TILens Daily Edition 2026-09-24 Filters: topic=ai-research, github=hidden Stats: 622 articles, 8 sources, 612 research papers Top topics: AI, AI Research, Information Retrieval ## News - AI Agents Are Now Operating Enterprise Networks. Trust Sets the Limits. Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/cisco-agentic-ai-network-operations-autonomy/ - Claude Opus 5.5 Broke Our GPT-6 Benchmark Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/claude-opus-5-5-gpt-6-sol-livestream-benchmark/ - Meta’s Big AI Bet Now Fits on Your Keychain Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/metas-big-ai-bet-now-fits-on-your-keychain/ - True Positive Weekly #179 Source: true-positive-weekly Topic: AI (+AI Research) URL: https://aiweekly.substack.com/p/true-positive-weekly-179 - 😺 LIVE IN 5: GPT-6 Sol vs. Claude Opus 5.5 Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/live-gpt-6-sol-vs-claude-opus-5-5-round-2/ - Who Made Space Bunny? A MiniMax Clue Sharpens the Mystery Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/blog/who-made-space-bunny-minimax-clue/ - Adobe Wants Its Tools Wherever Your Next Project Starts Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/adobe-tools-gemini-claude-premiere-android/ - Jensen Huang’s AI Safety Rule: If You Can’t Evaluate It, Don’t Ship It Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/jensen-huang-ai-safety-dont-ship-what-you-cant-evaluate/ - 😺 What 950 Claude agents found Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/what-950-claude-agents-found/ - I made a Jev competitor Source: true-positive-weekly Topic: AI (+AI Research) URL: https://aiweekly.substack.com/p/i-made-a-jev-competitor ## Research - Automating coherent long-form video generation Source: google-research-blog Topic: AI Labs (+AI, AI Research) URL: https://research.google/blog/coherent-long-form-video-generation/ - How to Maximize Your Coding Agent Subscriptions Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/how-to-maximize-your-coding-agent-subscriptions/ - Beyond RAGs: Building Actually Truthful AI Harnesses Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/beyond-rags-building-actually-truthful-ai-harnesses/ - Towards Spec-Driven Test Automation: Part 1 Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/towards-spec-driven-test-automation-part-1/ - When the Correct Answer Is Nothing, What Does Your Pipeline Return? Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/when-the-correct-answer-is-nothing-what-does-your-pipeline-return/ - Value Mirror Descent for Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.06039 - Parameter Importance-Driven Continual Learning for Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.15375 - Scalable Subgraph Sampling via Resistance Curvature Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27209 - When Post-Processing Fairness Constraints Help and When They Harm: Evidence from Eight Cross-Domain Evaluations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26955 - hyperbolix: Hyperbolic Deep Learning in JAX Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28248 - MLSkip: Data Skipping for ML Filters via Lightweight Metadata Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03946 - Marginally Correct Tool Caches Can Reverse Group-Normalized Policy Updates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26866 - EvEMTBench: An Open Benchmark for Machine Learning in Power System Protection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28149 - VCMM: Variance-Calibrated Momentum for Multimodal Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27577 - TransBERT: A Framework for Synthetic Translation in Domain-Specific Language Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26347 - Variance Reduction for Independent Metropolis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.17699 - Finite-Sample Probabilistic Safety Certification for AI-Based Grid-Edge Coordination Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28182 - ForgetMimic: Motion Unlearning for Reinforcement Learning Humanoid Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28378 - Energy-guided Recursive Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.10128 - NPBoost: Neural Processes with Gradient-Boosted Fixed Effects Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28122 - Log-Depth Recurrent Language Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28212 - "What's That Sound?": A Versatile, Robust, and Lightweight Convolutional Transformer for Environment Sound Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27762 - A 3D-Printable Dataset for Fair Testing and Comparisons of Tactile Sensors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.25886 - QVAC Genesis III: A Large-Scale, High-Quality Open Synthetic STEM Corpus for Efficient Language Model Pre-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19513 - Repurposing Pre-trained LLMs as High Fidelity Continuous Text Autoencoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27248 - PHONOS: PHOnetic Neutralization for Online Streaming Applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.27001 - Honest and Reliable Evaluation and Expert Equivalence Testing of Automated Neonatal Seizure Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.04899 - WTF?! Simulation-Free Reinforcement Learning with Wasserstein-Tilted Flow Maps Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27033 - Localized Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.04417 - Visual Tripwires: Anticipating Failure in Deep Vision Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28099 - From Sentiment Classification to Actionable and Responsible Feedback: A Scoping Review and Evidence Map of NLP in Student Evaluation of Teaching, 2015-2026 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27939 - Assessing the impact of dimensionality reduction on clustering performance - a systematic study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.22099 - ZO-COSMO: Index-Free One-Hop Mixing for Decentralized Zeroth-Order Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27199 - EBRL: Asynchronous Embodied RL by Multi-Grained Resource Management Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27547 - Discovery of fully efficient fault indicators along a data-based diagnosis process Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28087 - Distillation for Efficient Multitask Manipulation Policies via Conditional Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28107 - Simultaneous Latent Budget Trees for Stratified Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.13295 - PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.12171 - Less Language, More Latents: Annotation-Efficient VLAs for Driving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27747 - KITE: KV-Invariant Transformer Expansion for Efficient Agentic LLM Scaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27294 - VMMU: A Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.13680 - Scaling of Capability and Efficiency at Inference Time in Large Reasoning Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27166 - CS-WCP: Robust Conformal Sets for LLM-Judge Traffic Shifts with Uncertain Group Proportions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27955 - Efficient Linear Bandits via Cluster-Aware Sketching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27594 - VertexCBF: Improving Neural Control Barrier Functions via Vertex-Restricted Control Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.12831 - Task-Aware QUBO Allocation for Mixed-Precision Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22238 - Learning to Approximate Uniform Facility Location via Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.13155 - Fed-ReMasker: Federated Tabular Imputation under Feature-Level Missingness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28105 - SWE-Proof: Can Language Models Resolve Real-World Issues with Machine-Checked Proofs? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21190 - CAST: Context- and Anomaly Structure-Conditioned Time Series Anomaly Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27825 - Predicting Quantization Price for Selecting PTQ Configurations Before Deployment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28270 - A Foundation Model for Instruction-Conditioned In-Context Time Series Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.22586 - Rolling Conformal Prediction in Sequential Model Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26951 - A rubric-based controlled comparison of frontier language models on expert-authored clinical reasoning tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.02175 - Evaluating Open-Weight LLMs for Turkish Domain Documents Under Retrieval and Hardware Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28007 - Nonequilibrium Phases of Repulsive Self-Attention: Chaos, Attention Condensation, and Emergent Locality Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28448 - Self-Improvement as Coherence Optimization: A Theoretical Account Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.13566 - CVaR anchor regression protects against rare shifts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27034 - PEARL: A Lightweight Prompt-based Feature Interpreter Framework for Real-Time, Anonymous, and Heterogeneous Collaborative Perception Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27123 - TiAb Review Plugin: A Browser-Based Tool for AI-Assisted Study Selection in Systematic Reviews Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.08602 - DeliveryGym: An RL Environment for Long-Horizon Embodied Agent Planning with Adaptive Curriculum Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19801 - Agent-Editing World Model: Rethinking World Modeling for LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28416 - PhyMo: A Physical-Field Modality for Multimodal AI4Physics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27554 - Memory Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28399 - An Adaptive Machine Learning Framework for Fluid Flow in Dual-Network Porous Media Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.19561 - A Very Big Video Reasoning Suite Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.20159 - LWCal: Loss-Weighted Calibration for Tabular Classifiers with Noisy Calibration Labels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26839 - Probabilistic and Geometry Aware Neural Surrogate of Scrape Off Layer Plasma Simulations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28116 - Untangling the Geometry and Speed for RF Sensing Spectrograms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26960 - Private Decentralized Optimization with Noise Reduction and Bias Correction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27658 - ProteinJEPA: Latent prediction improves protein language model pretraining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07554 - Same Outcome, Different Readout: What Does a Steerable Valence Direction in LLMs Represent? