Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.22069 - Exact Theory and Optimal Stepsizes for Stochastic Gradient Descent in Smooth Convex Minimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42048 - Differential rank preservation manifold learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41107 - Are We Really Benchmarking Forecasting Models? The Impact of Preprocessing on Time Series Performance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09096 - In-Model Context Compression with Agentic Soft Tokens for Long-Horizon LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41291 - Fewer Heads, Fewer Memories: Pruning Redundant Attention Heads Suppresses Verbatim Memorisation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40974 - Benchmarking Forecasting Agents on Yesterday's Tomorrows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40940 - MOSAIC: Addressing Disproportionate Task-Modality Dependencies via Modality-Partitioned Gradient Routing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41004 - No Channels Left Behind: Understanding Diffusion Acceleration through Residual Gates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40914 - Anomalies as Residuals: Cauchy Displacement Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41387 - Chronos-2: A foundation model for multivariate time series forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41956 - Kernel-based Interpolatory Methods for Context Compression of Attention Mechanisms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40943 - Semantic Optimal Transport for Sparse Autoencoder Feature Matching and Circuit Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28567 - VisualSphinx: Large-Scale Synthetic Vision Logic Puzzles for RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.23977 - Text as an Index for Zero-Shot Cross-Domain Knowledge Tracing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41883 - A richness-sensitive Acoustic Biodiversity Index from species-level detections: classifier benchmarking, false-positive control and validation against standard soundscape indices in an African savanna and an urban zoo Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42042 - Li$^{2}$SAO: Lifting Light Singl-Rollout Asynchronous RL Optimization via Group-Relative Actor-Critic Bootstrapping Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40726 - Learning to Reason from Reference Samples Alone: Reinforced Adversarial Learning for Modern LLM Post-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38851 - bf16 Rounding Silently Discards Most RL Policy Updates: A Hidden Training-Inference Mismatch and an Unbiased One-Line Fix Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41073 - Implicit Assumptions About Tasks in Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41792 - When Is a Relation Worth Trusting? Manipulation Costs, Exposure, and the Trust Trap in Multi-Relational Graph Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37239 - Temporal speckle enables probabilistic weights for uncertainty-aware photonic AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.02217 - Predictive Maintenance at the Edge: An Embedded Anomaly Detection Pipeline Trained with Quantum Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40848 - Controllable User Simulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11519 - Binary Sparse Codes: Where are we on Energy Efficient Representations? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41933 - Hard Constraint Projection in a Physics Informed Neural Network (Burgers) Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42106 - Beyond Scarcity: When Encoder Adaptation Is Worthwhile Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41213 - Proof-Carrying Materials: Falsifiable Safety Certificates for Machine-Learned Interatomic Potentials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.12183 - AMMA: A Multi-Chiplet Memory-Centric Architecture for Low-Latency 1M Context Attention Serving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.26103 - Minimax Alternating Regret for the Experts Problem and Online Convex Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25182 - ElTab: Elastically Looped Tabular Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41819 - When the Past Shapes Action: Understanding Embodied Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41688 - SkillEvoLean: Mutation-enhanced skill evolution for Lean provers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01799 - A prospective randomized study of patient-centered AI for clinical visit preparation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41437 - Towards Out-of-Distribution Uncertainty Quantification for Machine-Learned Interatomic Potentials via Pre-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41801 - Task Vectors Can Be Linearly Decomposed into Interpretable and Controllable Components Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41743 - What Does a Harness Repair? Three Preregistered Studies Around a Longevity-Tuned Language Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05533 - LLINBO: Trustworthy LLM-in-the-Loop Bayesian Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.14756 - Riemannian Optimization on Unknown Manifolds via Stochastic Proximal Refinement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41379 - A Better Critic Matters for Distribution Matching Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42135 - HyCO: A Hybrid Neural Solver for Combinatorial Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07990 - Vision Transformer Ensembles for Panoramic Street Segmentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06063 - Locality-Controlled Out-of-Distribution Guidance for Robust Regulatory DNA Sequence Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41736 - A Controlled Comparison of Deep Learning Architectures for Multi-Horizon Financial Forecasting: Evidence from 918 Experiments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16886 - Towards Understanding Score-Seeking in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41014 - A Unified Matrix-Spectral Framework for Stability and Interpretability in Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01136 - CAP: Learning to Optimize from Sparse