TILens Daily Edition 2026-10-16 Filters: topic=ai-research, github=hidden Stats: 903 articles, 8 sources, 897 research papers Top topics: AI, AI Research, Information Retrieval ## News - I Tested NVIDIA Nemotron Bolt and Super VL. Here’s Where Each Shines. Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/nvidia-nemotron-3-5-bolt-super-vl-review/ - 😺 Advertisers can target ChatGPT by prompt Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/advertisers-can-target-chatgpt-by-prompt/ - ChatGPT Adds 13 Voices. Can GPT-Live-1.1 Make AI Easier to Talk To? Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/chatgpt-gpt-live-1-1-13-new-voices/ - Meta’s Muse Spark Open Runs on Macs. Can Local AI Justify the Cost? Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/meta-muse-spark-open-macs-local-ai-cost/ - Everything That Happened in AI Today (Friday, October 16, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-today-friday-october-16-2026/ - AI Weekly Issue #538: The FTC wants OpenAI's and Anthropic's safety incident records Source: ai-weekly Topic: AI (+AI Research) URL: https://aiweekly.co/issues/the-ftc-wants-openais-and-anthropics-safety-incident-records ## Research - Grounding AI agents in biological reality: Building blocks for autonomous wet labs Source: google-research-blog Topic: AI Labs (+AI, AI Research) URL: https://research.google/blog/grounding-ai-agents-in-biological-reality-building-blocks-for-autonomous-wet-labs/ - Do You Still Own the Code Your AI Wrote? I Built CodeOwnership to Measure It Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/do-you-still-own-the-code-your-ai-wrote-i-built-codeownership-to-measure-it/ - I Built a Claim-Checker for Writing With Codex. It Passed a Wrong Claim. Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/i-built-a-claim-checker-for-writing-with-codex-it-passed-a-wrong-claim/ - Deploying Data Science Tools: Part 1 Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/deploying-data-science-tools-part-1/ - I Reran My Python 3.14 JIT Benchmarks on Python 3.15 Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/i-reran-my-python-314-jit-benchmarks-on-python-315/ - Generalization Guarantees of Randomized Block Coordinate Descent for Nonconvex Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22213 - DeciCAD: Harness-Grounded Learning of Action Policies for CAD Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21755 - International Multi-Centre Validation of Unsupervised Domain Adaptation for Precise Discrimination between Normal and Abnormal Retinal Development Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21719 - Beyond Invariance: Factor-wise Selective Treatment of Shifts for Multimodal Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21403 - INCONVENIENT: A Benchmark to Assess LLM Generalization Capabilities from Convenience Samples Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21038 - Interfaces and Modules: A Scalable Representation for Weight-Space Learning across Architectures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21995 - TabFORGE: A Tabular Foundation Model for Generative Modelling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09424 - Analog RF Computing for Integrated Data and AI Flows Over Wireless Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20841 - Missed Detections and False Alarms in a CNN Technosignature Detector on Breakthrough Listen Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22050 - Self-Guided LLM Reasoning for Error Diagnosis in Vehicle Routing Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21393 - Poisoning the corpora of protein design systems during pre-training and retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21200 - Halve-Then-Greedy: Adaptive Sampling for Posterior Success with Near-Optimal Instance Dependence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20997 - How Much Physics Can Vision Learn from Audio? Probing and Distilling Damping Structure Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22221 - Amortizing Sequential Experimental Design in Reasoning LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20832 - Where to Steer: Input-Dependent Layer Selection for Steering Improves LLM Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.03867 - Value-Informed Schedule Trimming for Accelerated Sequential Monte Carlo Guidance in Discrete Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20669 - Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22273 - Mosaic: Multi-Session Agentic Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22174 - Activation-Adjacent Layer Normalization: Effects on Approximation Power Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21527 - Learning to Steer LLM Agents and Multi-Agent Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22316 - ReTerm: Recovery Training for Self-Improving Terminal Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18484 - Evaluating Model Capabilities After Benchmark Saturation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20667 - Fractional Rotation, Full Potential? Investigating Performance and Convergence of Partial RoPE Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.11611 - CNet: A Complex-Valued Deep Learning Framework with Wirtinger Autodifferentiation and FFT--Hadamard Convolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08592 - Graph Dirichlet Energy for Fitting-Free Bivariate Causal Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21892 - Behavioral Compositionality of Sparse Autoencoder Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21261 - Rethinking Calibration for High-Sparsity LLM Pruning: From Single Sources to Capability Coverage Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03328 - Shortcut Sensitivity in Agent-Safety Evaluations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22243 - When Reality Outpaces Cognition: A New Scaling Principle for Reliable Intelligence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20764 - Verdict: Encode Once, Decide Many Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20778 - AdaptLSTM: Efficient Adaptive Online Learning for Cloud Workload Forecasting under Distribution Drift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12265 - SUPN: Shallow Universal Polynomial Networks for Efficient Function Approximation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.21414 - Score Mismatch and Set-Constrained Sampling in Zero-Shot Conditional Discrete Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21061 - BitSparse: Compact Activation Storage for ReLU Feed-Forward Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22256 - Policy-Aligned Predictive Verification for Adaptive VLA Action-Chunk Execution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21434 - On-Policy Residual Learning for Diffusion Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20687 - Defining and Generating Compositional Structure Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20922 - PAC-Causal Learnability: From Identification to Finite-Sample Guarantees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.18903 - ReText: Text Boosts Generalization in Image-Based Person Re-identification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.05785 - KV-streams for Efficient Compaction in Agentic Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35750 - Towards Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06503 - LightMedSeg-ISLES: Stroke Lesion Segmentation with 81x Fewer Parameters than nnU-Net Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09634 - Sharp and Stable Label-Free Calibration Certificates from Logical Coherence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21567 - Physics-Aware Distillation of a Grid Foundation Model for Real-Time Edge Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21833 - Market Incentives for AI Safety Investment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21607 - Learning Rewards in Strategic Games Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21912 - Learning Topology-Aware Representations for Mechanics-Relevant TPMS Metamaterials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20684 - SHIP: Structured and Hierarchical Insight with Privacy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21048 - A Closed Form Depth-Width Law for Neural Collapse in Deep Linear Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21820 - In-Context Batch Black-box Optimization via Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20138 - SNOAR: Self-training with Noise filtering, Observation adding, and Remixing for Speech Denoising Without Clean References Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20863 - Tail-Replay: Escaping the Curse of Linear Attention in Prefix Caching for Hybrid LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30310 - Flexible Doubly Robust Proximal Causal Inference for Censored Outcomes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20893 - SPARCL: Spatially Adaptive Regional Coverage for Active Learning in Chest X-ray Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17808 - Acceleration and its Limits in Gaussian Variational Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21020 - Not All Unlabeled Data Are Equal: Unlabeled Data Selection for Semi-Supervised QSAR Modeling with Large Chemical Repositories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22025 - Selection-Safe Conformal Early Exit: Distribution-Free Coverage under Adaptive Depth Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20773 - Let's Ask Gauss: Improved One-Run Privacy Auditing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.12733 - StabilityArc: Decoding Protein Sequence Embeddings into Generalizable Stability Landscapes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00742 - CarBench: A Comprehensive Benchmark for Neural Surrogates on High-Fidelity 3D Car Aerodynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.07847 - Wrong Votes, Right Gradients: Why Majority-Vote Rewards Track Verifiable RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20898 - STAMP: Symmetric Temporal Averaging Message Passing for Domain Adaptation in Chronologically Split Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.10957 - Recursive Offline Distillation via Entropy Gain Sampling and Answer Mixing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20914 - Does Compression Imply Generalization? A Minimum Description Length Perspective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21376 - Follow the Perturbed Leader for Linear Bandits: $\sqrt{T}$ Regret over General Convex Sets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17818 - Hard Way, The Only Way: Provable Merits of Training on Hardest Examples Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21201 - Minimal Witness Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07226 - Not All Change Is Damage: Update-Matched Unlearning for Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21230 - Router Drift Control: Mitigating Off-Policy Degradation in Mixture-of-Experts Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21682 - Calibration Language Shapes Block-Influence Pruning in Multilingual Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21383 - FlowBudget: Training-Free Sampling-Budget Estimation for Flow Matching Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20636 - Lethe: Link Inference Attacks For Evaluation of Edge Unlearning Methods Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21869 - ShiftQAT: Quantization-Aware Training for the Numerical Contract of a Fixed-Function Edge CNN Accelerator Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21695 - CausalEvo: Causal Skill Self-Evolution for Health LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21016 - Calibration-Preserving Pruning: Compression as a Reliability Contract Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23744 - Global-in-time Spectral Duhamel-Picard Method for Post-Exposure Bake Simulation and Physics-Informed Neural Operators for EUV Lithography Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20655 - Same Answer, New Box: How Much of RLVR's Out-of-Domain Gain Is Answer Format? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20639 - Amplitude-Only FFN Intervention for Tool-Structured LLM Inference: Method, Gated Evaluation Protocol, and Cross-Model Empirical Results Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.11183 - Rethinking Learning from Label Proportions via Moment Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21262 - Supervised Learning Objectives for High-Dimensional Treatment Effects Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.27281 - Neurodata Without Boredom: Benchmarking Agentic AI for Data Reuse Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12808 - Fractional Power-of-Two Quantization for Efficient and Effective Multiplier-Free LLM Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21257 - Compatibility Matters: A Framework for Token-Level Teacher Selection in On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21234 - Augment the Cache, Replace the Activation: A 2x2 Study of Internal-State Sharing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22026 - Same Target, Different Origins: Aligning Latent Rollout for Consistent PDE Emulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21370 - LIBERO-PeRM: Benchmarking Personalized Robotic Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22372 - Pairwise Difference Learning for Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.20031 - ToolBottleneckBench: Measuring Tool-Agent Performance under Controlled Pressures and Fixed Harness Budgets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21098 - Semantic Latent Alignment for Flow Matching with Invertible Bi-Lipschitz Adapters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21332 - Ranked Right, Sized Wrong: Ensemble Spread Fails Silently at Streamflow Extremes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20947 - Conditional Mean Flows: Few-Step Densities for Simulation-Based Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21657 - Optimal Hydra: Model Heterogeneous Federated Learning for LLMs using Data-Informed Hydra-Nets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20753 - Why Shallow Neural Networks Learn Sinusoidal Components First: An Orthogonal Polynomial Dynamics Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21964 - Mitigating Memorization Where It Happens Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.08901 - Finite-Time Guarantees for Constrained Reinforcement Learning under Partial Observability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21548 - PureTD: Reinforcement Learning for Backgammon Money Games with No Evaluation-time Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15146 - Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.26226 - Sign Betting for Misspecified Regression: Variance Adaptivity and Optimal Approximation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20903 - Multimodal Remote Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.07555 - AlignSAE: Concept-Aligned Sparse Autoencoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.02004 - The Tilted Sampling Problem: Optimism, Posterior Sampling, and Logarithmic Regret Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21908 - PotentialEP: Backprop-Free Training of CIFAR-Scale Generative Models via Equilibrium Propagation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14409 - Morphology-aware deep learning predicts colorectal cancer survival from whole-slide images Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17603 - AI Scientists for Building Virtual-Cell Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.02276 - Q($\gamma_H$): Entropy-Guided Horizon Mixing in Multi-Discount Q-Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21764 - Identification and Inference for Algorithmic Frontiers with Selective Labels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.14977 - D-DOIT: Training-free Adaptation of Discrete Diffusion via Doob's h-Transform Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04938 - Sim-to-Real Transfer for Muscle-Actuated Robots via Generalized Actuator Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.09487 - pcNN-SN: a physics-enhanced predictor-corrector neural network algorithm coupled with the discrete ordinates method for neutron transport equations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20619 - A proximal gradient algorithm for composite log-concave sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12461 - A Phenomenology of Neural Geometry in Vision-Language-Action Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20840 - Diminishing Returns of Data in Sparse Autoencoders: Functional Behavior does not Guarantee Feature Reproducibility Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20680 - World Modeling through Spectral Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15429 - PMB-NN: Physiological-Model-Based Neural Network for Glucose Forecasting in Type 1 Diabetes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15456 - HERO: Preserving Structure and Semantics in Heterogeneous Continual Graph Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.17458 - Self-Calibrated Subspace Robust PCA for Parameter-Free Removal of Mixed Noise and Line Stripes in Hyperspectral Images Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21896 - Planning to Learn: Real-Time Robust Adaptive Control on the GPU with Guaranteed Future Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20925 - LLM-as-an-Investigator: Evidence-First Agentic Reasoning for Robust Interactive Problem Diagnosis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.13220 - The Self-Improvement Problem Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21646 - System1-Arena: Which Decisions Can Be Left to System 1? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21244 - A Bethe-Ansatz Source of Early Token Correlations: A marginal-preserving construction for parallel proposals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16781 - SALTO: Solver-Anchored Lifted Transfer Operators for Nonlinear Event Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21049 - Sensor Diagnosis for Fuel and Emissions Monitoring in Heavy-Duty Diesel Vehicles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21188 - Spectral-Spatial Interpretation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21114 - A Model Ensemble-Based Post-Processing Framework for Fairness-Aware Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18838 - Efficient Pairwise Difference Learning: A Comparative Study of Encoding Strategies and Training Pair Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21644 - TimeRSI: Towards Self-Improved Agentic Deployment for Time-Series Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19725 - ChronoSheaf: Joint Spatio-Temporal Spectral Filtering on Cellular Sheaves Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21958 - Judging the Judges: Confidence and Disagreement in Rubrics as Rewards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21179 - The Safety Relay in Roleplay Jailbreaks: A Component-Resolved Causal Analysis of Harm Recognition and Refusal Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30585 - Nonconvex Composite Functional Constraints via First-Order Augmented Lagrangian Methods under Local Regularity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.08954 - EigDiff: Eigensample Diffusion - or how to significantly reduce training dataset size with marginal performance variation? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20999 - Selection Is Not Learning: Choosing Model Futures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22029 - Expanding Attention: A Taylor-Series Route to Linear-Time Transformers with a Fixed Number of Recurrent States Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20637 - Beyond the Dominant Label: Recovering Coexisting Lesion Evidence with Multiple Instance Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22091 - Stateful Testing for Deep Learning Compilers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22003 - Robust Covariance Estimation for Entry-wise Contaminated and Partially Observed Data via Expectation Maximization Algorithm Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21709 - Boltzmann generators for amorphous particle systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.16607 - Time to Fake It: Continual Machine Learning Intensifies Unfairness in Deepfake Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21974 - Beyond Fixed Acquisition Functions: Temporal Difference Active Learning for Perturbation Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22122 - What Should We Remove? Evaluating the Reliability and Costs of RLVR Data Decontamination Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21229 - ULTRADISCOVERY: Abductive Exploration in an Interconnected, Epistemically Open Universe Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03092 - ICON decomposition: Multivariate concept auditing reveals shortcuts that neural networks rely on Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26083 - PLSP (Pre-hoc Liminal Space Profiling): OOD Prediction over Detection -- An Anticipatory Approach for Machine Learning Model Reliability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.12225 - CRAFT: Forgetting-Aware Intervention-Based Adaptation for Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05732 - KNOU-Flood: Advancing global streamflow forecasting with lead-aware probabilistic machine learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20640 - Do LLMs have core beliefs? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.03255 - AirPASS: Over-the-Air Federated Learning via Pinching Antenna Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.06768 - Rethinking Routing Exploration in Modern Mixture-of-Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22353 - A self-learning framework for adaptive free-form pipe routing in aeroengines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.03669 - GeoState: Learning View-Decoupled Geometry States for 3D World Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22343 - Machine-learning-based neutrino-event generation constrained by experimental measurements Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20870 - PathFM: Fast Generative Forecasting of Multivariate Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22358 - Vertical Sliced Wasserstein Distances for Meta-Measures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20743 - V-SHARE: Provable Convergence Guarantees for Advantage-based Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21448 - Identifiability of a dissipative knowledge-dynamics model: exact recovery under designed excitation, degeneration on observational data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09889 - P2TPO: Structure-Aligned Page-to-Token Credit Assignment for Full-Page Document Parsing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21979 - Second Maximum of a Gaussian Random Field and Exact (t-)Spacing test Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.18397 - Does Morphological Correctness Matter for Tokenization? A Scrambled Control Study in Tagalog Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20859 - Learning Warm Starts for the Simplex Method from Measured Solver Cost Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20892 - Probe-and-Resume: When and How to Evaluate Agent Execution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21088 - Personalized Projected Ascent for Federated Stackelberg Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21295 - The Blume-Capel Model as a $\phi^6$ Field Theory: A Monte Carlo and Flow Model Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20982 - A Multimodal Emotion Recognition System: Integrating Facial Expressions, Body Movement, Speech, and Spoken Language Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.17907 - DemoStream: Batched Task-and-Motion-Plan Optimization for Automated Learning from Demonstration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22020 - Sparse Federated Echo State Networks for Time-Series Classification via Smooth-L1 Regularization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21742 - Diffusion Models in Simulation-Based Inference: A Tutorial Review Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.20685 - Ranking and Partitioning of Attention Heads for Sparse and Continual Reinforcement Learning Fine-tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21336 - Plan Before You Trade: Inference-Time Optimization for RL Trading Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12653 - Spectral Indistinguishability and Learning-Curve Identifiability in Quadratic Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20678 - Amortized Factor Inference Networks for Posterior Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26419 - Athanor: An Agent-Native System for Autonomous Post-Training Research Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21055 - Stabilizing the Modality Gap: Null-Space Projected Continual Learning for Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.19839 - Size-Transferability of Graph Transformers with Convolutional Positional Encodings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.15239 - Arithmetic Circuits and Neural Networks for Regular Matroids Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.02406 - CascadeLedger: Counterfactual Auditing of Information and Resource Integrity in LLM Cascades Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20668 - TurboMamba: Faster Inference, Faster Training, and Better Prediction with Lexical Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20682 - TTS-Q: Perception-Guided Post-Training Quantization of Text-to-Speech Diffusion Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12474 - Kolmogorov-Arnold Networks: Curse of Dimensionality and Structural Bias Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21480 - Query-Efficient Rejection Sampling for Parallel Masked Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22238 - Ergodic topology sampling toward the continuum with Stochastic Normalizing Flows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20747 - Do Emergent Misalignment Models Share a Circuit? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20887 - CAT-alyzing Honesty: Continuous Adversarial Training for Transferable LLM Honesty Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22292 - Spatial Context or Memory? Sizing the Inputs of Neural Surrogates for Partially Observed Fields Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12723 - RoLaQ: Joint Rotation and Range Calibration for 2-Bit KV Caches in Multi-Head Latent Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20686 - Isolating a Language Model's Judgment with a Label-Free Subspace Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21256 - DuET: Note-Frame Dual Encoding for Piano Performance-to-Score Transcription Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21467 - LEV: Thinking Fast and Deep with Looped Decision Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20951 - Learning to Read Out: Unembedding Dynamics in Language Model Pretraining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21025 - Optimal Watermark Localization in Mixed-Source Large Language Model Texts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14906 - Asking Smarter Questions: Targeted Active Preference Learning for Underspecified Rewards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22285 - Imperfect Is Perfect: Learned Column Prefilling for Branch-Price-and-Cut Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21001 - Blockwise Stabilized Adaptive Cubic Regularization with Subsolvers via Recurrence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22129 - Detectability without Interference: Efficient Canary Design for Privacy Auditing in One Run Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.27292 - Robust Reinforcement Learning for Dynamic Treatment Regimes under Model and Measurement Uncertainty Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22336 - Do As I Do, Not As I Say: On-Policy Distillation Inherits the Teacher in Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20989 - Transfer Learning in Bandits from Unknown Adaptive Policies: Problem-Dependent Lower and Upper Bounds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21582 - Pixels to Tokens: Token Space Efficient Active Learning for Low-Budget Semantic Segmentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20881 - Task-Phase-Conditioned Expert Routing Is Not a Reliable Proxy for Quantization Sensitivity in MoE FFN Tensors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20826 - Agentic-MatriBO: Capability-Compiled Agentic Bayesian Optimization for Materials and Chemical Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17832 - Predict Before You Modify: Learning Improvement Dynamics for Self-Evolving Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13991 - Audio-Visual Dog Identification and Tracking in Real-World Videos Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21011 - Deep Learning of Topological Equivalence Classes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21981 - SEVerA: Verified Synthesis of Self-Evolving Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.25111 - In-Context Learning Before Specialisation: Theory of Learning in a Solvable Topic Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21901 - UniWind: Day-Ahead Wind Power Forecasting via Physics-Informed State Routing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.01670 - Regret Lower Bound for Online Learning of Quantum States with Logarithmic Loss, with Applications to Quantum State Tomography and Confidence Sequences for Matrix Means Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21273 - RM-OPD: On-Policy Distillation for Generative Reward Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20174 - HyCo: Hybrid Drafting for Cost-Efficient Mobile-Cloud Speculative Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21436 - Imaging-anchored multiomics in cardiovascular disease: integrating cardiac imaging, bulk, single-cell, and spatial transcriptomics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.07871 - MARS: A Momentum-Aware Adaptive Rating System for Personalized Assessment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21685 - DataKernelBench: Can LLMs Optimize Database Queries on GPUs? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25061 - Towards Continual Learning: Mitigating Forgetting With Subspace Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22293 - FAME: An FPGA-Based Platform for Approximate Multipliers Evaluation with Pattern-Guided DNN Retraining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17730 - SIEVE: Overcoming Topological Obstruction in Equivariant Self-Supervised Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21087 - SHRED: Self-Play for Heterogeneous Road-Users without Expert Demonstrations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20866 - Tourist arrival forecasting with game-theoretic social influence weighting and deep learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.03411 - Confidence-Calibrated Inference Expansion for Evaluator-Guided Test-Time Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20836 - When Does "Post-Call" Begin? An Availability Contract for Earnings-Call NLP Benchmarks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21659 - Dimension-Free PAC-Bayes Generalization for Deep Neural Networks via Dirichlet Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21340 - Optimal Condition for Initialization Variance in Deep Neural Networks: An SGD Dynamics Perspective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.12834 - Long-Context Drafting Does Not Require Long-Context Drafters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20865 - ReFlow: Replay-Driven Decoupling for Efficient RL Post-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21640 - Two-Stage Score Estimation for Group-Specific Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20979 - Telling FIBS: Probes Effectively Detect Sabotage and Catch Unverbalized Deception Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12445 - Momentum, Commentary Tone, and Earnings Surprise in LLM Financial Forecasts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22043 - PanoDiff-SR: Synthesizing Dental Panoramic Radiographs using Diffusion and Super-resolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.09227 - CompMat-Bench: Benchmarking AI Agents for Computational Materials Science Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00636 - A polylogarithmic bound for list replicability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20657 - GraphBEAT: Graph-based Bucketized Event Aggregation Over Time for Early Risk Stratification of Gastrointestinal Cancers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22014 - Twice Upon a Time: Complementary Representations for Time-Series Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22327 - Flow Matching with Missing Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.28698 - Training-Free On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22236 - AlphaDiana: A Measurement System for Agents in Verifiable Reasoning Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20675 - Feature-preserving Latent-EnKF for Data Assimilation of Flows with Shocks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.12559 - Efficient Agnostic Learning of Univariate Densities Under Local Differential Privacy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21033 - CogDrift-4D: Hierarchical Multimodal Modeling of Temporal Behavioral Decay for MCI Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20877 - Self-Refining Vision Language Model for Robotic Failure Detection and Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.12405 - Differentially Private Distribution Release of Gaussian Mixture Models via KL-Divergence Minimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.03467 - The impact of temporal resampling on the safety of clinical reinforcement learning: A simulated trial Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.06603 - One Bias Score, Two Factors: How Mitigations Affect Option Bias in Multiple-Choice Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20993 - DST-Net: Decomposed Spatio-Temporal Network for Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21123 - Scientific feedback reveals productive regimes beyond training conventions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.15756 - From Perception to Prediction and Intervention: Benchmarking Proactive Video Assistants in Real-Life Scenarios Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21568 - Quality control in sublinear time: a case study via random graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.16531 - When to Align, When to Predict: A Phase Diagram for Multimodal Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11190 - Purify Before You Align: Improving Representation Alignment for Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20761 - Symbolic Mechanistic Data Attribution: Tracing Training Influence to Learned Behavioral Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.29171 - Priming Base Models for Agentic Post-Training: An Open Midtraining Recipe Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22019 - Approaching Backpropagation Accuracy with Weight Perturbation on MNIST Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21665 - Lean Graph Search for Formal Theorem Proving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22339 - Pairwise AUC Optimization Needs Corrective Power: A Unified View Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21743 - TLA-Verus: Generating and Solving Temporal Proof Obligations with LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14923 - Optimal Unambiguous DNFs and Alon-Saks-Seymour Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02533 - Interpreting Language Model Parameters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20748 - An End-to-End Hybrid Quantum-Classical Sampling Workflow for Discrete Markov Random Fields: A Reproducible Case Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.09893 - The importance of tensor handling and implementation of physics-informed DeepONets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22157 - Exploring the Design Space of Permutation Diffusion LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20635 - When the KV Cache Is Slower Than the GPU: Scaling Remote KV Tiers for Context-Parallel Prefill Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21500 - Privacy-Preserving Text Inference for Health-Misinformation Classification and Semantic Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20796 - Thermodynamically Consistent Machine Learning for Fracture Prediction in Heterogeneous Materials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20614 - LLMSurgeon: Diagnosing Data Mixture of Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30348 - E$^2$-OPSD: Taming Entropy Overshoot in On-Policy Self-Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05048 - TASTE: Task-Aware Out-of-Distribution Detection via Stein Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.07640 - Product Interaction: An Algebraic Formalism for Deep Learning Architectures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02573 - MIDI-REPA: Improving Text-to-Music Generation with Symbolic Representation Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20967 - Can AI Forecast the Extremes? Evaluating Probabilistic Weather Models on Tropical Cyclones Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22077 - The Right Byte First: How UTF-16 Helps Multilingual Boundary Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22071 - Temporal Periodic Image Registration with Implicit Neural Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21845 - Does On-Policy Distillation Need to Complete Every Rollout? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21337 - TIPS: A Tiny Inference-time Policy for Scaling in Diffusion Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22099 - DeepUnfolding_Agent: A Classical_Quantum Adaptive Control API Source: arxiv-cs-lg Topic: AI Research (+AI, FastAPI, Python) URL: https://arxiv.org/abs/2610.20615 - Lexical Reference Frames: Interpreting LM Residual Streams in Native Semantics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22169 - Baselines and Score Centering in Policy Gradient Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22263 - Efficiently Estimating Optimal Hyperparameter Scaling Laws through Power-Law Entropy Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01431 - Single-stage joint diffusion of sky images and clear-sky index for ultra-short-term irradiance forecasting: what the frame-to-irradiance stage discards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21795 - Mine, Sample, Render: Test-Time Diversity Alignment Of Generative Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21185 - Two Sample Sizes in Test-Time LLM Ensembling: Buffered ERM and Minimax Theory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21363 - Federated Art Chase: Privacy Leakage and Data Poisoning in Federated Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21547 - Multi-task Neural Diffusion Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.03419 - Reducing the Cost of Qudit State Preparation by Learning a Sparse Structure for SNAP Gates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21557 - When Does Muon Actually Win? A Paired Data-, Time-, and Tuning-Budget Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21555 - How to Train Your Little Dragon: Teaching a Small Language Model to Construct and Refine GPU Optimization Scripts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20980 - Inherent Trade-offs when Enforcing Correct Data Symmetries in Multi-head Self-attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30417 - Reliable Knowledge Acquisition for Continual Learning Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21739 - L2GSSL: Label-Efficient Local-to-Global Self-Supervised Learning for Volumetric Healthcare Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21356 - LoopAhead: Speculating Ahead for Faster Decoding in Looped Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21594 - Circuit Claims Depend on What Is Extracted and How It Is Compared Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.18921 - Scene Reconstruction Using Ubiquitous Wireless Signals via Diffusion Posterior Inference Over physics-Grounded Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22120 - Linear Strategic Classification with Endogenous Improvements Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01198 - Can Capability Enhancement be Localized? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21294 - Semantic Alignment of EEG and Text: A Contrastive Learning Framework for Decoding Imagined Speech Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20766 - Human Interventions as Labels: Localizing, Steering, and (Sometimes) Editing the Computations Behind LLM Agent Failures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21708 - Self-Scaled Broyden Family of Quasi-Newton Methods in JAX Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.10599 - SelectPFN: Amortized Bayesian Variable Selection for Sparse Nonlinear Regression with Prior-Data Fitted Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21950 - Multi-Reward Hacking: From Aggregation-Induced Drift to Trust-Anchored Defense Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21404 - Calibrated Evidence Inference With a Small, Permissively Licensed Open Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07019 - Identifier-Free Code Embedding Models for Scalable Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05251 - Parallel Layer Normalization for Universal Approximation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.13142 - KnowEEG: Explainable Knowledge Driven EEG Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.00541 - Learning Lean Feedback for Efficient Proof-Candidate Evaluation on GPUs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21881 - Measuring the local shape of learning-rate transfer curves Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21814 - LASER: Latent Space Adjoint Matching for Support-Constrained Entropy-Regularized Offline RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08989 - Complete or Sparse: A Tale of Two Identifiabilities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20851 - Each Reward to Its Relevant Tokens: Reward-Specific Token-Level Credit Assignment for Multi-Reward RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21439 - Harmful Partial Interventions and Benign Leakage in Concept-based Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21750 - ManifoldFlow: Spectrum-Learnable Stiefel Optimization via SPD Relaxation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04535 - Neuro-Relational Programs: Unifying Queries and Neural Computation over Structured Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11946 - 3DTCR: Vortex-following generative reconstruction improves tropical cyclone intensity prediction from global AI weather forecasts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.13049 - Rethinking Successive Rejects Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22051 - Local Epochs as Optimal Stopping: Theory and Evidence in Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21832 - Predicting Live Birth After Fresh Embryo Transfer in IVF/ICSI: Differential ICM/Trophectoderm Morphology Encoding and a Hybrid Attention--Logistic Regression Ensemble Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21134 - Replicable Dueling Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20908 - OS-Helix: Unifying GUI Interaction and Code Execution in Native Computer-Using Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22234 - Stochastic Gradient Descent: A Nonlinear Time Series Perspective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20894 - Coordination-Free Workload Regularization for Variable-Cost Distributed Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21162 - Iterative Neural Variational Solver of Committor Function in Under-damped Langevin Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20617 - Learning Changes the World and Then What Was Learned has Changed: Training and Deploying Neural Networks in the Control Loop Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22084 - When is a better LLM worth paying for? Stochastic Optimization with Switching Mixed-Fidelity Oracles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21139 - On the Stability and Convergence of Flow Map Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20674 - Mind the Gap: Structure-Aware Consistency in Preference Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.27733 - Topology-Inspired Fine-Tuning for Wind-Field Super-Resolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22262 - Bellman-Consistent Trajectory RL for LLM Arithmetic Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21060 - When Should a Low-Light Pipeline Generate? Auditable Risk Control for Selective Generative Enhancement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21335 - Architecting for Hardware Diversity: Meta's End-to-End Co-Design for High-Performance AI Training on AMD GPUs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22230 - Linear Independence of Polynomial Compositions with Bounded Input Degree Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20825 - Diffusion Language Models as Open Quantum Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21672 - ManiFusion: Unlocking the High-Throughput Generation via Superposition in Manifold Space Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21433 - Self-improving data synthesis enables scalable adaptation of embedding models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14730 - TensorDex: A Compact, Tensor-Centric Storage System for Modern AI Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.17104 - Formal Bayesian Transfer Learning via the Total Risk Prior Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.23768 - Clean Data Can Still Carry Backdoors: Support-Persistent Backdoors for Model Reuse Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21208 - Graph Additive Models disentangling feature, topology, and interactions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20662 - Co-Evolving Acting and Forecasting for Language Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20597 - Feature Elicitation for SAE Steering of Deceptive Behaviour in Small LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20638 - Causal Integrated Gradients: Scalable Feature Attribution Along Causal Paths Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22126 - Memory as Weights: Internalizing Long-Term History for Streaming Videos Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22070 - Denoising Score Matching in Diffusion Models: The Effect of Rank Constraints on Generalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20850 - Sliced Wasserstein Sketches with Error Certificates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20788 - When Is Muon Optimal? Radial Fragility and Minimax Geometry Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21549 - CoCopula: Conformal Calibration and Copula Aggregation for Reliable Renewable Energy Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02583 - A Distribution-to-Distribution Neural Probabilistic Forecasting Framework for Dynamical Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.25370 - Clinically Interpretable Biological Age Estimation Using CatBoost and SHAP with Continuous and Categorical Features from NHANES Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20868 - Replica Symmetry Breaking and Algorithmic Thresholds in Empirical Risk Minimization under Multi-Index Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.28573 - HAServe: Horizon-Aware Scheduling and Memory Co-Design for Efficient LLM Serving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08581 - Provably Efficient Risk-Sensitive Offline Reinforcement Learning via Optimized Certainty Equivalents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21870 - Spectrum Is Not Enough: A Random-Matrix Account of Data-Free Preconditioning for Differentially Private Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21312 - THEIA: A Multimodal Dataset and Benchmark for Vision-Language Analysis of Layout Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35035 - Graph Homomorphism Distortion: A structural (pseudo)-metric for attributed graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.03068 - LCT: Losslessly Compressed Tensors with GPU friendly execution for Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22179 - RDL-Bench: A Benchmark for Task-Aware Question Answering over Relational Databases Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21382 - GRASP: Plan-Guided Graph Retrieval with Adaptive Fusion and Reranking on Semi-Structured Knowledge Bases Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30237 - Uncertainty Quantification in Pairwise Difference Learning for Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21554 - Learning to Search for Executable Patternmaking from Certified Programs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21579 - BD-HazardVLM: Probing Vision-Language Models for Latent Defensive-Driving Hazards in Bangladesh Road Scenes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20627 - Effectiveness of Hidden-State Probes for Localizing Reasoning Failures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22046 - Close Enough is Nowhere Near: Fidelity-Consumability Decoupling in KV Caches Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22016 - PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviews Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21046 - Training-Free Task Vectors for LLM Behavioral Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09054 - Knowledge That Is Linear Before Fine-Tuning Generalizes After It Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22300 - Same Spectrum, Harder First-Order Training: Phase-Locking in Single- versus Multi-Qubit Re-Uploading Circuits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21778 - ABNAT: Attention-Based Noise-Aware Training for Robust Transformers on Analog Compute-in-Memory Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22065 - Whole-Body Dexterity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22184 - Rethinking Classifier-Free Guidance for TI2I Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21550 - Hindsight-Privileged RLVR: Single-Rollout Token Credit Without Group Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20497 - Compiling Multi-Threshold Operators for Quantized Non-Monotonic and Fine-Granular Activations in Custom-Tailored DNN Accelerators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21825 - Classical methods for modern applications: synthetic tabular data generation using lightweight discrete response continuous latent variable model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21674 - ZenFlow: Enabling Stall-Free Offloading for LLM Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.12242 - Learning Rational Strategies for Temporal Objectives in Multi-Agent Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22287 - Exhaustive Canonical Skeletons Generation: A Formal Dataset for Decomposable Symbolic Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20108 - TabClustPFN: A Prior-data Fitted Network for Tabular Data Clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21656 - Cross-subject decoding of imagined speech from scalp EEG: a leakage-controlled evaluation on three public corpora Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20954 - Pathwise Shrinkage and Probabilistic Calibration of the Multiplicative Half-Cauchy Process Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21136 - RT-J: Large-Scale Pretraining of Relational Transformers for Context-Efficient Predictions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17867 - TGrasp6D: Task-Informed Vision-Language Priors and Pose Refinement enable Zero-Shot Task-Oriented 6DoF Grasping Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20901 - Computational and Statistical Hardness of Calibration Distance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18391 - Set Membership Estimation for Stochastic Linear Contextual Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.20022 - The Lagrangian Structure of Cost-Penalized Active Feature Acquisition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21919 - Attention over noisy examples: generalization and memorization in the exponential Hopfield network Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22191 - EV-JEPA: Elastic V-JEPA for Any Device and Cross-Device Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14324 - CIM-Embed: Learning Instruction-Conditioned Multimodal Embeddings for Clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21805 - SurvICL: a Foundation Model for in-context Survival Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22242 - AlphaRLM: Aligning Language Models for Literature-Grounded Symbolic Factor Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14959 - PocketTSLM: Deploying an On-Device Soft-Prompt Time-Series Language Model for Privacy-Preserving Smartphone Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21308 - MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22344 - INTERVenE: Temporal-Abstraction-Interval Based Transformers for Short-Horizon Medical Event Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29901 - Fault Detection and Bit-Error Rate Diagnostics in Optical Wireless Links Using Edge-AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21402 - Causal Syntax Circuits in CodeLMs: Budget and Probe Decide What Looks Localised Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20683 - Optimal Explicit and Implicit Regularization Strengths in High-Dimensional Continual Linear Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20804 - Can LLMs Anticipate Their Cruxes? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21006 - A Large-Scale Dataset for Multi-Class Financial News Classification in Brazilian Portuguese Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20630 - CIViC: Evidence Gates for Audio-Conditioned Visual Prediction on Proxy Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15327 - FutureLift: Lifting Trajectory Proposals into Bidirectional Future Graphs for Motion Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22215 - Language Models Can Control Their Own Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02737 - CoTranslator: Reverse to Forward Chain-of-Thought Translator for Reasoning Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20828 - Latent Annealed Posterior Sampling with a Variance-Preserving Bridge for Sparsely Observed Random Fields Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20659 - DialFork: Going Beyond Factuality to Evaluate Procedural Hallucination in Conversational Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21561 - Noise-Space Reward Alignment for Few-Step Generative Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21125 - Feasibility Ceilings Before Learning: Sizing and Timing Bounds for Drone-Mesh Interception Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20823 - Learning to Forecast on Multiple Spatiotemporal Hierarchies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21414 - Interpretable but Fragile? Robustness of Concept Bottlenecks under Geometric-Semantic Perturbations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38625 - On the Last-Iterate Convergence of Clipped Gradient Methods Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21026 - Decoding Naturalistic Speech from fMRI with Temporal Modeling and Multimodal Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22049 - Right Answer, Wrong Tokens: Tail-Aware Credit Calibration for RLVR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.07976 - Backward Compatibility in Zero-Bit Neural Audio Watermarking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22296 - Bridging the Gap: Converting Read Text to Conversational Dialogue Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18001 - Language Is a Security Surface for Agent Guards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22244 - Multi-Modal, Multi-Temporal Geospatial Foundation Models Improve Global Above-Ground Biomass Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.04792 - ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.03874 - Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20243 - DeFlow: Decoupling Behavior-Prior Modeling and Value Maximization for Offline Policy Extraction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.10471 - ETH: Data-Balanced Heterogeneous Pipeline Parallelism for Training Large Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22035 - Language Models Share a Readout Bottleneck in Working Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21176 - ContextLift: Breaking the Spurious Correlation Behind Conditional Emergent Misalignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21633 - Honesty is the Best Policy ... or is it? Demand Management for Probabilistic Service Options Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21351 - A Quantum Machine Learning Approach to Content-Based Media Recommendation Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.21562 - Learning and Forecasting Multiscale Spatiotemporal Epidemic Dynamics with Lagrangian-Eulerian Graph Neural ODEs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21223 - When Do Learned Blocks Preserve Causal Meaning? Block Identifiability and Constructive Causal Abstractions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18155 - Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.29983 - Local Temporal Contrasts on Human Motion Data Induce a Latent Geometry Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21630 - LOOP-MAC: Learning-Based Multi-Agent Coordination with Guaranteed Local Feasibility in a Virtual Power Plant Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2310.17882 - O-RAN-Native Jamming Detection Under Network Heterogeneity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20816 - Kolab: Benchmarking Human-Agent Collaboration in Long-Horizon Workflows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21109 - Uncertainty-Aware Federated Learning for Joint Communication and Computation in XR Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21969 - Phase Kernel Lifts Capacity of Dense Associative Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21493 - REKI: Registering Knowledge in VLAs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22178 - Near-Exponential Convergence Rates for kNN Classification based on Boltzmann Margin Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10361 - Soft Sensor for Bottom-Hole Pressure Estimation in Petroleum Wells Using Long Short-Term Memory and Transfer Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.03737 - Evolutionary Multi-Task Optimization for LLM-Guided Program Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22613 - EEG-Based Prediction of Music Enjoyment Using Deep Learning with Explainable Temporal Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20795 - Beyond Downstream QA: Rethinking How We Evaluate Agent Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22209 - StochLOB: Heavy-Tailed Score Matching for Robust Limit Order Book Trend Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21081 - Resisting Harmful Instructions through Training-Free Weight Editing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21189 - Patch where the text is new: a compression view of where byte-level models should spend compute Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22100 - Structure-Preserving Correction Learning for Sparse Bayesian Inference in Brain Source Imaging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07196 - FIRM: Fisher-Informed Retention Merging for Federated LLM Unlearning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21720 - A Greedy PDE Router for Blending Neural Operators and Classical Methods Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.24814 - BOLT: Universal Classifier Training via a Bayes-Error Upper Bound Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.07754 - ChaosBench-Logic v2: Evaluating LLM Logical Reasoning over Dynamical Systems at Scale Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24305 - HarnessMDP: Learning to Control LLM Agent Harnesses with Offline Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.05458 - OntoAct: Hypothesis-Based Neuro-Symbolic Agents through Ontological Abstraction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21983 - Explore Once, Evaluate Many: Multiple Policy Evaluation for Stochastic Linear Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22252 - N-Gram Memories at Two Bits: Quantizing Lookup Tables in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21810 - DYSANOS Generative Dynamic Smooth Arbitrage-free Non-parametric Option Surfaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12587 - Distributionally Robust Regularization of Sparse Integer Programming Trained Learning Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2311.01994 - Specification Gaming and a Constrained Reinforcement Learning Mitigation in a Cleaning Gridworld Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22152 - FANTF: Fuzzy attention network based transformers for time series analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.00070 - Gibbs-Gap Policy Optimization for Off-Policy RL with Verifiable Rewards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20814 - Learn Only Where You Can't Compute: Structured Corrections to Gaussian Process Posteriors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21977 - What Does History Add? Calendar Controls and Information-Timing Audits for University Trajectory Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21419 - ClaimScope: Label-Blind Witness Verification for Mathematical Claim Auditing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21581 - TimeCap: A Scalable Open-Source Pipeline for Captioning Wearable Health Time-Series Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21274 - Trajectory-Level Speculation with Semantic Verification for Tool-Using Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21463 - Adaptive Randomized Neural Networks for PDEs: Structure-Aware Feature Redistribution and Residual-Driven Block Enrichment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21077 - Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21601 - Time-partitioning Gaussian Process Mixture Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20860 - Learning Not To Interfere: Adapting Experts For Model Merging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.13467 - Online Quantile Omniprediction for Proper Losses Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21342 - Representation Redistribution in Sparse Autoencoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21240 - Quantile-Guided Diffusion for Probabilistic Time-Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20739 - The Delegation Dilemma: Economies of Scale, Accountability, and Polycentric Governance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21746 - Task-Centric Multimodal Learning for Cognitive Impairment Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20906 - Memorilla: Latent Semantic Memory for LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21375 - Designing Experiments for External Decision Makers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22032 - Scaling Multilingual Mixture-of-Experts: How Language Coverage Changes Capacity and Compute Allocation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20247 - AbridgeKV: Compressing Long Reasoning into the KV Cache of Learned Pause Tokens Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20641 - Locking Pretrained Weights via Deep Low-Rank Residual Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10777 - GACC-Bench: Benchmarking Goal-Adaptive Context Compression Ability across Large Language Models Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.21893 - GraphCompliance: Structure-Aware Regulatory Compliance through Policy-Context Graph Alignment Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2510.26309 - What Tracks Hard-Negative Transfer? A Study of Lexical and Semantic Signals Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2603.20990 - CARA: Causally Guided Retrieval Agent for Question Answering Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.22017 - Making every stage of medical device document assessment with large language models deterministic Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.21300 - Knowledge Graphs as Files: An Agent Harness Where Tool Creation and Tool Use Co-Evolve Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.18616 - The MPB Corpus: A Dataset of Melody, Rhythm, Harmony, and Melody-Harmony Relationships in Brazilian Popular Music Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.13842 - Aligning LLMs with Sparse Retrieval via Adaptive Sparse Supervision Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.21877 - How Do LLM-Generated Texts Impact Term-Based Retrieval Models? Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2508.17715 - RecSoup: Efficient Model Merging Approach for Controllable Multi-Objective Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.21220 - SSR: Structural Signal Retriever for Scalable Agent Discovery in LLM-Orchestrated Multi-Agent Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.21113 - TransX Technical Report: Scaling Sequence Transduction for Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.20913 - Idea2Prior: Auditable Paper Retrieval and Ranking from Research Ideas Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.20857 - MemSyco-Bench: Benchmarking Sycophancy in Agent Memory Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2607.01071 - Enhancing Knowledge Density via Hierarchical Context Pruning for Retrieval-Augmented Repository-Level Code Completion Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2508.10068 - ReviewPilot: A Multi-Agent System for Screening and Data Extraction in Systematic Reviews Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.21042 - Retrieved but Not Read: Understanding Why Search-Augmented LLMs Fail to Use Available Evidence Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.21731 - Information-Gain Calibrated On-Policy Distillation for Deep Search Agents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.20664 - TRACER: Trajectory-Aware Tool Retrieval for LLM Agents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.21267 - VoteGEO-Bench: Measuring the Impact of Generative Engine Optimization on Electoral Visibility Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.21330 - Learning When to Think: Utility-Guided Adaptive Reasoning for Efficient Text Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.21030 - When Inputs Receive No Score: Evaluating Open-Web Event Admission on the Complete Stream Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.17814 - Multi-Agent Transactive Memory Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2606.19911 - KoViDoRe: A Benchmark for Korean Visual Document Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.20840 - Prune the Summary, Not the History: Source-Judged Compaction for Long-Horizon Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20927 - PRISM: PRIvileged Sibling-guided Multi-Agent Topology Design Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20628 - Translation Circuit Discovery and Targeted Optimization for Low-Resource Multilingual Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21456 - MBBQ: A Dataset for Cross-Lingual Comparison of Stereotypes in Generative LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.07243 - LLMR: Knowledge Distillation with a Large Language Model-Induced Reward Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2409.12500 - GSM: Efficient Language Modeling with Shared Global State Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33465 - CoTS: Competitive Token Selection for Latent Reasoning in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20642 - CLUE: Uncovering Social Context for Pragmatic Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22167 - Towards Emotion Consistency Analysis of Large Language Models in Emotional Conversational Contexts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06476 - The Necessity of Setting Temperature in LLM-as-a-Judge Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.28304 - BLOOM-WILT: Logit Tilting for Behaviour Elicitation in Automated LLM Auditing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.31105 - Do Agents Need a New Kind of Paper? SPRA: Structured Paper Representation for Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21424 - EMO: A Closed-Loop Test-Time Computation Framework via Alternating Context Optimization and Logits Steering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22160 - Does Personalization Break Trust? Open-Set Rejection Calibration Under Few-Shot On-Device Intent Adaptation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20652 - Intern-Decision: Efficient Multimodal Decision Making with Autoregressive Masked Language Modeling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22131 - X-Alpha: An AI Quant Researcher with Memory-Driven Self-Evolution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.08332 - VALCON: Benchmarking and Enhancing Value Consistency in Large Language Models via Dual-Role Variation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21304 - In the Guise of Correction: How Framing and Cultural Adaptation Erode LLM Safety on Real-World Criminal Cases Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21789 - Hy-Memory-30B-A3B: Attributed Reinforcement Learning for Long-Term Memory Writing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22196 - SCRIBE: Scalable Contextual Representations of Interpretable Brain-Grounded Semantics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21518 - TEM: Temporal State Tracking Memory for Large Language Model Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21900 - From Long Context to Selective Memory:A Survey of Memory-Centric Compression for Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21165 - BASIS: Evaluating Belief-Aware Solutions in Interactive Settings beyond Instructions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.13832 - Stop Training Against Soft Users: Mentalized Adversarial Self-Play for Proactive Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21156 - Can LLMs Tell Stories Out of Order? A Corpus and Benchmark for Nonlinear Narrative Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21468 - VELD-QA: A Large-Scale Dataset for Visual Evidence Grounding and Question Answering in Long Documents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20964 - HTN-Orchestrate: A Hierarchical Task Network Framework for Multi-Agent Orchestration Source: arxiv-cs-cl Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.22195 - Auditing Escalation Reliability in Healthcare LLM Agents: A Perturbation-Controlled Benchmark of Workflow-State Failures Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21270 - Beyond Context Length: Characterising the Difficulty of Long-Context Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22067 - Reasoning without Gold Standards: A Proxy-Judge Theory of Autoformalization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09449 - A generative-informed neuro-symbolic framework for syntactic ambiguity resolution: Evidence from Arabic DPs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02529 - Enhancing Multimodal RLVR with Pairwise Token Contrast and Adaptive Trajectory Confidence Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21671 - Believed but Not Said: Measuring Hidden Belief Collapse in Multi-Agent LLM Discussions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22138 - Emotion Is Not External Knowledge: Internal Attention Signals for Affective State Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21347 - Archer: Adaptive Reuse of Cached Hidden States for Efficient Rollback in Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.08086 - Writability and the Pathway: A Controlled Study of Knowledge Injection into Addressed Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21553 - SkillNEO: Non-Elitist Evolutionary Optimization of Agent Skills Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20926 - Where Is the "Self" of a Large Language Model? -- From Self-Index to Self-Reference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16717 - PEDBench: Can Speech Models Detect Phonetic Errors? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20830 - APRiL: An Open-ended Benchmark for Chinese Social Awareness in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20785 - Towards Better Aligned LLM Judges for Radiology Report Evaluation across Modalities and Anatomies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.03376 - MagiC: Evaluating Multimodal Cognition Toward Grounded Visual Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.07297 - Not X, but When: Diagnosing a Mandarin LLM Writing Tic through Contextual Appropriateness Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22249 - ARIA: Runtime Inspection and Amendment for Multi-Agent Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20780 - M$^3$R-Bench: A Unified Benchmark for Evidence-Grounded Multimodal Metaphor Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.05817 - Cost-Efficient RAG for Entity Matching with LLMs: A Blocking-based Batch Processing Framework Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.05708 - DischargeBench: Pre-Deployment Evaluation of LLM Discharge Educators through Persona-Grounded Patient Simulation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20827 - FDE-Gym: The Last Mile of AI Delivery Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22350 - Explaining the Roles of Experts in Mixture-of-Experts LLMs for Personalization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22127 - What Makes Good Instruction-Tuning Data? An In-Context Learning Perspective Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.25132 - Multi-Target Few-Shot Prompting with Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22294 - Content associations with answer selection and engagement in supply chain community question answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21807 - WEAVE: Weaving Real-World Code Evolution into Dependency-Structured Tasks for Benchmarking and Training Code Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22039 - Can Crowdsourcing Survive the LLM Era? A Community Survey on Human Data Collection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04924 - MindEval2: Clinically Grounded Patients and Rubrics for Evaluating Language Models in Mental Health Support Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22314 - RenoLayout: Unified Floorplan Renovation and Furniture Layout for Constraint-Aware Residential Design Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21366 - Entertain, then Cancel: How Thinking Makes Reasoning Models Read Some and Or Literally Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21204 - Data Strategies for Large Language Models: A Unified Perspective on the Training Lifecycle Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21681 - OmniVerifier-C1: Decomposed Graded Verifier for Rule-Governed Generative World Modeling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22355 - Automatic Sentence Completion Using Bengali Audio Speech with a Transformer-Based Early Speech Recognition System Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21164 - PremiseSQL: Evaluating Premise Critique and Abstention in Text-to-SQL Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22158 - Spurious Attention Heads in Vision Transformers: Mechanistic Identification of Annotation-Driven Bias in Medical Chest X-Ray Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21638 - Hybrid Generative-Tagging Decoding for Efficient Product Attribute-Value Extraction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21329 - Where Do LLM Ensemble Gains Come From? Decomposing Candidate Value, Diversity, and Aggregation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18786 - DPA-MoE: A Runtime Precision Control Framework for MoE Inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21378 - Evaluation Awareness Beyond English: Do LLMs Act Differently When Tested in Indic Languages? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22333 - Chronoberg: A 250-Year Diachronic Corpus with Temporal Affective Lexicons for Language Model Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.22360 - DocPilot: Interactive Agent Orchestration and Training for Long Visual Document Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21327 - SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07711 - Real-time Chatbot Romance Scam Detection in Stage Classification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20631 - A large-scale pipeline for LLM-assisted corpus annotation: variation and change in the English consider construction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.12306 - Closed-Loop Molecular Inverse Design with Semantic LLM Surrogates Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22967 - AdaptEvo: Learning under Imperfect Supervision through Confidence-Adaptive Training with Knowledge Evolution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11354 - Probing Negation Understanding in Vision-Language Models With Object Attention Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20852 - Grid-Bench: Can LLMs Predict How Discrete Worlds Change? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22312 - Unfragmenting Nawatl NMT: Single-Variant Specialization for Masewalkopa Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22110 - Reference-Guided Turn-Taking Style Transfer for Full-Duplex Spoken Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20763 - EVA-Cap: Optimizing Audiovisual Video Captioning via Event-Centric Alignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22186 - CoSTA: Compressed Speech Token Adaptation for Efficient Spoken Dialogue Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21143 - Analyzing performance of Retrieval Augmented Generation models for Question Answering Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20419 - Towards Reliable Long-Context Reasoning: Detecting Unanswerable Questions via FactGuard Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.05607 - A Jury, Not an Electorate: Label-Free Reliability Estimation for Ensembles of Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21085 - Mind the Shift: Decoding Monetary Policy Stance from FOMC Statements with Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.14313 - Wolof-Adapted Industry-Ready Open-Weight Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20824 - Explanation Generation for Contradiction Reconciliation with LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.22735 - Hitting a Moving Target: Test-Time Adaptation for AI Text Detection under Continual Distribution Shift Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.25152 - Change the Number, Change the Answer: Assessing Rating Scale Sensitivity in LLM-Based Text Scoring Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22187 - SITAR: A Situational Distortion Metric for Automatic Speech Recognition Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21440 - When Reasoning Traces Conflict with Evidence: How Answer Configuration Shapes Evidence Following Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20805 - Name-Bias in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22053 - Compression Does Not End at Selection: Post-Selection Positional Geometry for Sparse KV Caches Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.21126 - 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 - Is Text All You Need? Text as a Universal Information Bottleneck for Speech LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09366 - Learning Speech Attribute Representations via Multi-Teacher Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21941 - Bias Mitigation in Audio-Enabled LLMs through Adversarial Training and Distillation Methods Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21763 - Evolving Together, Failing Apart: The Skill-Policy Co-evolution Trap in Self-Improving Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20845 - LEAP: Learned Block-wise Evidence Retrieval for Long Audio-Video Perception Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39938 - MemComposer: Learning to Assemble Memories for LLM Agents via Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21091 - AutoSFT: An Agentic System for Automated Data Research in Supervised Fine-Tuning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22194 - Reasoning Error from Known Fact: Step-Level Self-Consistency Group Relative Policy Optimization for LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.18915 - RefactorPlatform: An Open-Source Harness for Controlled Evaluation of Repository-Scale Refactoring Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04898 - Jev-as-a-Judge for RAG Claim Verification: Confidence-Gated Cascading Between a Non-Generative Verifier and a Frontier LLM Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20634 - Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.12036 - $\Phi$-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10226 - A primer on evaluation methods for large language models in healthcare Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14819 - Planning Commitment of LLM under Partial Observability Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21108 - MIXAR: Scaling Autoregressive Pixel-based Language Models to Multiple Languages and Scripts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.11575 - Large Language Models Naively Recover Ethnicity from Individual Records Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21132 - MoCo: A One-Stop Shop for Model Collaboration Research Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21257 - Abstracts or full text? Evaluating input scope and computational efficiency in biomedical lay summarization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21690 - JetSpec++: Foresight Parallel Drafting with Self Refinements Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19792 - LLM-Based Weak Annotation for Cybersecurity Tweet Classification: A Teacher-Student Framework Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21254 - ESG-Kor: A Korean Dataset for ESG-related Information Extraction and Practical Use Cases Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21368 - Language Models Struggle to Use Representations Learned In-Context Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.04212 - Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.19747 - Behavioral Forgetting Is Not Privacy in Machine Unlearning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21799 - AI Consilium: a Benchmark of LLM Clinical Multidisciplinary Second Opinions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22298 - Writer-R1: Dynamic Rubric Mining for Reinforcement Learning of Open-Ended Writing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.15061 - Anuvani-Diarization: Zero Shot Speaker Diarization and Annotation Conventions Across 22 Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20327 - When Judges Agree and Are Wrong: Consistency-Accuracy Dissociation as a Blind Spot for Label-Free Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21128 - 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 - Rethinking the Role of Tool Graph Memory in Multi-Turn Tool Use Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21571 - OPRD: On-Policy Reminder Distillation for Long-Horizon Coding Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21496 - From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.27679 - Code-Switching Detection via Language-Selective Dimensions in Speech Foundation Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18726 - Context Injection and Long-Horizon Reliability: Separating Duplicate Recognition, Local Processing, and Counter Tracking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20633 - Documenting Trofinetide Treatment Phenotypes in Rett Syndrome with a Dual-LLM Consensus Pipeline Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22062 - Decomposing Brain-LLM Alignment with Interpretable Semantic Representations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21508 - Dynamic ordering in sequence generation in Transformers: experiments on low-resource Tagging scenarios Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21862 - PRISM: Transfer and Limits of Activation Interventions in Tool-Calling Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20808 - KBS: A Korean Benchmark Suite for Foundation Model Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21227 - FGSS-BO: Feedback-Guided Hypothesis Management for LLM-Based Bayesian Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21246 - QuasiLeak-Bench: Evaluating LLM-Based Privacy Detectors on Policy-Conditioned Quasi-Evidence Group Recovery Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21333 - CARE-SD: Explainable Reasoning Architecture for Local SLM Self-Disclosure Analysis in Textual Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21151 - BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16557 - RoleQ: Role-Aligned Scales for Converting Language Models to Ternary Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21808 - ORACLE-SWE: Quantifying the Contribution of Critical Information Signals on SWE Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.07789 - Multi-SFT: Permissively-Licensed Multilingual Instruction-Following Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22086 - Beyond Retrieval Failure: Understanding Why LLMs Miss Evidence in Multi-Hop RAG Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21184 - SceneWeave: Audience-Guided Scene Exploration for Dramatic Adaptation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21737 - Identifying Effective Strategies in Prompt Evolution for Stress and Emotion Prediction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21407 - Training Reasoning Models to Generate Diverse Scientific Ideas Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22324 - NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08183 - EmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.20012 - Same Context, Different Agents: A Behavioral Study of Semantic Layers, Orchestration and Compaction in Data Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20959 - One Reference or Many? Rethinking Multi-Reference Training for Intermediate-Entropy Text Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22805 - Learning Self-Orchestration in Decentralized Agent Swarms Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22322 - A Self-Improving Agent that Grows its Own DSL: Oracle-Free Operator Induction for Exact Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20809 - No Single Tokenizer Feature Reliably Predicts Downstream Language Model Performance Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21679 - Who May Release an Agent's Promise? Standing over Commitments in Multi-Party Chat Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21203 - The Last Remote Sensing Model Built by Humans? Casting Any Earth Observation Task as Recursive Self-Improvement Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18845 - Can MLLMs Read the Room? A Multimodal Benchmark for Assessing Deception in Multi-Party Social Interactions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.16221 - PREPING: Zero-Task Agent Memory Construction via Self-Practice Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13880 - ZoomCap: Evidence-Routed Visual Zooming for Recoverable Visual Information Transfer Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21320 - Towards Unbiased On-Policy Distillation for Block Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05373 - MeddeX: A Retrieval-Augmented LLaMA-3 System with Gemini Vision for Evidence-Backed Medical Report Analysis Source: arxiv-cs-cl Topic: AI Research (+AI, FastAPI, JavaScript, PostgreSQL, Python, React) URL: https://arxiv.org/abs/2610.20632 - Love for Believable AI: Artificial Partiality and Relationship Persistence as an Engineerable Stance Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09895 - KV$^2$: A Self-Refining KV Cache Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03198 - From Documents to Spans: Span-Centric Learning for LLM-based Explainable Medical Coding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.15270 - RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19705 - EnsembleLink: Accurate Record Linkage Without Training Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21138 - Bias Control and Injection for Multi-Agent Aggregation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21290 - Neither True nor False: Do LLMs Represent Truth-Value Gaps in Plural Predication? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14438 - From Observation to Intervention: Distilling Self-Generated In-Context Demonstrations via Executable Causal Intervention Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21149 - OpCredit: Operation-Aware Policy Learning for Agentic Knowledge Graph Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21345 - Multimodal AI Detection for Math-Heavy Scientific Text Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21062 - LLMs Infer Cultural Context but Fail to Apply It When Responding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17688 - Learning at the Right Pace: Adaptive Data Scheduling Improves LLM Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.22305 - KULTURE Bench: A Benchmark for Assessing Language Model in Korean Cultural Context Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.07251 - Mind the Delay: Latency-aware Query Routing for Heterogeneous LLM pools Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.18253 - Self-Programmed Execution for Language-Model Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06898 - Decentralized LLM Workflows via Sequential Auctions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22201 - From Research Goals to Scientific Closure: Evaluating Agents Through Evidence-Supported Physics Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21767 - StepSafe: Learning Timely Intervention with Context-Aware Safety Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20960 - CriticaLLM: Using LLMs as Autonomous Game Master for Tabletop Role-Playing Games Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21525 - JEPA-DNA: Grounding Genomic Foundation Models through Joint-Embedding Predictive Architectures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.17162 - Tool-Augmented Large Language Models for Reliable Medical Calculation from Patient Notes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21477 - Frame Evidence:A Benchmark for Reference Frames and Visual Evidence in Multi-Image Spatial Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19564 - SOMA: Stack-of-Objects Manipulation using a Quadruped Robot Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20968 - Condition-Contrastive Extrapolation for On-Policy Distillation of Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21195 - SWE-Nexus: Automated Composition of Software Engineering Tasks from Test Execution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20038 - INFUSE: A Unified Surface Benchmark for Indirect Prompt Injection in Agentic Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20776 - Learning to Reason with Selective Internal Feedback Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21392 - Hierarchical Interpretable Multitask Audio Representation Learning: An Analysis of Event-Scene Relationships through the Information Bottleneck Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21520 - BiShield-TEE: On the (In-)Security of Unilateral Weight Obfuscation in On-Device TEE-Shielded LLM Partition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21565 - From Migration to Calibration: Aligning Agents with Deployment Requirements Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35149 - One Is Not Enough: How People Use Multiple AI Models in Everyday Life Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.26107 - DINO-FIL: Multi-Layer Transformer Fusion for Generative Inpainting Forgery Localization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21780 - OTel: Open Telco AI Datasets, Benchmarks, and Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07766 - SCARCE: Emergent Institutions in Long-Horizon Multi-Agent Coding Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21029 - Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.30587 - OmicsBench: a long-horizon multi-turn benchmark of AI agents on research-study-scale bioinformatics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21074 - X-Fly: Learning to Reach and Stop in Full-Chunk Aerial Vision-Language Navigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21450 - Stronger Judges Do Not See More: Deployment-Integrity Blindness in LLM Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21135 - Constrained Multi-Agent Reinforcement Learning in Imagination Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21319 - Independent Data-Integrity Verification for LLM-Driven Functional Coverage Closure in Hardware Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21570 - WorkflowPerturb: Calibrated Stress Tests for Evaluating Multi-Agent Workflow Metrics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.17990 - Motion- and Gravity-Aware Feedforward 3D Reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22177 - PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23074 - When Reasoning Is Not Enough: Proactive Inquiry for Cross-Modal Safety in Multimodal Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22068 - MIRAGE: Stealthy Visual Prompt Injection for Vulnerability Detection in Web Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.20717 - Benchmarking Code LLM-as-a-Judge via Constrained Perturbation and Calibration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.20159 - AgentPerturb: Evaluating LLM Agent Robustness under Controlled Interaction Perturbations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21624 - GraphACM: Graph-based Action Consistency Measurement for Uncertainty Quantification in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22031 - MetaExp: Learning to Self-Improve through Experience via Verifiable Cross-Task Environment Scaling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21492 - Asynchrony Is Nearly Free for Evolution Strategies on Long-Horizon LLM Agentic Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04196 - Language models recognize dropout and Gaussian noise applied to their activations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.17465 - Dexterity from Supervised Play Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22340 - Evaluating Inquiry Learning in LLM-Based Agents: Hypothesizing, Reasoning, and Exploration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21604 - RAG-RST: Retrieved Exemplars as In-Context Discourse Schema for RST Parsing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22150 - Anvil: Scaling Embodied Spatial Intelligence through Knowledge Recirculation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21882 - CoDA: Co-Evolution of Data Engines and Action Policies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22362 - Improving Environment-Agnostic Coding Agents: The Role of Scaffolding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22289 - JevAgentHarness: Benchmarking, Deploying and Training Decision Models That Share Control with LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21412 - Diviner: Agentic RCA with Human-Governed Adaptation for Large-Scale Infrastructure Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21281 - The Density of Thought: Predicting and Steering Reasoning in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21286 - Limitations on Autoregressive Token Generation via Sequential Sampling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14615 - Where, How, and When: Query-Guided Grounding for Video Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21422 - ParanoiaEval: Benchmarking Unnecessary Defensive Work in Agentic Coding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08662 - Agent Status Protocol (ASP): A Lightweight Specification for State Reporting in Multi-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21538 - SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03056 - Screwtape: Adversarial Transcript Editing for Monitor Red-Teaming Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20941 - Cross-Embodiment Causal Transfer from Human Videos to Robot Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21798 - Prospective multi-pathogen disease forecasting using autonomous LLM-guided tree search Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16238 - MEMONDEMAND: A Memory Management System for Large-Scale Enterprise Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22141 - Realtime-Bench: Can Frontier Models Solve Real-time Interactive Problems? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22155 - CleanRM: Reward Modeling from Noisy Feedback with a Few Clean Feedback for RLHF Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21138 - SecureClaw: Clawing Back Control of LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09549 - Active Learning of Fractional-Order Viscoelastic Model Parameters for Realistic Haptic Rendering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.00667 - VOiLA: Vectorized Online Planning with Learned Diffusion Models for POMDP Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.19729 - 3DCodeVerse: Exploring 3D Worlds as Code Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22341 - Neural Visual Decoding via Cognitive guided Adaptive Blurring and Information Constrained Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16418 - Terminal-RSI: Recursive Self-Improving Terminal Agents via Recursive Self-Rewrite and Policy-Refine Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22192 - Can Visual Generation Expand What Unified Multimodal Models Know? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21459 - Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02522 - Why Do Agent Teams Fail Across Boundaries? A Failure Taxonomy for Agent-to-Agent Systems with Private States Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19342 - ISW-Agent: Integrating LLM-Driven Dialogue with n8n Workflow for Internal Solitary Wave Remote Sensing Image Processing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21502 - GNN-Guided Local Refinement for Efficient Layout Decomposition with DSA-MP Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22214 - RMBench: Memory-Dependent Robotic Manipulation Benchmark with Insights into Policy Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.01229 - In-Context Preference-Conditioned Pareto Set Learning from Limited Offline Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21736 - RICE-Alpha: Reliability-Informed Correction with Event Graphs for LLM-Agent Stock Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34004 - Language-Based Agent Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12863 - When Correctness Feedback Erases Evidence: Phase-Separated Completeness Auditing in Verus Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20676 - LLMON: An LLM-native Markup Language to Leverage Structure and Semantics at the LLM Interface Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.22519 - Open Benchmark of AI Impact on Humans (ImpactBench): an expert-guided, open platform for the holistic evaluation of AI impact on humans Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20690 - Counterfactual Neighborhood Risk Fields: Evidence-Grounded Selective Safety for Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20679 - Learning When to Withdraw: Curriculum Coverage and Rule-Specific Failures in Fine-Tuned Language Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21045 - T2-z: Test-Time Optimization of Environment Latents for Robotic World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22364 - RAC: A Relational Agent Contract for Constraint-Governed Engineering Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20935 - All-in-One Memory: Process-Rewarded Reinforcement Learning for Memory Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21147 - Uncovering Grounding IDs: How External Cues Shape Multi-Modal Binding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.24072 - When Do LLMs Apply the Wrong Law? Diagnosing LLM Failures in Temporal Legal Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14610 - AVALON: Zero-Shot Indoor Navigation with Human-Seeded Topological Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21586 - Failure Is the Mother of Success: Recovering Supervision with Grounding Hindsight Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21018 - Functional Subnetwork Localization for Efficient Continual Learning in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21537 - Volition Elicitation: Operational Semantics for People and Their Machines Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.14138 - BeatEdit: Symbolic Music Generation as Explicit Editing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.11124 - QREF: Improving DeepSearch Agents by Aligning Search with Reasoning via Query Refinement and Evidence Filtering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21512 - MID: Mask-Image Distributional Divergence for Evaluating Medical Image Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17354 - Recursive Reward Improvement via Adversarial Meta-Prompt Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21040 - LTM: Latent Transition Based In-Context Memory for Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21362 - Quantum Versus Classical Machine Learning for Neuropsychiatric Disorders: A Feature-Matched Multi-Cohort Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21344 - Atomic Proximal Policy Optimization for Electric Robo-Taxi Dispatch and Charger Allocation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.13392 - SCOPE: Certified Theorem Proving with a Language Model as the Policy Planner Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08319 - Decoding What iOS Location Services Send to Apple: An LLM Is an Unreliable Analyst but a Useful Toolmaker Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21597 - ANEForge: Python for direct computation on the Apple Neural Engine Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17090 - Loud and Clear: Making Visual Evidence Count in Multimodal Document RAG Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21318 - AgentEval: Evidence-Bounded Assessment of Stateful Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21177 - RAP-WAM: Learning World-Action Models through Predictive Rehearsal and Action Perturbations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16443 - TRACE: Topology-Aware Reconnection via Prediction-Adaptive Connectivity Enforcement for Thin-Structure Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22210 - Witness Overlap: Directional Provenance Inside Open-Weight Model Families Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31784 - Anticipatory Commonsense with Moving Objects: An ASP-Based Framework for Predictive Reasoning with Interacting Trajectories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20867 - Hierarchical Graph Convolutional Network Approach for Detecting Low-Quality Documents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21350 - X-RIC: An Agentic RAN-Intelligent Controller Benchmark for Enhancing Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22269 - Mallea: Building, Steering, and Memorizing Worlds with Coding Agent Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21283 - Global Coherence: When Every Agent Is Right and the Team Is Still Wrong - A Local-to-Global Semantic Foundation for Multi-Agent Collaboration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02036 - MSP: Modality Self-Play for Training Multimodal LLMs Without Paired Cross-Modal Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20965 - Incentivizing Tool-Use Reinforcement Learning for Post-Arrival Emergency Care Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21449 - InverFill: One-Step Inversion for Enhanced Few-Step Diffusion Inpainting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.23463 - Learning from Interaction Experience via Localized Context Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21427 - Filling Before Advancing: Capability-Gap-Driven Post-Training for Scenario-Specialized Remote Sensing MLLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22205 - Adaptive Duration Model for Text Speech Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.22612 - CART: Compatible Routing for Multimodal Continual Instruction Tuning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22137 - InkSight: Offline-to-Online Handwriting Conversion by Teaching Vision-Language Models to Read and Write Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2402.05804 - A Multi-Tiered AI Accessibility Model (MAIAM): Proportionate