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22850 - Evolving Inspectable O-RAN Slicing xApps with LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27337 - Signal2Symbol: Neuro-Symbolic Temporal Reasoning for Explainable Physiological Time-Series Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26820 - Optimization without Future Compromises? Decentralized Coordination via Collective and Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.18088 - QUARTET: Quad-branch cross-Attention and Random-walk Traces for Enhancing Transformers on Relational Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26855 - Fine-Tune, Then Rectify Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.19486 - Active Learning for Biodiversity Monitoring: From Label Efficiency to Reliable Ecological Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27409 - SMT-Based Active Learning of Weighted Automata Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07758 - Quantum Reinforcement Learning for Cost and Delay Tradeoffs in Quantum Cloud Orchestration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27446 - Pheno-GS: Phenoscape-scale Geodesic Sinkhorn Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27633 - Experts Rise Where LLMs Disagree: Using Cross-Model Disagreement to Target Expert Effort in LLM Codebook Revision for Large-Scale Annotation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26926 - Transferable Evidence Reconstruction for Longitudinal Glucose Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28199 - Feed the Panel Dimensions, Not Verdicts: Rubric-Decomposed Fusion of Vision-Language Aesthetic Judges Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27110 - Robustness of Diffusion Models under Distribution Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27546 - PISCES: Physics-Informed Solar-wind Convolutional autoEncoder for Space-weather Anomaly Detection and Early Warning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28022 - Reliable Fusion of Conflicting Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27913 - Parameter-Efficient Construction of the Rashomon Slice for Concept Bottleneck Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.19636 - Sharp Convergence of Wasserstein Gradient Flows for Spectrally Nonnegative Interaction Energies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27008 - The Recall Ceiling of LLM Recommendation Reranking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27953 - Exact Minimax One-Bit Unbiased Compression: Heavy-Tail Necessity and Finite-Randomness Approximation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27860 - Modular Norm RandOpt: Population-Efficient Ensembling through Architecture-Aware Perturbations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.25745 - False-science induction in autonomous scientific discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27883 - Minimal-Norm Univariate Two-Layer ReLU Classification: Exact Solutions and Global Optimality with Skip Connections Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28438 - On Preference Coverage Collapse from Hindsight Relabeling in Multi-Objective Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26918 - What Converges in the Platonic Representation Hypothesis? Structure over Geometry Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27252 - Dual-GNN Multilevel Coarsening for Maximum Independent Set Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.25149 - Tail-Aware Geometry Learning for Conformal Ellipsoids Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27221 - Federated Learning for Distributed CNC Tool Wear Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11281 - SoLiD26: A First Principles Solid-Liquid Interface Dataset for Machine-learned Interatomic Potentials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28013 - Softmax gradient policy for variance minimization and risk-averse multi armed bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.00241 - Anomaly-Free Self-Optimization via AUC Bounds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27362 - Learning Where to Look: A Shared Relative-Alignment Module for Time-Series Forecasting and PPG-to-Vital-Sign Reconstruction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27473 - Learning Local Heterogeneity and Cross-Region Context for Large-Scale Traffic Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27637 - Anon: Extrapolating Adaptivity Beyond SGD and Adam Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.02317 - Hidden not Deleted: How Networks Suppress Entangled Features Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27593 - Role of scrambling and noise in temporal information processing with quantum systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.10080 - tidyHEBO: Robust General-Purpose Bayesian Optimization with Model-Consistent Warping and Pareto Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.10669 - The Truncation Blind Spot: How Decoding Strategies Systematically Exclude Human-Like Token Choices Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18482 - Uni-LaDiR: Latent Diffusion Unifies Multimodal Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19878 - ANO: Robust Policy Optimization via Bounded, Redescending Gain Fields Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.02320 - From Reasoning Strings to Partial Orders: Verifier-Certified Rule Transport through Quotient Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27833 - COPE: Continual Personalization of LLMs under Sparse User Feedback via User Embeddings and Self-Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26853 - Integrated Multivariate Segmentation Tree for Heterogeneous Credit Data Analysis in Small- and Medium-Sized Enterprises Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.00550 - Confidence Falls Short: Asymmetric Certainty Gains from Optimization Hinder Multimodal Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28165 - Resource-Efficient Distributed Recursive Gaussian Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26979 - GeoRVQ: Decoder-aware geometry for residual-token prediction in physiological signals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27018 - Silent Failures Beyond the 32-Bit Index Range: A Differential Characterization of Large-Tensor Matrix Multiplication in PyTorch's MPS Backend Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22991 - NS-ATTENTION: Newton-Schulz Transformations of Attention Outputs in Vision Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27735 - Contrastive Learning for Authorship Verification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28471 - Reinforcement Learning with Decomposed Subtasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27035 - SR-Fraud: An Outcome-Supervised Reflective LLM Agent Framework for Non-Stationary Payment Fraud Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27287 - Risk-Controlled KV-Cache Eviction: From Memory Budgets to Risk Targets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27981 - Stable Neural Decoding Across Sessions via Task-Conditioned Latent Alignment for Brain-Machine Interfaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27441 - Does Graph Structure Earn Its Place in Microservice Root-Cause Analysis? A Controlled Study on RCAEval, and What the Benchmark Was Really Measuring Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27069 - Forecast Workflow Bench: Evaluating Language-Model Decisions with Budgeted Forecast Tools Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27385 - Type-II Error Bounds for Test Supermartingales from Lower-Tail Hypotheses Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27766 - Task-Induced Riemannian Metrics for Vision Transformer Feature Spaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27988 - Judge Circuits Explain Format-Induced Inconsistency in LLM-as-a-Judge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16023 - The Like Trap: Multi-Stage Poisoning against Agents in Similarity-based Recommendation Systems Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.27155 - Context-Continuous Preference Learning for Exoskeleton Personalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28427 - DCRL: Decoupling and Coupling Reinforcement Learning via Policy-Reward Manifold Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27572 - World Models for Cross-Machine CNC Transfer under Partial Sensor Overlap Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.16071 - Agora: Git as Shared Memory for Collective AutoResearch Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18094 - Prediction with Expert Advice: Anytime Regret with Many Experts Matches the Fixed-Time Constant Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27206 - ChronosAttack: Adversarial Tool Scheduling Attacks on LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27857 - On-Policy Distillation with Curriculum Turn-level Guidance for Multi-turn Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.15912 - KATOsuper: Surrogate-accelerated neural topology optimization with sensitivity-consistent Fourier neural operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27216 - GlyRAG: Context-Aware Retrieval-Augmented Framework for Blood Glucose Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.05353 - M3D-Net: Hierarchical Coordination of Spatial Context, Feature Reuse, and Differential Attention for Mammography Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27523 - Query Implied Generative Engine Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27845 - Locally Private Inference for Riemannian Stochastic Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22642 - How Sensitive Are LLM Leaderboard Claims to Hidden Model Selection? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28177 - Weighted Quantum Signal Processing: Low-Depth Polynomial Approximation with Applications to Kolmogorov-Arnold Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21567 - NGN: Learning Neural Network Size as a Differentiable Count Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27291 - Support-Compiled Feature Folding: More Evidence at Lower Memory Across Tabular Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28208 - A lift for input-convex neural net training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24274 - Learning the Cost of Reliable Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28322 - Evaluation Choices Decide the Forecasting Leaderboard: Evidence from a Production Marketplace Panel Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27867 - Regular Fourier Features for Nonstationary Gaussian Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.23006 - TNLearn: An Open Source Python Package for Task-based Neurons Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27564 - On the Sample Complexity of Active Learning with Membership Queries Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27241 - Multitask Regression with Pairwise Fusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27280 - FairTest: Search-Based Fairness Testing for Multi-Agent Reinforcement Learning Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27309 - Tensor Decomposition of Transformer Key-Value Caches: Spectral Structure and Format Comparison Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28029 - Starter-Iterator Neural Operator: A Unified Architecture for High-Fidelity Forward and Inverse PDE Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18305 - Does Step Law Transfer to Small-Scale Language Models? An Empirical Recalibration Below 59M Parameters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27581 - ChipMEM: Verification-Grounded Memory for EDA Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27067 - Local Evidence and Geometric Readout Repair in Trained GNNs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27092 - Learning to Remember: Attentive Reinforcement Learning for Edge Serverless Autoscaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.28790 - Turning Safety into Competence: Minimally Exploitable Robot Policies via Safety-Filtered Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27312 - Advances in Diffusion-Based Generative Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.18932 - Learning Informative Prior with Infinite-Dimensional Continuous Normalizing Flow for Bayesian Inverse Problem Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03343 - FFM-CP: Cross-Backbone Fusion of Vision-Language Foundation Models for Few-Shot Computational Pathology Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27710 - Random Polytope Descriptors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2009.13987 - Graph Learning with Spectral Connectivity Priors for Scarce Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27278 - Discrete Diffusion Models via Evolving Variational Autoregressive Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27306 - Unifying Physical Backpropagation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11585 - DeltaS: Reading the Gated Linear Attention State for KV Cache Eviction in Streaming Video Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27470 - AdaDim: Dimensionality Adaptation for SSL Representational Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.12576 - ASCIIBench: Evaluating Language-Model-Based Understanding of Visually-Oriented Text Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.04125 - A Parameter-Free Few-Shot Evaluation for Elephant Vocalisation Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14824 - SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26780 - When Labels Are Scarce: An Oscillatory State Space Model for Vibration Diagnosis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27411 - Tight Regret Bound for Online Inverse Linear Optimization via Multiscale Matrix Weights Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26978 - InsurTech innovation using natural language processing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.21112 - Live Assistant: Learning Whether, When, and Whom to Assist in Real-World Live Social Streams Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27303 - Quantum score matching with applications to learning thermal states Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28391 - The Computational Value of Sensory-Aligned Receptive Fields Depends on Neuronal Expressivity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26940 - Conformal Bayes under Continuous Label Shift: Sensitivity Analysis and the Limits of Exact Validity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27976 - Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.21653 - On the Diffusibility of High-Dimensional Latents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28473 - Spread and Scale: What Determines Whether Test-Time Budget Allocation Pays Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27917 - Non-Commutative State Tracking with Input-Dependent Low-Rank Updates in Mamba-3 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28273 - Small Cues, Big Consequences: Learning Pivotal Cues for Multimodal Meme Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26907 - ChronoSteer: Bridging Large Language Model and Time Series Foundation Model via Synthetic Cross-Modal Alignment Dataset Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.10083 - Path Regularization: A Near-Complete and Optimal Nonasymptotic Generalization Theory for Multilayer Neural Networks and Double Descent Phenomenon Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.02129 - Safety Nudges: User-Facing Interventions for Real-Time AI Risk Awareness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26865 - Intervention, Not Shared Latents: Blocking Visual Shortcuts in Audio-Video Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22361 - Counterfactual Constraint-Conditioned On-Policy Distillation for Multi-Constraint Instruction Following Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27421 - Memory Is Not Always Needed: Characterizing Conditional Memory in Scientific Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23982 - Limiting-Kernel Q($\lambda$): Bridging Short and Long Horizons Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27741 - CORE-STACK+: Meta-Learning for Deep Stacked Generalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26905 - A Discrepancy-Based Perspective on Dataset Condensation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.10367 - Repairability of Inexact Solvers in Recursive State Estimation with Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28425 - A Hybrid Iterative Deep Ritz Method for Elliptic Interface Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27325 - A Systematic Benchmark of Explainable Methods for Temporal Attribution in Sequential Recommendation Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27201 - FastManly: An EM-Gradient Algorithm for Manly Mixture Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.00848 - What Makes a Terminal-Bench Task Hard? Separating Genuine Hardness from Fake-Hardness on an Adjudicated Agentic Corpus Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26826 - MENO: Memory-Efficient Neural Operator Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27739 - SPIBER: Reconstructing Free Energy Landscapes from Short, Unconverged Trajectories with Generative Flow Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22663 - The Drift Contract: Spectral Updates for Depth-Robust Local Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26811 - Fitting Large Nonlinear Mixed Effects Models Using Variational Expectation Maximization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.26160 - WhatWorkedBench: Benchmarking Experimental Understanding in AI Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27490 - Noise-Induced Predictability Redistribution Across Forecast Horizons of Extreme Events in Chaotic Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27877 - ProCredit: From Outcome Rewards to Progress Credit in Agentic Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27532 - Inverse Problems Conditioned on Observation Ensembles: Applications and Methods Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.22029 - On Basis Function Selection for Sparse Gaussian Process Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26624 - Global tree forecasters collapse at the hierarchical aggregate: a five-panel failure characterization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27912 - A Scaling Study for fMRI Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27232 - From Concept Alignment to Causal Grounding: An Intervention Test of Chain-of-Thought Faithfulness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23065 - Exact Quantile Balancing and Load-Error Injection for Mixture-of-Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28053 - The Chandra-Gaia Catalog of Counterparts: Resolving ambiguous Gaia matches to X-ray sources in the Chandra Source Catalog using Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.19329 - PBLH Estimation from Satellite Radiances via a Dual-Encoder Transformer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28286 - TabPFN-3.5: Technical Report Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17895 - Shared Global KV with Layer-Specific Local History Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28006 - Local Geometric Mixing via Dobrushin Contraction with Applications to Diffusion Path Monte Carlo and the Proximal Sampler Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28338 - What Changed? Drift Detection with Real, Virtual, and Incomparable Diagnosis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27865 - When Accuracy Gaps Fail to Certify: Auditing Cross-Domain Recalibration of LLM Judges Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27954 - Artificial intelligence surrogates for treatment effect estimation with before-and-after data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27180 - I-SplineFlow: Learning Monotone Spline Stochastic Interpolant Schedulers for Few-Step Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27963 - Even Sharper Bounds for Transductive Learning and Its Applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28459 - Variational Bayesian Flow Network for Graph Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.22524 - Safe learning-based control via function-based uncertainty quantification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.01173 - Transfer Learning with Conformalized Quantile Regression for Solar PV Forecasting Under Load-Shedding-Driven Data Scarcity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26959 - Discover, Falsify, Revise: Auditing Input-Use Claims from Source Code to Predictive Contribution in Agent-Discovered Cell Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27234 - What Do Tabular Foundation Models Compute In Context? In-Situ Representation Refinement through Attention-Gated