Observations of Related Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41173 - CalibCause: A Quality-Gated, Interpretable and Calibrated Deep Learning Framework for Diabetic Retinopathy Grading Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40699 - Cumulative Marginal Matching for One-Step Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34575 - INLA for Adaptive UAV Sampling of Radio Environment Maps in IoT Networks: Prior Width Governs Accuracy and Calibration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40723 - SPT-Flow: One Integration, Many Futures in Continuous-Time World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41273 - KV-Cache Patching: Tracing How and Where Fine-Tuned Behaviors Arise Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41480 - From Teleoperation to Long-Horizon Dexterity: Evaluating Visuomotor Skills and Offline Proxies for Dexterous Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40828 - A Function-Space Stability Boundary for Generalization in Interpolating Learning Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.03514 - Does Reasoning Make Language Models Agree? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41691 - A Learning Stability Profile for Finite-Dimensional Learning Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.21208 - Mage-VL-Cowork: A Full Training Recipe to Learn Hybrid Computer Use From Evolved Harnesses Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40747 - Toward Optimal Switching Regret for Multi-Armed Bandits with Oblivious Adversary Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.13547 - TSBPO: Tree-Structured Branching for Policy Optimization in Interactive Language Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41697 - When Less is More: The LLM Scaling Paradox in Context Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.09789 - Underdamped Stochastic Optimal Transport with Landauer boundary conditions: machine learning and analytical solution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41599 - Communication-Efficient Private Federated Reinforcement Learning with Post-Quantum Authentication for Vehicular Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41055 - Discrete Diffusion Models Exploit Asymmetry to Solve Lookahead Planning Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.19980 - On-device Detection of Wearer-induced NLOS on Chest-worn UWB Tags: Machine Learning, Link Indicators, or Both? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41799 - TalentRL: Strategy-Guided Reinforcement Learning for Hierarchical Skill Routing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41143 - Optimizing Anytime Reasoning via Budget Relative Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.13438 - Predicting Dose-Response Success from Primary Screening Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26538 - rl_rob: A transparent, from-scratch Python library for teaching reinforcement learning from tabular methods to deep policy gradients Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41303 - Don't Just Impute, Detect: Task-Aware Diffusion Pipelines for Edge Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40732 - Analyzing the Optimization Conflict Between Image- and Text-Based Person Re-Identification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02242 - From Representation to Readout: Mechanistic Analysis of Membership Signals in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41445 - Empirical Evaluation of Quantum Kernel Methods for Classification: A Comparative Study with Classical Kernels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42029 - Multiscale Supervised Unbalanced Optimal Transport Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16529 - Geometry as a Missing Axis of Representation Quality: The Variational Geometric Information Bottleneck under Data Scarcity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.02496 - The Geometry of Multitask Learning: Sharp Rates for Shared Subspace Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40713 - A Unified Framework for Probability Estimation of Data-Dependent Events Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41244 - When Everyone Can Build a Model: Mechanistic Inference in the Age of AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41454 - Automatic Construction of Strong Simple Baselines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40700 - On the Generation Order in GFlowNets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41648 - Co$^2$ODE: Conditionally Coarse-Grained Model Discovery for Rewiring in Biochemical Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41634 - Towards Universal Tabular Embeddings: A Benchmark Across Data Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.21696 - StrictPRMBench: A Replayable Evaluation Benchmark for Auditing Fixed-Score PRM Aggregation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41333 - MUON-RT Reusing the Teacher's Trajectory for Momentum-Free Muon for LLM Self-Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41104 - AIMER: Calibration-Free Task-Agnostic MoE Expert Pruning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18492 - Variational decomposition autoencoding improves disentanglement of latent representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.06844 - AquaProbe: Efficient Adaptation of Frozen Vision Models for Underwater Images Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40900 - Transferring Peptide-Target Interaction Patterns to Small Molecules by Joint Guidance for Diffusion and Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41322 - PCD: Predictive Coding Dynamics for Irregularly Sampled Time Series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41506 - Where, When, and How Many Bits? Scaling Laws for SGD with Stochastic Rounding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41074 - On k-nearest-neighbor regression in metric spaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41896 - A Constructive Orbit-Based Theory of Learnability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41641 - Learning Maximal Regions of Attraction on Compact Sets using Taylor Lyapunov Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2408.17246 - RC Prediction: A Python Package