Access and Capability Limits for Comprehensive Frontier AI Safety Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20921 - TRACER: A Multimodal Harness for Patient Care in Hospitals Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21266 - CF-AVSS: A Coarse-to-Fine Audio-Visual Speech Separation Framework with Target-Speaker Refinement and Post-Fusion for Real-World AVSE Challenge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21773 - Deep Reinforcement Learning for HPC Job Scheduling: A Statistical Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21008 - AutoOnboarder: Autonomously Onboarding LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21218 - LOADBench: A Large Open Analog Dataset and Benchmark for Machine Learning in IC Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21591 - Constructing and Evaluating Clinical Reasoning Trajectories for Medical Agent Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05090 - A team of Gemini 4 Argon agents beats Minecraft Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22319 - FedSumUp: User-Auditable Privacy-Aware Representation Sharing for Resource-Constrained Federated Intelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21194 - Prism-1: Position- and Rival-Independent Scoring for System One Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22066 - Truth for Believable AI: Expressed Doubt, Provenance, and Belief Revision as an Engineerable Stance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26035 - Sci$\Pi$vot: Benchmarking Principal-Investigator Judgment at Pivotal Moments of Scientific AutoResearch Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21082 - PriorityFEC: Deadline-Aware Streaming FEC for KV-Cache Handoff in Edge Multi-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21390 - Drive As You Like: Multi-Head Diffusion with Reinforcement Learning for Personalized Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.16947 - The World Won't Wait: Evaluating and Teaching Agents Under a Live Clock Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20665 - Agent Gym: A Framework for Continuous Evaluation and Evolution of LLM Agents Through Human-in-the-Loop Feedback Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15591 - Poison Valleys: Diagnosing Path-Dependent Failure in LLM Code Repair Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21514 - Does Latent Chain-of-Thought Actually Reason? A Single, Unifying Taxonomy for Latent Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21182 - CoWorld Reasoner: Agentic Multimodal Reasoning with the Evolving Video World Model-Driven Harness Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21910 - Designing Transformers for Continuous Diffusion Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22330 - DropKV: Decoupling Residual-Output Perturbation for Near-Optimal KV-Cache Eviction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22130 - Watts If? A Benchmark for Counterfactual Reasoning About the AI Data Center Buildout Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21397 - Are You Sure Your LLM Is Sure? Repairing and Auditing Confidence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22139 - Discovering state-of-the-art quantum circuits with large language models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22367 - From Simulated Citizens to Simulated Deliberation: Challenges in Representation and Interaction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07573 - Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.26428 - Approve What, Exactly? Effect Binding and Trusted Rendering for Agent Step-Up Authorization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21063 - Video-Time Priors for EEG-fNIRS Emotion Regression on Familiar Videos Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03618 - ACEdit: Stable Multi-Turn Image Editing via Asymmetric Conditioning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22328 - When do quantum views help? Complementary classical-quantum representations in multi-view fusion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21395 - Visual Contrastive Self-Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.21556 - What do AI chatbots do after users decline therapeutic redirection for suicide thoughts? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21253 - Rubric Judgments Lack Uncertainty: Conformal Weighting for LLM Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21214 - Reinforcement Learning-driven Diffusion Models: Language, Vision, and Beyond Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21539 - On the Privacy of LLMs: An Ablation Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.02255 - Harness-Bench: Evaluating Agent Harnesses across Models and Realistic Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.27922 - Contextual Probability and Operational Minimality in Tug-of-War Decision Making Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.10034 - Learning from Unverified Peers via Shared Residual Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22080 - VDE Bench: Evaluating The Capability of Image Editing Models to Modify Visual Documents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.00122 - Multi-sourced AI Tutor for Non-Native English Speaker Students Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22163 - MemScope: Evolving Agent Memory Architectures through Localized Code Repair Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21170 - UniFGVC: Universal Training-Free Few-Shot Fine-Grained Vision Classification via Attribute-Aware Multimodal Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.04136 - ReasonUni: Reasoning-Augmented Reconstruction Advances Unified Multimodal Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20781 - MasDrift: Benchmarking Authorization Preservation Across Multi-Agent Architectures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.07556 - SoK: Trading Agents or Market Crashers? Dissecting Robustness and Security Failures in Academic Financial LLM Trading Schemes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19705 - L2G-SR: Learning to Guide LLM-based Symbolic Regression Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20685 - Ontology Refinement with Embeddings and LLMs: A Case Study on CASTON Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21466 - MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20939 - Encoded but Exposed: Language Embeddings can Reveal More Than They Should in Recommender Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21713 - BridgeAfford: Bridging Query-Target Gap for Generalizable 3D Affordance Grounding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21918 - Orchestrating LLM Agents for Scientific Research: A Pilot Study of Multiple Choice Question (MCQ) Generation and Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.18891 - Generative Recursive Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19376 - Task-Level Natural Language Priors as Learning Signals for Low-Resource LLM Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02244 - FedSkillGit: Federated Skill Evolution via Version Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21348 - Qwen-Audio-Jev: A Unified Interface for Audio Decisions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21614 - LCPNet: Latent Consistent Proximal Unfolding Network for Infrared Small Target Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04603 - IneqAgent: Agentic Inequality Proving in Lean with Symbolic Computation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20681 - SonicWorld: Source-Centric Latent Dynamics for Spatial Audio Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17131 - DexMimic: A Generalist Dexterous Hand-Object Tracking Policy via Value-Guided Reset Allocation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19089 - Spec-Driven Development as Prescribed and as Practiced Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25202 - Deep Learning-based Semantic Segmentation of Dental Radiographs: Comparative Evaluation of PSPNet, DeepLabv3, UNet, and UNet++ Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15061 - Proofs Without Nominals: G\"odel's Ontological Argument, its Shallow Embedding, and the Open Questions of the Monatshefte Notes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.36279 - What Coding Agents Leave Unsaid: Measuring Task-State Gaps Between Execution and Reports Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20003 - HIMMEL: Hierarchical Interleaved Multi-stream Motion Encoding for Long Video Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08158 - ChaosBench-Logic: A Benchmark for Logical and Symbolic Reasoning on Chaotic Dynamical Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.01982 - LIBERO-Industry: Benchmarking Robotic Manipulation under Industrial Process Constraints Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16782 - Temporal Specification Guidance for Text-to-Video Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20822 - Jev-LiteMAS: Separating Decisions from Generation in Multi-Agent Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21411 - PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22124 - Progress Reward Model for Reinforcement Learning via Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22056 - 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 - WorldCast: Exploring Intelligent Visual Generation in World State Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20731 - EvoFlux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2606.12674 - RAG4Tickets: AI-Powered Ticket Resolution via Retrieval-Augmented Generation on JIRA and GitHub Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.08667 - AI-Driven Disaster Response and Displacement Monitoring Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21482 - Following Delegation Traces to Study Human Oversight in Interaction with Multimodal AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21948 - T-GADE: Thermodynamical Generative-AI-Driven Evolution of LLM Artifacts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.12286 - Don't Regenerate, Debug: A Domain-Specific Agent for Repairing Near-Miss Accelerator Kernels Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02712 - Agent Skill Framework: Perspectives on the Potential of Small to Medium Language Models in Industrial Environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.16653 - AI and Consumer Rights in India Working Paper Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12863 - Full-Duplex Interaction with Speech, Expressions and Gestures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21452 - Agentic-Priors: Using Large Language Models to Address the Cold Start Problem in Preference Elicitation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21938 - ZeST: A VLM-based Zero-Shot Traversability Navigation for Unknown Environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.19131 - EvolvingBrain: An Adaptive Skill System for Multi-modal Agents Self-Evolution in Open Worlds Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20786 - Open-world AI: a Tale of Three Requirements Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20782 - Skill-Decoupled On-Policy Expert Distillation for Unified Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22217 - Design the Feedback, Not Just the Reward: Environments for Open-Ended Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27906 - Private Retrieval Augmented Generation via Random Projection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22297 - Measuring Harness-Induced Belief Divergence in Multi-Step LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04528 - ARGUS: An Agenda-Driven Framework for Reliable User Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21346 - Data World: Scaling Data Environments from Scratch Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21656 - A Responsibility-Centered Coordination Mechanism for Decentralized Multi-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21243 - MegaMem: A Retrieval Solution for Ultra-Large Context Windows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22137 - GRADS: Graph-Regulated Agentic Data Synthesis with Controllable Difficulty Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21167 - Learning Intrinsic Dynamics in Latent World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21612 - Disagreement-Guided Weak-to-Strong Routing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22245 - CodeHealth Predicts the Token Cost of Agentic Code Review: A Pre-Registered Study of 465 Agent-Authored Pull Requests Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21914 - Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22166 - KACE: Knowledge-Adaptive Context Engineering for Mathematical Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00532 - CABAL: Multi-Agent Simulacra for Tracing the Effects of Collusive Bidding in Peer Review Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05227 - Forecast lead time and the timing of crew deployment for weather-driven power outages using AI weather models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20918 - MemCut: Every Secret Leaves a Trail in the Long-Term Memory of LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21405 - RSIFlow: Adaptive Self-Improvement Workflows with an Evolving Meta-Agent Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21791 - EliteReplay: Preserving Diverse Solutions in RL Post-Training via Quality-Diversity Search Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22290 - FAOPs: Normal Forms and an Algebra for AI Agent Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22061 - Generalising from Self-Produced Data: Model Training Beyond Human Constraints Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.04711 - Matoi: Selective Revalidation of Consequence Evidence for Agent Authorization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21394 - Evaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and Searching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01404 - AI Alignment From Social Choice Perspectives Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.21550 - OnBodyAI - Why the Next AI Needs a Body Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21137 - Co2In: a Bi-level Memory Incremental Learning Framework with Knowledge Encoding, Consolidation, and Integration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21804 - FlashAttention with Statistics: Low-Overhead Attention Features for Compact Hallucination Detectors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21483 - ValueFormer: Stage-Aware Value Labels for Online Failure Detection and VLA Post-Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02958 - AVC-Reward: Event-Centric Audio-Video Consistency Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22321 - KnowGPO: Knowledge-Grouped Policy Optimization for Search Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22331 - Money-Mule Detection as a Relational Learning Problem: A Study on the RBIH NFPC Dataset Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21314 - LEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22280