Updates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27679 - Crossflow: Prefill-Decode Elasticity for Agentic LLM Serving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27085 - Physiologically Informed Digital Auscultation for Pneumonia Detection in Long-term Care Residents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27222 - Helping Customers in Distress: An LLM-powered Agent that Converses, Probes, and Routes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16268 - Semantic Self-Distillation for Language Model Uncertainty Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.04577 - Quality over Quantity: Semi-Supervised Detection of Illicit Bitcoin Flows via Feature Engineering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27936 - LexLattice: Multilingual Extractive Summarization via Neural Cellular Automata on Document Hierarchies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27032 - A Shared Encoder Is Not a Shared Task: Conditional Comparison for Deep Expert Pools Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27866 - Information Geometric Self-Organization at the Edge of Stability in High-Capacity Kernel Associative Memories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.16827 - Theoretical Study on the Evidential Learning-based Variational Autoencoder Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27853 - QuadraSHAP: Stable and Scalable Shapley Values for Product Games via Gauss-Legendre Quadrature Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05870 - Order-Invariant Answers, Order-Sensitive Representations in Mathematical Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28442 - Training Leaves Traces: Centered Residual Signatures for Language Model Lineage Verification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14929 - PR-Smoother: Simulator-Preserving Non-Gaussian Smoothing for Data Assimilation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26890 - Learning to Detect Symbolic Failure: Machine Learning and the Limits of Black-Scholes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27764 - Conditional Co-Ablation: Recovering Self-Repair Backups in Transformer Circuits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.01940 - Quantization-Robust Unlearning through the Lens of Retain-Forget Loss Landscapes Interaction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27355 - Never Too Late for Force: Accelerating VLA Post-Training with Reactive Force Injection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.14236 - A Leakage-Aware Multimodal Evaluation Framework for Early Intraoperative Acute Kidney Injury Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26848 - Benchmarking Active Spot Selection for Cost-Efficient Spatial Transcriptomics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27208 - HARN: Hierarchical Associative Resonance Network for Event-Driven Multi-Timeframe Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26822 - Median Temporal Ensembling: Training-Free Robust Aggregation for Action-Chunked Visuomotor Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27167 - Beyond the Illusion of Power: Calibrating Quasi-Experiments in Observational IS Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27299 - When and Where to Trust the Teacher: Unifying On-Policy Distillation and GRPO through Entropy-Calibrated Credit Assignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28385 - Learning Risk Scores Robust to Unobserved Confounders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27144 - Linear RNN Scaling Laws: When Longer Sequences Beat More Sequences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27964 - GTR: Gated Token Recurrence for Efficient Dense Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26590 - Data-driven discrete-time deep recurrent neural network-based modeling for dissipative systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27186 - Riemannian Simultaneous Inference for Tangent Vector Field Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21910 - FedIncome: Federated Learning for Income Estimation in Digital Lending Under Data Sovereignty Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27654 - LAYERSCOPE: A Layerwise Characterization of Video and Multimodal Learned Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28086 - The Linear Representation Hypothesis Needs a Group Action Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27158 - Fine-Tuning LLMs for Translation: General Forgetting Mitigation Does Not Preserve MT-Specific Instruction Following Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28395 - Binary Classification from Coupled Pairwise Labels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.19713 - EduBehaviors: Assertion-based Schemas for Auditable Coding of Educational Dialogues Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27043 - Giving Credit Where It's Due: Redundancy-Aware Learning for Efficient Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27156 - Conditioning Degenerate Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04090 - Learning Holographic Reduced Representations with Clifford Variational Autoencoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28409 - Six Layers Less: Encoder Pruning for Whisper with Label-Free Recovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27980 - NeuroRule: Making Black-Box Neural Networks Explainable through Rule-set Evolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26841 - Backdoors Leave Structural Traces: FedMAST for Backdoor Detection and Containment in Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27760 - CRISP: Scalable Importance-Stratified Coresets for Imbalanced Tabular Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26962 - Geometric Uncertainty for Detecting and Correcting Hallucinations in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.13813 - Geospatial embeddings detect old-growth forests but buffered spatial validation narrows their advantage over Sentinel features Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28194 - The Capability Manifold and ML Scaling Laws Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27588 - Resource-Adaptive Stochastic Gradient Descent for Online Linear Programming without Re-solving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28263 - Binary Quantized Neural Network Training Is W[1]-Hard Parameterized by Input and Output Dimensions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27932 - RL Starts before RL: On Policy Distillation for Better Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28145 - Evaluation of pre-trained models for pedagogical assessment of novel AI-assisted educational questions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27749 - LEAP-CBF: A Safety Filter for Uncertain Systems with Least-Effort Adversarial Potentials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28364 - Joint Interference Detection and Identification via Adversarial Multi-task Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.08607 - VERPO: Verified Evidence Regularized Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06100 - TimeEvo: Failure-Driven Self-Evolution of a Time Series Agent Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27277 - RAMP: Robust Adaptive Mixed-Precision Quantization for Edge CPU Vision Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28262 - Faithful, Interpretable Chest X-ray Diagnosis with Artifact-free B-cos Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.16761 - Riemannian Structure and Optimization for a Class of Low-Parametric Orthogonal Matrices Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27982 - Robust Adversarial Reinforcement Learning with Risk Sensitivity and Critic Consistency Regularization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27667 - Improving Ensemble Filters with Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28015 - Learning Collective Dynamics with Differentiable Gaussian Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28405 - Enhancing Multiclass Malware Classification in Resource-Constrained Environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27950 - An open benchmark for machine learning-based polymer property prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27036 - When Adaptation Hurts: Split Sensitivity and Person-Level Negative Transfer in Federated Wearable Onboarding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27819 - Relative Discharge Stage (RDS) Classification: A Practical Indicator of Battery Discharge Progress Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27986 - EMA: Elastic and Performance Transparent Memory Across GPUs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27040 - Attention Routing Stabilizes Early: Working-Set Inference for Recurrent Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27373 - MolDesignBench: Evaluating LLM-based Agent for Scenario-grounded Molecular Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27349 - Statistical Properties of Deep Neural Networks with Dependent Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.11113 - The Type-II Error of Test Supermartingales: e-Power versus the Chernoff-Stein Exponent Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27765 - MyoFlow: Anchor-Tied Rectified Flow for HD-sEMG Gesture Recognition Across Sessions and Subjects Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17194 - PCQC: Privileged Counterfactual Question Credit for Multi-Turn Medical Dialogue Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27987 - ScoutNeRV: Rapid Encoding of Grid-Based Video INRs via ScoutNet Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27958 - Output-Aware Rotation for INT2 KV-Cache Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02691 - TinyUDE: Solver-Free Universal Differential Equations on Microcontrollers via Lie-Taylor Jet Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26972 - Generalizable Robotic Insertion with World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28258 - Reliable Federated TinyML Deployment for IoT Security Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27202 - Learn Your Own Thoughts: Abstract Token Curriculum Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19717 - LORA-CRAFT: Cross-layer Rank Adaptation via Frozen Tucker Decomposition of Pre-trained Attention Weights Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.17510 - PhenoBench: Mapping What a Deeply Phenotyped Human Cohort Can Tell Us Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06080 - Quantifying the Occult: A Comparative Study of Hindu and Buddhist Deities Using Machine Learning Methods Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27074 - RideSkill: A Hierarchical Algorithm for Generalized Ride Sharing with LLM-Driven Automatic Evolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02250 - FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27657 - Intelligence Across Embodiments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27095 - Predicting Activities in Aqueous Electrolyte Solutions with Hybrid Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.19114 - Dirichlet Process Mixtures of Trees with Gaussian Process Splits: A Bayesian Nonparametric Framework with Posterior Contraction Rate Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27930 - EvoAudio: Recursive Self-Improvement for Audio Understanding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27389 - An improved periodic activation for PINNs reconstructing convective flows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21798 - Full-Covariance Smoothing of Bayesian Neural Networks for Online Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27244 - Learning from Failures: Heterogeneous Graph Memory for Small Language Model Tool-Using Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28003 - Curriculum Learning with GNN-based Reinforcement Learning for Job Shop Scheduling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28085 - LLM-Assisted Workflow for Structural Difference Visualization in Evolving Software Requirements Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.28002 - MultiVENT-Raw: A Benchmark for Retrieval and Reasoning over Raw Videos Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.28437 - MM-BRIGHT: A Multi-Task Multimodal Benchmark for Reasoning-Intensive Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2601.09562 - KnowTeX: Visualizing Mathematical Dependencies Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2601.15294 - BoundaryMORPH: Budgeted Reranking via Active Set Selection for Diffuse Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.27213 - LEGO: Synergizing Expert GraphRAG and Expert Chain-of-Thought for Legal Reasoning Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.27009 - Distilling Lexical Product Associations into Deep Transformers: An Extreme Multi-Label Approach for Natural Language E-Commerce Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.26921 - Automated Extraction of Records of Processing Activities (RoPA) Using Hybrid RAG and Locally Deployed Large Language Models Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.27359 - When Learned Context Planning Fails to Beat Strong Retrieval: A Controlled Study of Planning, Routing, and Reranking for Long-Context QA Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.26976 - Test-Time Adaptation with Query-Dependent Residuals for Visual Document Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research, JavaScript, React) URL: https://arxiv.org/abs/2609.27688 - LabourCrew: A Multi-Agent RAG Framework for Trustworthy Adversarial Deliberation and Statutory Reasoning over Labour Law Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.27814 - VLM2GeoVec: Toward Universal Multimodal Embeddings for Remote Sensing Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2512.11490 - Seal, Then Sample: Sampled Layerwise Proofs for Verifiable LLM Inference from GPT-2 to 70B Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.27367 - Dual-Hypergraph Indexing: Bridging Knowledge Islands for Multi-Hop Reasoning in Retrieval-Augmented Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.28108 - Offline A/B Testing of Slate Recommendation Systems with LLMs: Reducing the Dependency on Pre-Collected User Interaction Data Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2511.04541 - Agentic Governance and Adversarial Verification for Policy-Constrained LLM Healthcare Appeal Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.27844 - Tie Handling Is Part of the Evaluation Protocol: An Order-Invariance Audit for Tie-Heavy Recommender Scores Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.26977 - Beyond a Scalar: Distributional Serving Interfaces for Watch-Time Prediction Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.28383 - From Ranked Documents to Reliable Contexts: An Answer-Oriented Context Construct Framework for AI Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.23354 - Calibrating Reproduced Claims in Recommender Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.26975 - Large Knowledge Model: From Papers to a Scientific Reasoning Landscape Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.27297 - WARP: Wasserstein-Aligned RAG for Population Opinions Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.22859 - When LLM-Based User Profiling Adds Value in Production Streaming Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.27183 - A Flexible Recommendation System for Individuals and Groups Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.27998 - EidosDoc: Implicit Structure Encoding for Cost-Effective Semi-Structured Document QA Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.27784 - Meet, Compare, or Abstain: LatWeave for Deterministic Multi-Hop Question Answering on Knowledge Lattices Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.27225 - ItColBERT: An Italian-Specialised Late-Interaction Retriever Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.26856 - Entangle: Uncovering Collaboration in the GitHub Quantum Software Ecosystem Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.28349 - PASTABench: Proactive Assessment of Sequential Trajectories for Agent Safety Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28197 - Context-Aware Multimodal Claim Verification in Spoken Dialogues Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11420 - WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.01354 - How Much Were You Told? Measuring External Information in Peer Reviews Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28041 - LOCKR: A Hidden-State Trajectory-Guided Planner for Detecting and Repairing Stable-but-Wrong Lock-In in Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27220 - EnComp: Lightweight Encoder-Only Context Compression for Retrieval-Augmented Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.09222 - Exact Feedback Is Not Control: Evaluating Text-based Closed-Loop Revision in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28150 - Beyond Overlap: Estimating the Causal Effect of Benchmark Exposure Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27176 - Beyond Poetry: Can Large Language Models Generate Classical Arabic Maqamat? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28245 - EviStreams: Human-in-the-Loop AI Data Extraction for Systematic Reviews in Medicine Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27418 - Beyond Information Seeking: Severity-Aware Question Supervision for Proactive Medical Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24521 - Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18216 - The Collaboration Tax: How Much LLM Multi-Agent Systems Pay to Coordinate Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22152 - Can LLMs Reason About Runtime Behavior? A Repository-Level Dynamic Benchmark Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28449 - Controlled Attribute-Specific Summarization of Interrogative Dialogues Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28004 - Causal Tracing of Audio-Text Fusion in Large Audio Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.13768 - ContraVis: Evidence-Grounded Visual Analytics for Contradiction Review in Legal Contracts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27014 - TEMPS: Temporal Sentence Embeddings for Temporal Information Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.28048 - CAVEAT: Towards Robust Computer-Use Agents in Incentive-Misaligned Environments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27273 - Evaluating Decision Models for Text Annotation in Computational Social Science Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24574 - When Entanglement Lower-Bounds Disparity: Auditing and Repairing Demographic Fairness in Audio Understanding Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27382 - PatchBoard: Schema-Grounded State Mutation for Reliable and Auditable LLM Multi-Agent Collaboration Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29313 - What Confidence Routing Is Actually Doing: Auditing Routing, Calibration, and Commitment in Multi-Agent Deliberation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27822 - Towards Expert Financial QA via Self-Improving RAG Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26706 - Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.03228 - Guides That Cause Actions: An Offline Study of Guide-Action Mutual Reinforcement in Multimodal Web Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27353 - LiSeCo: Linear Semantic Control for Language Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2405.15454 - Routing-Aware Expert Calibration for Machine Unlearning in Mixture-of-Experts Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10338 - NADI 2026: The Second Multidialectal Arabic Speech Processing Shared Task Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27086 - Realize What Matters: Principled Context Representation for Large-Scale Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27173 - Wisdom in Unity: The Role of Multilingual Training in Figurative Language Identification in Proverbs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.08090 - MORSE: Multi-Context Ordering via Reverse Scoring for Evidence-Preserving Compression Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27380 - Optimizing watermarks for large language models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2312.17295 - Uncheatable Eval: Dynamic Compression-Based Evaluation of Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27510 - Psychoacoustically Aligned Latent Smoothing for Adversarial Robustness of Full-Duplex Speech-to-Speech Dialogue Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27378 - Digital diglossia: Arabic between X and Facebook Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28352 - A Decade of Climate Polarization on Brazilian YouTube using Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27811 - TopoCompress: Topology Aware Token Compression Algorithm for Distributed Edge MoE Inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26061 - Predicting Startup Exit from Textual Descriptors - A Computational Linguistics Framework Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00045 - EnSIMem: Entity-Structured Indexing for Long-Term Agent Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27279 - VectraYX-Vision-1B: A