for Parameter-Aware Reservoir Computing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40984 - How Much Reconstruction Does Quantum Machine Learning Need? Late Fusion of Uncoupled Quantum Subcircuits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.05595 - Transport-Free Lower Bounds for Ollivier--Ricci Curvature in Higher-Order Networks: Scope, Tightness, and Computational Applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2405.13302 - Natural Language Actor-Critic: Scalable Off-Policy Learning in Language Space Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.04601 - Quantifying Concentration Phenomena of Mean-Field Transformers in the Low-Temperature Regime Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10931 - A Comprehensive View of Fairness through Distributional Stability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37061 - Overcoming the Representational Limitations of Amplitude Encoding for Quantum Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41824 - Fields of the Planet: Field Boundary Mapping Beyond 10m Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04449 - From the Zoo to the BULLPEN: Sample-Efficient LLM Profiling via Multi-Channel Model Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41375 - Satellite-derived bathymetry of Arabian Gulf ports under leakage-free validation: a multi-site benchmark of empirical, machine-learning and deep-learning models against 285,000 multibeam soundings, with an outlook for UAE waters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33609 - Accelerating Min-Max Optimization via Power-Law Stepsizes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01764 - Variance Reduction for Decentralized Stochastic Optimization with Multiple Local Updates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41927 - When Can Unlabeled Data Pools Replace Membership Queries? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41001 - EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18421 - Accelerated Dataflow: scaling inference in streaming data analytics with efficiency Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22731 - What Carries Architectural Signal? A Code-to-Architecture Mapping Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41628 - Windowed-MTP: Removing the Full-Context Draft-KV Tax at Million-Token Context Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.21535 - Cross-Fitted Clipped Covariance Estimation with a Data-Driven Tail-Energy Criterion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.14020 - Parabolic Positional Encoding: A Vision-Centric, Principled, Extrapolatable, and General Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01418 - Fully Offline Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.22442 - Frozen in Time: How a Physics Foundation Model Forgets Under Sim-to-Real Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40857 - Soft Mixture-of-Recursions: Going Deeper with Recursive Vision Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.00774 - TSFLab: A Self-Improving Agent-Agnostic Workbench for Time Series Forecasting Research Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40901 - Observable-Specific Validity Tests for Scientific AI: Controlled Approximations and Intervention Response Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41939 - D2ML: Models for Direct-to-Biology Small Molecule Screening Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41070 - Backpropagation-free Deep Learning for Time-Series Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41805 - Stochastic and Noisy Oracles in Smooth Continuous Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41086 - Inadvertent Context Leakage in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19857 - Co-optimization for Adaptive Conformal Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.01719 - FLAT: Smoothing the Rugged Landscape for Learnable, Sample-Efficient Traffic Calibration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04337 - Regret-Optimal Wasserstein-Robust Linear Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42109 - Unsupervised Feature Selection Using Local Intrinsic Dimensionality -- Extended Version Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40736 - Gluing Local Contexts into Global Meaning: A Sheaf-Theoretic Decomposition of Transformer Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17117 - MS-GPT: Rethinking MS/MS De Novo Structure Elucidation as Spectrum-Induced Posterior Querying of a Molecule-Language Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.23607 - Peeling the Matryoshka: Extracting Ontological Structure from Retrieval Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41785 - Instrument-Anchored LLM Judges Transfer Expert Counseling-Quality Ratings Across Three German Corpora Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08055 - Gradient Descent on Two ReLU Neurons: Global Landscape and Bifurcation Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42118 - AuditFL: A Contract-Backed Clearing Layer for Open Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41278 - MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.04217 - Towards Reliable, Scalable, and Value-Aligned Generative Recommendation for Large-Scale Advertising Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38378 - Bilevel ZOFO: Efficient LLM Fine-Tuning and Meta-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.03604 - Self-improving data synthesis can scale embedding-model adaptation across domains and tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14730 - Cyclical Entropy Eruption: Entropy Dynamics in Agent Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.27954 - Know When the Equation Is Wrong: Structural Uncertainty for LLM-Guided Symbolic Regression under Extrapolation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42024 - On the Origin and Evolution of Training-Inference Mismatch in LLM Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40945 - Robust-by-Design Distributional Learning from Contaminated Samples Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40884 - ORION: An Outcome-Driven LLM Advisor for RL-Based Multi-Domain 6G Slice Placement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41563 - An Agentic AI Workflow for Liver