Sub-2B Spanish/LATAM Cybersecurity Vision-Language Model with Structured Visual Reasoning and Native Tool Use Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.08477 - MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26114 - Neither Silence nor Overlap Is Failure: Intent-Conditioned Evaluation of Turn-Taking in Full-Duplex Spoken Dialogue Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27372 - Preserving What Matters: Semantic Scaffolds Beyond Saturation in Summarization Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22603 - Per-Aetiology Contrastive Severity Embeddings with Phonological Pseudo-Labelling for Multilingual Dysarthric Speech Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21789 - Beyond Unsafe Detection: Counterfactually Anchored Evidence Attribution for Multi-Turn LLM Safety Failures Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27773 - The Illinois Social Attitudes Aggregate Corpus (ISAAC): An Open Tool and Reproducible Pipeline for Analyzing Social Group Discourse at Scale Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27059 - Delegated Misalignment: How Multi-Agent Structures Amplify LLM Safety Risks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27900 - Can LLMs Catch a Rigged Backtest? A Clean-Control Calibration Benchmark Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28090 - Reporting Under Pressure: Separating Factual and Tonal Sycophancy in LLM Statistical Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27756 - SkillGym: Internalizing Human Skills into LLMs for Real-World Problem Solving Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27717 - Brain-to-Language Decoding: Tasks, Signals, Methods, Evaluation, Practical Use and Beyond Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27650 - FRAUDSkill: Structured Frozen-Weight Skill Optimization for Audio Anti-Fraud Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18766 - Jev for Scientific Decisions: Evaluating Semantic Choices and Their Consequences Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24965 - Distilling Sequential Computation in Transformer Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27233 - AraGenre 2026: A Hierarchical Definition-Guided Arabic Genre Classification Shared Task Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27387 - "AI Is Turning Too Human": How Teenagers Experience and Negotiate AI in Everyday Life Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27824 - Which Objectives Need a Dial? Predicting Objective Conflict and Covering Trade-offs in Steerable Pluralistic Alignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26929 - Cross-Lingual Legal QA for Vietnamese Labour Law: Retrieval, Translation, and Verifier-Guided Correction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27376 - Algorithmic Unverifiability of Safety for Fixed and Recursively Self-Improving Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.28639 - When Helpful Context Leaks: Privacy Risks in Domain-Adapted ASR Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28211 - Quieter Than the Room: Representation Drift and Task Robustness in Speech Encoders Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27195 - Preregistered Belief Revision Contracts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.15558 - Scaling Attention Head Analysis via Gradient-Based Attribution in Context-Aware Machine Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28117 - DreamAvoid: Critical-Phase Test-Time Dreaming to Avoid Failures in VLA Policies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11750 - FormalTCS: Benchmarking End-to-End Frontier Formal Theoretical Computer Science Research of Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20153 - Shutdown Sabotage Propensities in Multi-Agent Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28274 - Mizar: A 159M-Parameter Audio-Language Model for Audio Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28344 - Reference-Based Analysis of Coherence and Diversity in Open-Ended Text Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28080 - RapidUn: Influence-Driven Parameter Reweighting for Efficient Large Language Model Unlearning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.04457 - Phonemizing User-Generated Text: A Benchmark, Taxonomy, and Compositional Approach Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27205 - Toward Measuring Structural Drift in LLM Communication Loops Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.13061 - Structuring occupational accident narratives for cross-sector safety analysis: Transferability of accident-process role classification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22081 - COMED: The Missing Middle Between Routing and Collaboration in Multi-LLM Inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26913 - Recognized but Not Produced: A Generation Benchmark for Culturally Specific Kinship Terms Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26942 - Learning When Not to Listen: Selective Anti-Interference Pretraining for Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27925 - When Parallel Drafter Meets Parallel Speculative Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27396 - Evaluating Feedback Focus and Pedagogical Adaptivity in LLM-Generated Feedback on Student Writing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28026 - When Context Misleads: In-context Learning with Jurisdiction in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27603 - Can One Adapted Model Do It All? Fine-Tuning Strategy Selection for Customer Support LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27262 - Same Scores, Different Decisions: Evaluating JEV and Language Models for Legal Document Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27678 - HIVE: Hidden-Evidence Verification for Hallucination Detection in Diffusion Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.26139 - MetaHOPE: A Metaphor-Oriented Evaluation Framework for Analysing MT and LLM Translation Errors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.00848 - Long-Tail Rebalancing for Non-Verbal Vocalization-Aware ASR: A Track 1 System for the NVVSpeech Challenge Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23462 - What Changes When Fact-Verification Scores Improve? Evidence and Answer Accounting Across Trained Verifiers and LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27064 - Towards Efficient Reasoning: Learning Causal Shortcuts for Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28272 - Classifying Interpretive Canons at the Sentence Level: A Benchmark from the German Federal Constitutional Court Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26945 - Text Scores Can Miss Waveform Use: A Qwen2-Audio Quantization Case Study Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26823 - MWE-ECL: Recoverable Long-Range Context Does Not Always Override Local Lexical Priors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27590 - The Path Matters: Evaluating Small Language Models Beyond Answer Accuracy in KGQA Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27669 - ThaiTrees: Thai Syntactic Dependency Trees Across Domains Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27558 - Ruby-ASR: Evidence-Preserving Supervision for Joint Orthographic and Lexical-Reading Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27289 - Cross-Scale Transfer Learning for Depression Severity Prediction: From PHQ-8 to HAMD-17 Across Languages and Clinical Paradigms Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28430 - UniDataAgent: An Ontology-Grounded Agent for Enterprise Question-to-Report Automation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27257 - Complementary Roles of Activation and Parametric Memory in Few-Shot Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28250 - What Looks Like a Capability Limit in Vision-Language Models Is a Readout Limit Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27408 - Consequential Behaviour and Representational Fairness in the Validation of Synthetic Research Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27690 - Lost in Speech: Trilingual Spoken Hallucination Detection Across Audio and Transcripts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24707 - PRISM-VLM: A Multi-Axis Discriminative Benchmark for Compact Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27395 - TukaBench: A Culturally Grounded Jailbreak Benchmark for African Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01322 - Planned Test-Time Scaling with Coordinated Reasoning Paths Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27374 - Can Jev Judge Radiology Reports? Evaluating a System One Model for Clinical Factuality Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27607 - RexDrug: Reliable Multi-Drug Combination Extraction through Reasoning-Enhanced LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.08166 - Med-V1: Small Language Models for Zero-shot and Scalable Biomedical Evidence Attribution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.05308 - Retrieval Augmented (Knowledge Graph), and Large Language Model-Driven Design Structure Matrix (DSM) Generation of Cyber-Physical Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.16715 - A Native-Reference Coordinate Geometry for L2 Pronunciation Deviation Using Self-Supervised Speech Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28060 - Computation Over Geometry: Meaning Identity Is Computed, Not Shipped in the Embeddings Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28290 - Improving LLM-based Autonomous Web Agents with Filtering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27770 - Count Evidence, Not Sentences: Tempered Evidence Fusion of LLM Judgments for Long-Text Value Measurement Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27165 - SafeTutors: Benchmarking Pedagogical Safety in AI Tutoring Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.17373 - Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27321 - Hard Negatives Reveal What Easy Negatives Hide: Cross-Lingual Harmfulness Representations Degrade with Resource Tier Under Hard Negatives Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27758 - Building Socio-Affective Artificial Intelligence for Interactive Multi-Agent Simulations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26927 - When Clients Are Orchestrated: Strategic Gradient Manipulation to Defeat Federated Learning Servers with Efficient Defense Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27124 - Radiomics and artificial Intelligence for thyroid cancer diagnosis: Concepts, challenges, and solutions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2404.07239 - Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24815 - Alignment Inertia: Auditing the Durability of Training Data Influence Through Policy Override Resistance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27333 - BEE: Intervention-Adaptive Real-World Reinforcement Learning with Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27450 - Can AI Agents Deliver Verifiable Network-Wide Outcomes Across Authority Boundaries? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10181 - Cross-Modal Contrastive Learning from Histopathology and CT for Automated Renal Cell Carcinoma Grading Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26920 - Spec2COBOLRot: An Agentic-AI Degradation Loop for Realistic COBOL Corpus Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26835 - DRSR: Learning Set-Level Deletion Risk for Efficient Long-Horizon Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27276 - Issuer-Sovereign Agentic Payments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27452 - Using Vision Language Foundation Models to Generate Plant Simulation Configurations via In-Context Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.08930 - The Risk-Sensitive Schr\"odinger Bridge: Is Not a KL Projection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27250 - ActiveArena: Benchmarking and Understanding Active Perception in Robotic Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24124 - Behaviora - A Conceptual Architecture for External and Internal Behavior of Robots and Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27536 - FLINT: Fast Lightweight Inference for Traversability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26857 - HANIA: Planner-Guided Multimodal Graph Evidence Selection for Grounded Question Answering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29088 - InternW0: A Foundational Physical World Model for Efficient Real-World Interactions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27656 - FDE-Bench: Evaluating LLM Agents for Deployment Environment Configuration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27571 - OmniEcho: Audio-Visual Spatial Understanding for Omni-Modal Embodied Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23407 - G\"odel's and Scott's Variants of the Ontological Argument in Lean 4 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26806 - InGuard: Towards Generalized Inner Guardrail for Safe Text-to-Image Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27620 - Ask Which, Not How Good: Sizing Benchmarks Scored by an LLM Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27787 - Contextual Information Allocation in Shared-State Cognitive Models: An Information-Theoretic Bound Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.16716 - RelCheck: Dual-Evidence Spatial Grounding for VLM Hallucination Correction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27890 - Shopping by algorithm: How agentic AI deploys human heuristics as a surrogate consumer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28372 - RewardVerse: Rubric-Guided Policy Optimization for Video Reward Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22947 - Silent Failures in Agent-Tool Interaction: An Audit of ToolUniverse Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26836 - Kairos: Grounded Forecasting of Presence and Directional Flow in 4D Scene Graphs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27467 - EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06192 - Stable Geometry with Divergent Task Evidence for Efficient Long-Horizon Agent Compression Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27332 - Ajar: Measuring Open Privilege in Agent Defenses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26900 - Propose, Don't Judge: An Anytime-Valid Referee for LLM Agents That Mine Investment Factors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27051 - A Scalable Multi-Robot Framework for Decentralized and Asynchronous Perception-Action-Communication Loops Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2309.10164 - Memory Control Signals Emerge Before Action in Long Horizon Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27286 - Multi-View Fusion for Encrypted C2 Detection: A Leakage-Controlled Measurement Study of Evaluation Pitfalls Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27311 - TopoGS: Topology-Aware Anchor Feature Aggregation for Large-Scale 3D Gaussian Splatting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27868 - Compliant AI Infrastructure for Regulated Finance: A tiered multi-agent framework with DLT audit trails for financial operations in DACH Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27632 - Topological Signatures of Cyber-Attack Classes in Natural Visibility Graph Representations of Network Traffic Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26990 - Reachable Global Optimization in AI Systems: How Global Is Global? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27855 - Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26891 - Provably Complete Generalized Planning with LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27105 - Are Stated Reasoning Steps Causally Load-Bearing? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27038 - SsgCaps: A controlled dataset for the evaluation of sound scene generation algorithms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26854 - XLOG: A CUDA-Native Engine for Neurosymbolic Integration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27203 - Safe Multi-Robot Coordination via VLM-LLM Reasoning and Reachability Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27816 - Constraint-Driven Context Engineering: Designing Domain Interfaces for AI Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27354 - Hunyuan-A13B Technical Report Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27284 - Evolve Vision-Language-Action Model into an Agent with On-the-fly Tool-use Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14047 - Combining LLMs and Genetic Search for ARC-AGI-2 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27242 - Field-of-View Extension in Dental Cone-Beam CT via Implicit Neural Representations and Diffusion Model-Based Refinement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28110 - The Gaussian Is Enough: Flow-Matching Priors Do Not Help When Fine-Tuning Large Behavior Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27070 - BIDETA: Brain-Inspired Data-Efficient Tactile Adaptation for Unseen Sensors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08673 - A Resilience Recovery Method for Complex Traffic Network Security Based on Trend Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27903 - Omni-Decision: Evidence-Ledger Planning for Omni-Modal Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.11433 - Listening and Mirroring: The Effects of Verbal Attunement and Behavioral Mimicry on Social and Empathic Perceptions of Embodied AI Agents in VR Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27246 - The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.25804 - Automotive mmWave Spinning Radar Place Recognition with Spatially Gated Feature-Correlation Representation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27394 - Valerant: An Automatic Navigable Game Map Generator via Action-Conditioned World Model Exploration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09418 - "We'll Fix It Later": Education, AI, and the Deferral of Privacy in EdTech Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28137 - Training Intelligent Voice Assistant Wakeup with Controllable Synthetic Conversations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27037 - SlackDrive: Reclaiming Runtime Slack for Adaptive Driving Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28064 - A hierarchy of faithfulness criteria for knowledge base completion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27863 - SyzHarness: Patch-Based Kernel Bug Reproduction with LLM-Synthesized Fuzzing Harnesses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23889 - How Children Design and Reason about Trustworthy AI Chatbots Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.25244 - CART: Closed-Loop Adaptive Red Teaming for Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27336 - Leaky-integrator reconstruction: taming error accumulation in recursive differenced time-series forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23378 - Schr\"odinger's Code Repository: Have LLMs Learned SWE-bench or Memorized It? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27891 - MemBodied: Recurrent Associative Memory for Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28256 - SHRAV: State-Hypothesis-Reason-Action-Verify Framework for Physical Modeling and Inverse Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27621 - Escaping Python Dependency Hell: A Hybrid Replay-and-Repair Pipeline for Python Dependency Resolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26952 - When do prophets profit in prediction markets? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.06166 - Warranted Attention: Learning What to Pass from Attention to Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.30139 - Prompt, Probe, Train, or Annotate? Single-camera sports video understanding in amateur settings Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28049 - WorkWorlds: An Infrastructure for Evaluating AI Agents on Workplace Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23806 - AI-Driven Neural Surrogates for In Silico Design of Cognitive-Affective Neuromodulation Targets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27729 - Passing: An Endless Journey through Reconstructed Spacetime with AI-Generated Sound Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27489 - Learning Spectral Allocation: A Fractional Diffusion Framework for Adaptive Volumetric Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27217 - TACT: Taxonomy-Aligned Post-Training for Pedagogically Adaptive English Tutoring Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.03952 - A Lie Detector Test for Language Models: Reading Knowledge a Model Won't Reveal Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21996 - Policy-as-Skill: Governed LLM Decision Support with Evidence, Deterministic Control, and Audit Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27087 - FSCE: A Target-Aware Frequency-Spatial Collaborative Enhancement Framework for Noise-Resilient SAR ATR Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.21565 - TOPS: First-Principles Visual Token Pruning via Constructing Token Optimal Preservation Sets for Efficient