Lesion Segmentation and Structured Radiology Reporting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34599 - A Cross-Layered Multi-Drone Coordination for Medical Supply Delivery during Disaster Response Management Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09342 - On-Chain Behavioral Signatures for Classifying Centralized Exchange Addresses on Ethereum Using Proof-of-Reserves Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41888 - NECA: Neighbor Event Curve Augmentation for Multi-Horizon ICU Deterioration Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40420 - Less Loss, Fixed Weights: Logit Corrections for Forgetting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42000 - Near-Optimal First-Order Regret for Bandits with Feedback Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40861 - Shock Loading Accesses Reaction Pathways beyond Accelerated Thermolysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41955 - BYOD: Build Your Own DLM - Efficient Autoregressive-to-Diffusion Language Model Conversion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41574 - Leakage-Controlled Structure-Preserving Augmentation and Template-Aware Evaluation for Bangla Symptom-Based Disease Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41733 - Enhancing Medical Lesion Segmentation via Several Simple Modules Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41652 - A Unified XAI-NSAI Analytical Framework for Trustworthy IoT Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41424 - Step-wise Rubric Rewards for LLM Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.17291 - GraphTFactor: A graph-based approach for proteins transcription factor prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40867 - Can Personal Requirements Become Supervision for Planning? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40992 - Beyond IID: How General Are Tabular Foundation Models, Really? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.30410 - UpLoop: Training Looped Transformers via Upcycling at No Extra Pretraining Compute Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41720 - SATFRONT: Detecting Atmospheric Fronts with Satellite Data using Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42111 - FedPA-LoRA: Product-Aligned Framework for Mitigating Aggregation and Initialization Errors in Heterogeneous Federated LoRA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15381 - Exploring Bad Minima in Transfer Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41807 - Hyperbolic Inverse Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42104 - MILES-Rec: Uncovering Implicit Intents from Mobility Behaviors for Cross-Domain POI Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.41319 - Pix2Evidence: A Multimodal RAG System for Text and Visual Evidence Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.41335 - Defining Page-Centric Visual Document Retrieval and Evaluating Existing Benchmarks Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.41360 - FieldGuideRAG: Image-Grounded GraphRAG for Fine-Grained Recognition with Vision-Language Models Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.40971 - SpectRAG: Weighted Chunk Graphs for Token-Budgeted Context Selection in Multi-Hop Retrieval-Augmented Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.36991 - Prevented is Not Protected: What Attack Success Rate Hides about RAG Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.40742 - One-Step Retrieval Framework for Real-Time Sponsored Search Ads Using Hierarchical Text Representations Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.18296 - Context as Infrastructure: Knowledge Compilation for Retrieval in Agentic Systems with Harnesses Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.41172 - Recommendation Feedback Loops Shape Urban Income Segregation and Venue Visitation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.41911 - Completeness and Cost of Retrieval Structures for Multi-Tool Requests in LLM Agents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.41905 - Explain, Then Forget: Recommendation Unlearning under Asymmetric Access Constraint Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.40658 - EMAR: Efficient Multi-domain Adaptive Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2602.14960 - TileMaxSim: Roofline Regimes and Compression Limits for Fused GPU MaxSim Scoring Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2606.26439 - Retrieve-then-Disambiguate: Scalable Reviewer Discovery Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.40768 - How BERT-based Cross-Encoders Model Relevance in Information Retrieval? Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.41425 - KITE: Retrieval as a Decision Procedure for Long-Term Conversational Memory Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.41521 - Enhancing Knowledge Entity Relation Extraction in Abstracts and Full-text Content of Academic Articles Using Large Language Models Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.41552 - BrowseFlow: Sparse Event Flow Matching for Generative User Simulation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.41374 - Hierarchical Dual-Graph Retrieval for Long-form Audio Reasoning Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.41390 - WebOverlay: High-Throughput Vision-Only Distillation for Extreme Aspect-Ratio Web Overlay Detection Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.41037 - DeFT-RAG: Decomposing Multi-Hop Questions into Self-Contained Sub-Questions with Reusable Answers Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.37826 - Towards Trustworthy Multi-stakeholder Recommender Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.41674 - ProdCrawl: A Replayable Test Collection for Focused Crawling Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.40855 - Fidelity Synopses: Pre-Execution Plan Selection for Approximate Vector Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.41407 - ProSearch: Benchmarking Multi-Constraint Protocol Retrieval in Experimental Science Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.41396 - SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2603.07379 - GPUSparse: Fast and Exact Learned Sparse Retrieval on a GPU-Resident Inverted Index Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2606.26441 - Search When Needed, Proceed When Reliable: Metacognitive Reliability Supervision for Efficient Agentic Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.41738 - Your Spending Needs Attention: Modeling Financial Habits with Transformers Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2507.23267 - The Depth Flow of Token Representations Is Nonlinear and Does Not Descend Its Own Density Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29706 - Saidzoda-Tajik-LFM-2.6B: Adapting a 2.6B Hybrid Model to Tajik Tool Calling, and What Continued Pretraining Takes Away Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41576 - Robustness of Chatbot LLM Judgments of Presidential Actions and Hypothetical Reforms Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39398 - From Transcription to Reformulation: Defining and Benchmarking Grounded Generative Speech Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41292 - Stepwise-Querying: Distilling Reasoning without Access to Teacher Chain-of-Thought Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41769 - How Much Can Tool Calls Reveal About You? Privacy Leakage from Tool-Call Traces Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41885 - The No-Meaning Falsity: The Structural Impossibility of the Arbitrary Sign in Classical Arabic Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.07737 - Aligning MLLMs with the Latent Structure of Human Cognition via Behavior-Derived Semantic Dimensions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41951 - SCRBench: Beyond Equivalence Checking for Semantic Change Reasoning in Code Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41562 - GRIT: Gradient Masking for Visually Misgrounded Tokens in Text-Rich Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41629 - Agentic World Modeling for Agent Test-time Scaling without Environment Replica Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40927 - GraphNIAH: A Benchmark for Long-Context Reasoning over Real-World Graphs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41704 - Better Retrievers, Worse Labels: How Incomplete Relevance Judgments Distort Abstention Evaluation in Conversational RAG Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40966 - The Knowledge Layer Model (KLM): Evidence-Visible AI Output, Routing Diagnostics, and Negative Results Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42066 - AgentCollab: A Self-Evaluation-Driven Collaboration Paradigm for Efficient LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.26034 - Tracing the Influence of Retrieved Literature on Scientific Ideation in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39060 - Language Models Show Conformity Bias in RAG: When the Majority Endorses a Poisoned Claim Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41012 - Nedimo: An Evidence-Grounded Multilingual Pipeline for AI-Generated Sleep Stories Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40970 - Metacognitive Decoding: Efficient Inference for Diffusion Language Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37642 - EDU-Jev Training System-One Decision Models for Education Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41079 - Holistic Diversity Management in LLM-Guided Evolutionary Search Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38407 - Eroding the Truth-Default: A Causal Analysis of Human Susceptibility to Foundation Model Hallucinations and Disinformation in the Wild Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.22871 - DAMI: Dual-Axis Memory Initialization for Enhanced Long-Context Retrieval in Gated Linear Attention Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41994 - Do Open Language Models Invent Scripture? BILAL-BENCH: Benchmarking Islamic-Source Fabrication in Bengali Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40996 - Hybrid Computer Use: A Unified Programmatic, Semantic, and Visual Interface for General Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41432 - BlindToChange: AI Agents Can Find Changes When Asked But Do They Look When Needed? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41435 - The Generative Gap Between Speculative Drafter and Continuous Diffusion Language Model Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40847 - Beyond Response Scoring: An AI-aware Cognitive Supervision Framework for Automated Mathematical Short Answer Grading Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41215 - Subquadratic Attention with a Hierarchical Tree-Structured Indexer Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42112 - Capability-Grounded Agentic Planning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41040 - Table Serialization Determines Which Relations Language Models Preserve Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24798 - TRIDENT and SHAKTI: A Framework and Benchmark for Hindi AI-Text Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41232 - Where Is the "Self" of a Large Language Model? -- From Self-Index to Self-Reference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16717 - PersonaChatBench: Evaluating Chat Assistants with Diverse Simulated Users Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42060 - SOPO: Socratic Guided Policy Optimization for Span-Level Hallucination Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32212 - Qistas: A Pre-Registered, Portable Protocol for Fairness Evaluation of Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40893 - S2TDR: Structured Multimodal Reconstruction for Sticker-Aware Dialogue Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41176 - Keepace.ai: A Technical Report on a Large Language Model for Sports and Health Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38249 - TurnTurk-GPT: Text-Based Turn-Taking Prediction for Turkish Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42010 - When Support Crosses the Line: Evaluating Ethical Boundaries in LLM-Based Mental Health Support in the Chinese Context Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38452 - CoFiBreak: A Coarse-to-Fine Diversity Reward for Effective Multi-Turn Jailbreak Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40926 - Precision--Recall Trade-off on the Inference Level for LLMs in Grammatical Error Correction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41698 - Thinking Inertia: LLMs Keep Thinking When Told Not To Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11765 - Adapting LLM-SC to Living Sacred Heritage: Domain-Specific Extraction, Semantic Networks and Human Evaluation on Pashupatinath Temple Reviews Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35685 - CEFR Level Assessment across Languages and Text Granularities Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41553 - Enhancing Safety of Large Language Models via Embedding Space Separation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.20206 - VerifyMAS: Hypothesis Verification for Failure Attribution in LLM-based Multi-Agent Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.17467 - Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05927 - Iterated Integrals as Lexical Fingerprints: Path Signature Embeddings for Lexical Similarity Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41855 - From Association to Causation: Improving Retrieval Precision of Retrieval-Augmented Generation via Causal Relations and an Attention Mechanism Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21702 - Safin-1.5: Safety-Native Architecture and Verifiable Reasoning for Recursive Safety Improvement Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40751 - TamilEOT: A Dataset and Model for Semantic End-of-Turn Detection in Tamil Telephone Speech Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05631 - Optimal Multi-bit Generative Watermarking Schemes Under Worst-Case False-Alarm Constraints Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.08759 - TraceSpec: Understanding and Improving Speculative Decoding for LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41177 - Agentic Systems for Calibrating Cosmological Simulations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40685 - Language Models Show a "Women-Are-Wonderful" Effect in Blame Attribution That is Not Just Leniency Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41116 - Beyond the Black Box: Integrating Lexical and Semantic Methods in Quantitative Discourse Analysis with BERTopic Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.19099 - PsyInterviewee: Informational Invariance and Relational Adaptivity in Mental Health Interview Simulation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41289 - CogBattery: Human-Referenced Evaluation of Cognitive Task Behavior and Structure in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.24999 - Service, Solidarity, and Self-Help: A Comparative Topic Modeling Analysis of Community Unionism in the Boot and Shoe Union and Unite Community Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.01529 - Lineage Is Memory: Parent Inheritance and Feedback Disclosure in Short-Budget LLM-Guided Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41157 - Ctrl-G: Controlling Structural and Interaction Exposure in Knowledge Graph Augmented LLM Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.08739 - RangeSWA: Training-Free Length Extrapolation for Continuous Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42084 - Sparse Text Diffusion under Dual Budgets: Context Connectivity and Expert Activation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41487 - Beyond Public Access in LLM Pre-Training Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.00020 - SimXAI: A Simple Drop-in Layer Increases Interaction Quality and Understanding in Conversational XAI Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41856 - Exploring the potential and limitations of Model Merging for Multi-Domain Adaptation in ASR Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.05354 - Comparative Evaluation of LLM-Based Review Paradigms for Academic Paper Quality Assessment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41391 - Flide: Accelerating Decision Inference with Exact State Forking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42148 - CRoS: Causality Reward on Scrambled CoTs Improves Accuracy and Reasoning Faithfulness Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42054 - When Steering Shifts Discourse: Identifying and Intervening on Discourse-Level Changes due to Activation Steering in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41661 - MedResearcher-R1: Expert-Level Medical Deep Researcher via A Knowledge-Informed Trajectory Synthesis Framework Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.14880 - SciGraphSelect: Auditable Scientific Data Selection through Knowledge--Reasoning Graphs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41280 - Can Humans Tell? A Dual-Axis Study of Human Perception of LLM-Generated News Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.03755 - A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.16548 - HyperRepair: Recovering Forgotten General Capabilities of Fine-Tuned Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41147 - Unlimited OCR Works 2 Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39308 - SERIAL-7: Deriving, Realizing, and Preserving Machine-Verifiable Outputs Across Representations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41308 - Adaptive Personalization Under Preference Epistemic Uncertainty Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40930 - Incongruence-Aware Evaluation of Multimodal Speech Emotion Recognition in Audio Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40883 - Asynchronous Flow Map Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42018 - The psychophysics of affect in large language models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40985 - DecisionRank: On-Policy Distillation for Decision-Model Rerankers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42128 - KEEPER: Learning Control-Sufficient Textual Memory for Long-Horizon LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41482 - Digital sovereignty in professional translation workflows: a case study of migrating from Windows to Linux Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41561 - Imputation of Public Opinion Data with Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09351 - Accept Changes, Reject Attacks: Robust Memory Management for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41056 - Verify--Backtrack Loop: Structured Precondition