MLLM Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.27161 - Breaking Weather-Content Coupling: Type-Severity Guided Progressive Disentanglement for All-in-One Infrared Restoration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27317 - Validation and Simulation Catch Different Errors: Four Levels of Evaluation for LLM-Generated Circuits Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26830 - Where Should I Join? Robot Group Joining via Language-Guided Goal Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28467 - Sci-MMR: Benchmarking Multi-Step Evidence-Grounded Scientific Reasoning in Multimodal Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.11243 - Teach-to-Crash: A Closed-Loop Student-Teacher LLM Framework for Collision-Inducing Test Scenario Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27296 - Risk-Aware Occupancy for Safety-Oriented End-to-End Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21470 - Loss Choice or Model Choice? The Role of Forecast Level in Cryptocurrency Volatility Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27024 - Same evidence, different judgments: Evidence noncommutative in vision/speech-text conflicts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26986 - A Vision-Language Foundation Model for Precise and Comprehensive Brain Tumor Diagnosis from Preoperative Multimodal Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.16597 - Emergi-PersonaOS: A Persona Agent Operating System for Situational Adaptation and Controllable Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27417 - Bridging LLM Serving and CXL-SSDs with Chunk-Aware KV Cache Management Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26828 - StudentBench: AI and human tutoring yield equivalent GRE learning gains Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28470 - SMDDFNet: State-space Modeling and Dynamic Dual Fusion Network for Traffic Sign Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.05491 - A Hierarchy-Aware Video-Language Model Evaluation and Hyperbolic Baseline for Surgery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27139 - Why LLM Agents Collapse Without Oversight: The Enforcement Gap as the Mechanism Behind Emergence World Failures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15293 - Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16932 - Geometry-Conditioned Visual Place Recognition in Natural Environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27370 - TwinCheck: Evidence-Grounded Negative-Twin Verification for Stateful Tool Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26911 - Measuring and Exploiting Contextual Bias in LLM-Assisted Security Code Review Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18740 - Do We Need Complex Topology Control? Distinct-Peer Random Routing Improves Cost-Efficiency in Sparse Multi-Agent Debate Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27150 - ERPBench: A State-Grounded Evaluation Paradigm for Computer-Use Agents in Enterprise Software Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17885 - Controlling Collectives of AI Agents in Reasoning Space with Spatial Transformers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28247 - Evolutionary Stability Does Not Guarantee Learning Accessibility: A Multi-Agent Reinforcement Learning Perspective on Cooperation Emergence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27664 - State-Grounded Conditioning: Wrapping User-Facing LLM Agents Where Direction Depends on Live State Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27606 - LitPivot: Developing Well-Situated Research Ideas Through Dynamic Contextualization and Critique within the Literature Landscape Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.02600 - Discrete optimal transport is a strong audio adversarial attack Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.14959 - Bounded Loops: Pre-Run Spend Bounds, Proved Termination, and Verified Completion for Agent Harnesses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27871 - RAIN: Region-Aware Inversion Network for Semantic Watermark Extraction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14856 - Enhancing the Non-Functional Quality Compliance of LLM-Generated Code through Quality-Aware Preference Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.09020 - Compliant with Local Controls, Collectively Discriminatory. A Governance Architecture for Multi-Agent AI in Regulated Finance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27994 - Forget who you Forgot: Speaker Unlearning to Prevent Re-Identification in Zero-Shot Text-to-Speech Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27399 - NV-Reason-CT: 3D Visual Language Model for CT Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27511 - A Non-Invasive Cloud-Based Migration Strategy for Post-Quantum Cybersecurity in Smart HVAC Systems: Architecture, Implementation, and Empirical Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27828 - MicroQonv: Reshaping Convolution Tensors for Efficient Microscaling in Training and Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28358 - Calibration and transfer in indicator-based assessments of artificial consciousness Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.27597 - Math Reasoning in LLMs is Organized by Approach, Not Topic Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27041 - Same Stories, Different Journeys: Exploring Persona-Grounded Conversational Agents for Supporting Career Exploration with Peers' Posts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.11039 - Comparative Evaluation of Static Embedding Models for HTTP Request Anomaly Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26860 - Learning Stiffness Dependent Fluid Structure Dynamics from Coarse Flow Representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26816 - AnchorReasoning: A Visual Grounding and Causal Reasoning Dataset in Long-Tail Autonomous Driving Scenarios Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28366 - IB-Flow: Information Bottleneck-Guided CFG Distillation for Few-Step Text-to-Image Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.09133 - How a shared state is described determines whether AI agents synchronize Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06968 - Self-Evolving Multimedia Verification through Memory Consolidation of Contestation Experiences Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27175 - Do Center Biases Propagate? Robustness of Pathology Foundation Models in Whole-Slide Image Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28231 - DENSE: Distilling Agent Trajectories into Evidence-Grounded Shortcut Trees for Self-Refinement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21423 - A 3D Pose-Based Ensemble Framework for Cricket Shot Classification and Automated Biomechanical Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26923 - PRAGMA: Evaluating Personalized Guidance with Memory Alignment in Lifelong Conversations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09664 - Alignment of LRMs via Counter-Aligned Few-Shot Conversation Exposure Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27763 - Learn How to Act from Your Own Interactions: On-Policy Self-Distillation for GUI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27307 - QuantWM: Temporally Consistent 2-Bit KV Cache Quantization for World Models and Video Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26425 - BiCFlow-MER: Orchestrating Discriminative and Generative Multimodal Emotion Recognition via Conditional Transport Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27615 - InfiNoVA: Infinite Novel View Augmentation for Viewpoint Invariant Robot Policies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27734 - An Open Pipeline and Dashboard for Systemic-Risk Evidence under the EU AI Act's Code of Practice Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28335 - UniShield: An Adaptive Multi-Agent Framework for Unified Forgery Image Detection and Localization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.03161 - FleXray: Universal Clinical X-ray Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26756 - Learning What to Activate: Combinatorial Capability Allocation for Long-Horizon Multimodal Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27869 - Benchmarking Text-to-SQL under Role-Based Access Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22115 - Categorical Internalisation of Environmental Groupoids for Generalisable POMDP Solving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27745 - From Agent Output to Authorized Transition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28216 - A Study of the Reliability of Agentic AI-Generated Programs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18298 - Attention-based representations for multi-task computation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.04243 - Enhancing Small Language Models for Power Outage Report Generation via Minimum Risk Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27197 - StateComp: Learning When to Compress History in Long Horizon Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27298 - From Document Silos to Process Intelligence: A Multi-Layer Knowledge Graph for CMC Process Development Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.11493 - Frozen Flows Forget: Diagnosing and Restoring Lost Motion in a Latent-flow World Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28414 - Outcome-Conditioned End-Effector Geometry Across Vision-Language-Action Policies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21659 - MessyKitchens: Contact-rich object-level 3D scene reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16868 - Decoupling Internal Representational Changes and Causal Importance in Fine-Tuned Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21113 - Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27334 - Not What You Meant: Can LLMs Follow a Specified Negation Semantics? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27517 - PotARCin: Multi-Dimensional Evaluation of Skill Acquisition in Abstract Reasoning Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27288 - InterPol: De-anonymizing LM Arena via Interpolated Preference Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.15220 - Evaluating ADC-only deep learning pipelines for breast cancer detection and segmentation using standalone diffusion-weighted MRI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27815 - Sparse-Observation Atmospheric Thermal Forecasting with Physics-Informed Neural Networks for Climate-Aware Digital Twins Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27290