Recovery for Long-Horizon Language Agents Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.41564 - Using Machine Learning to Measure Self-Efficacy Belief Through Learners' Interaction Traces in Technology-Enhanced Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41900 - Learning to Interact and Direct: Co-Evolving Video Director Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41865 - Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42147 - TradeWar: A Benchmark for Execution-Grounded Trade Negotiation with Adaptive LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42004 - Risk-Sensitive Mission Planning for Multi-Target On-Orbit Inspection via Distributional Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41647 - When Does Test-Time Search Help World Action Models? An Empirical Audit of Candidate Selection and Simulator Integrity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41970 - ReX-GG: a LLM Ensemble Pipeline for Relation-extraction and Graph Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41901 - Advancing Clinical Trial Outcome Prediction with Domain-Specific Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41710 - Real Computation or Merely Naming? A Pre-Registered Mechanism Audit of 25 Cognitive-Architecture Modules in an LLM-Based Agent System Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41604 - BABA-Bench: Evaluating Long-Horizon Patient-Advocacy Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41076 - Researcher-in-the-Loop Evolutionary Discovery of Entanglement-Assisted Quantum Code Families Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41183 - Rome Wasn't Built in One Turn: Replay-Grounded Reward Signals for Long-Horizon Freeciv Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41264 - Hear No Evil: Detecting Gradient Leakage by Malicious Servers in Federated Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.20651 - Beyond Plausible Prediction: Safety Sufficiency in Web World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40798 - Chance-Constrained Inspection Viewpoint Sequencing for On-Orbit Servicing via Safe Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41639 - Subliminal Reinforcement Learning: traits travel through a judge's scores Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41301 - DiRAFT: Privacy-Aware Financial Transcript Synthesis from Aggregate Discourse Priors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40938 - ChatGPT as a Surveillance Assistant? An Exploratory Case Study of AI-Assisted Surveillance Risks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40890 - RTL-Interact: Training EDA-Interactive Models for Multi-Task RTL Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41225 - Confident Fools or Careful Searchers? A Behavioural Study of When LLMs Search Beyond Their Static Internal Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41124 - Optimization Techniques for Solving the Minimum Red--Blue Separating Set Problem with an Application to Human--AI Text Separation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41081 - Payroll Fraud Detection in Synthetic HR/ERP Graphs: An Inductive Comparison of Rules, Path Features, and Graph Neural Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41085 - ROSTrans: Empirically Benchmarking LLMs for ROS1-to-ROS2 Migration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41168 - Dreams Are Cheaper Than Flights: Curated World-Model Data Improves Aerial Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41030 - Counterfactual Pairwise Augmentation Improves Small Pointwise LLM Judges Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41149 - RECAST: REconstruction of Chain-of-Thought via Auditable Structured Traces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41813 - LEAP: Efficient LLM Inference Scheduling with Generalizable Length Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41359 - ARK: Avoiding Routing Collisions for KV Cache Transfer in Disaggregated LLM Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41160 - Dynamical Memory Transformer: Selective Recurrent Memories with Constant Cost Attention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41850 - Towards Portable Specification of the Agent Harness Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40917 - QUAL: Quantile Alignment Improves Zero-Shot Time-Series Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41100 - ImplicitHop: Evaluating knowledge integration across context and memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41169 - P-ContextBench: From Personal Fact Recall to Personalized Agent Behavior Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40959 - ACCT: Asymmetric Cross-LLM Context Transfer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42116 - Self-Improvement with Auxiliary Rewards: Learning from Verified Traces and Evaluating Transfer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41296 - LanG 2.0: Energy-Efficient Agentic AI for Semi-Automated Security Operations at Scale Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41072 - Structure-Aware Skill Retrieval and Arbitration for Optimization Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41909 - Leaner Training, Lower Leakage: Revisiting Memorization in LLM Fine-Tuning with LoRA Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.20856 - ReuScope: Auditing Data Reuse and Evaluation Sensitivity in Capsule Vision 2024 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41835 - From 1D Benchmarks to Complex 3D Geometries: Can Agents Reliably Specify Problems for Automated PDE Simulation? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41267 - "Shall We Approve?" Consequence-Aware Approval for Autonomous Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40753 - Circumventing the Computational Hardness of Computational Arbitrage Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40831 - MEMIG: Self-evolving Memory Construction for Antibody Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41245 - LLM Detoxification via Transition-Aware Reward-Guided Representation Sampling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41165 - Does Recursive Knowledge Construction Help Agents Verify Consensus Claims in Science? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40906 - Clinical-Protocol-Aware Cyber Resilience for Connected Clinical Technologies Under AI-Enabled Adversarial Conditions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41784 - Patch-Based Deep Kernel Learning for Data Assimilation and Bias Correction with Extremely Sparse Observations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41596 - Specification-Guided Generation for Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41511 - Automated Keyword Generation Using LLMs in a High-Volume Data Virtualization Service Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.41893 - Verifying Text-to-SQL Queries under Changing Business Semantics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41090 - STAR: Steering Action Representations during Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41009 - What Should LLMs Forget: Reinforcement Unlearning of Knowledge Associations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41616 - Breaking Information Islands in Sparse Tuning via Small-World Connectivity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41665 - Online Evidence-Containment Prediction over Text Spans under Distinct Queries Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41384 - scAnyOmics: Foundation-Model Distillation for Any-to-Any Completion of Multi-omics Virtual Cells Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41399 - Do Transaction Prices Reflect Visual Preference? A Diagnostic Study with Multimodal Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41358 - Radial Kernel Attention for Long-Range Modeling in Polymer Machine Learning Force Fields Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41675 - CIRCE Divines LLM Task Complexity from Constraint Structure Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41089 - Predicting Human-Gain Curves under Local Proxy Optimization from Repeated Ratings Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41114 - Prune Gradually, Adapt Sparsely: Efficient Pruning of Large Language Models at Extreme Sparsity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41968 - Violet Teaming in Practice: Lessons from a Pilot Expert Workshop on Governing Complex AI Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41018 - MetaVul: Agentic Harness Discovery for Vulnerability Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40721 - One Verdict Is Not Enough: Regression Testing Learned World Models and Their Test Harnesses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41130 - More Rules, Longer Lists? Benchmarking Self-Evolving Agents on a Hidden-Rule Curriculum Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40758 - Connectivity-Aware Client Selection in Decentralized Federated Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41570 - Fuzzy selective state model for forecasting the dynamics of consumer preferences Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41879 - Multimodal In-Context Learning with Explicit Rule Induction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41754 - Experts Exhibit Structured Redundancy: Structure-Preserving Expert Pruning for Mixture-of-Experts Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41236 - Multi-Test Nation Bias Benchmarking of LLMs with Explicit Unbiased Baselines Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41486 - The First Few Tokens Matter: Understanding Chain-of-Thought Controllability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40939 - ID2Pattern: Pretraining Generalizable Identity Behavior Patterns for Transaction Risk Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41988 - Whose Values, Which Contexts, and What Signals? Grounding Cultural Value Alignment with Re3Culture Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41793 - Characterizing LLM Agent Behaviors in Module Shadowing Environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40716 - FrontierMat: Benchmarking Language Models at the Frontier of Materials R&D Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41162 - When Disclosure Is Compulsory: Evaluating Ride-Hailing Rebalancing Policies with Self-Interested LLM Driver Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41132 - When Should AI Agents Ask? Clarification Requests Under Limited Human Attention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41129 - Sensorium: An Open-Source Multimodal Data Collection and Curation Library for Embodied Surgical AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41946 - Lifelong Learning of Scheduling Rules with Surrogate-assisted Genetic Programming for Dynamic Flexible Job Shop Scheduling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41158 - Calibration of Large Model Quantization based on HiFloat4 Format Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41112 - Ask on Demand: Targeted Peer Communication for Parallel Agentic Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41378 - CLIC: Closed-Loop Intent Consistency for Securing LLM-Driven Control in Open RAN Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40744 - Cross-Interface Authorization for AI Computer-Use Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41397 - Evidence-Guided Recovery for AI Agents with Ambiguous Tool Outcomes and Partial Execution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41453 - RiskyPy: Toward Model-Calibrated Prompt Generation for Joint Security and Functionality Evaluation of LLM-Generated Code Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40735 - EvoMCP: Co-evolving MCP agents and training data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41479 - CausalWAM: Learning the Causes of Actions in World Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42096 - Same Question, Different Answers: Auditing Persona-Dependent Variation in Six LLMs on Smoking-Cessation Advice Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42039 - ReplayRCA: Measuring Post-hoc Diagnosis and Live Oversight of Agent Failures by Counterfactual Replay Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41025 - RECITE: Revising Eligibility Criteria Incorporating Textual Evidence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41368 - CryoAtlas: A Large Curated Dataset and Unified Benchmark for Cryo-EM Atomic Model Building Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41411