AI News

Marginal utility, matrix factorization, and the Key-Value (KV) cache: a unified information-economic framework for sovereign geo-mining inference (arxiv.org)

Tailored to you: longitudinal effects of personalising language models (arxiv.org)

A Proposal for an Agentic AI Architecture to Support Multi-Domain Decision-Making in the Brazilian Armed Forces (arxiv.org)

UnifiedPlayers: Enhance Tool-Integrated Reasoning in Agentic Reinforcement Learning (arxiv.org)

FINSKILLOPS: A Self-Evolving Multi-Agent System for SEC Filing QA (arxiv.org)

When2Think: Learning Difficulty-Aware Length Control for Efficient Hybrid Reasoning Models (arxiv.org)

EviRec: Continual Evidence Learning for Dual Cold-Start POI Recommendation (arxiv.org)

Minimax-Optimal Online Contract Design with Unrestricted Bounded Contracts (arxiv.org)

Learning Principal-Agent Contracts for Equitable Smallholder Carbon Farming under Moral Hazard and Adverse Selection (arxiv.org)

SCGFM-ART: Amortized Relational Transport for Structure-Centric Graph Foundation Models (arxiv.org)

EmbodiedMind: Adaptive Data Curation and Prefix-Tree Reinforcement Learning for Efficient Embodied Intelligence (arxiv.org)

PrefixBench-H100: Characterizing Prefix Reuse and Time-to-First-Token in H100 LLM Serving (arxiv.org)

Well-posedness of neural turbulence closures and tangent dissipation (arxiv.org)

UniExo: Unified Multi-Skill Policies for Musculoskeletal Locomotion and Co-Adaptive Exoskeleton Control (arxiv.org)

The Output-Space Hypothesis: Enumerative Equivalence Checking for Tensor Programs (arxiv.org)

Replan, Repair, or Edit? A Unified Empirical Evaluation of Travel Agents for Itinerary Revision under Resource Disruptions (arxiv.org)

ScientistTwo: Pioneering the Human Knowledge Frontier with Autonomous AI (arxiv.org)

Reach or Solve? Attributing Agentic RL Gains with Checkpoint Handoffs (arxiv.org)

From Intent to Action: Benchmarking LLM Safety in Vehicle Voice Command Authorization (arxiv.org)

Cross-Modal Attention Acts as a Frequency Filter: Why Verbose Prompts Improve Robustness in Vision-Language Models (arxiv.org)

Efficiently Linking Unstructured Data for Multi-step Reasoning (arxiv.org)

Predict Before You Deploy: Offline Prediction of Quantization-Induced Task Degradation for World Action Models (arxiv.org)

From Rollout to Reset: A Graph-Based Harness for Autonomous Long-Horizon Manipulation Evaluation (arxiv.org)

Efficient Nash Equilibrium Computation for Cybersecurity Games (arxiv.org)

Riemannian--Lorentz Fusion of Vision Transformers and State-Space Models (arxiv.org)

LinePilot Digitizer: Line-Plot Recovery with Manual and Automatic Calibration (arxiv.org)

Kinematics-Grounded Agentic AI for Robotic Additive Manufacturing Process Planning (arxiv.org)

One Intervention per Component is Enough: Towards Identifiability in Linear Stochastic Dynamics from Steady State (arxiv.org)

Chain-of-Thought Entropy as a Reliability Signal: A Preregistered Reproduction (arxiv.org)

Solving Minimum Span Antibandwidth and Cyclic Antibandwidth Labeling Problems (arxiv.org)

Perception, Layout, and Validation: Calibrated Confidence for Reliable Straight-Through Processing of Financial Documents (arxiv.org)

MTVA-Bench: Evaluating the Language Model Inside Cascaded Voice Agents (arxiv.org)

PaGNet: A Panel-Aware GBDT--Neural Network for Multi-Target Corporate Tax Avoidance Proxy Forecasting (arxiv.org)

Sequential Contextual Fit Predicts Human Behavioural and Neural Dynamics Across Domains (arxiv.org)

GLAMDRING: Gait Learning And Morphology co-Design via Reinforcement LearnING of CPGs (arxiv.org)

Deep Learning Detection of Beyond-General-Relativity Deviations in Gravitational-Wave Signals: A Detection-Threshold Study with Real LIGO Noise (arxiv.org)

AUDITPLAN: Commit, Then Answer for Auditable Safety Alignment (arxiv.org)

Seismic Site Response Prediction from Sparse Observations Using Finite-Element-Pretrained Latent Dynamics (arxiv.org)

Training Neural Networks to Approach the Optimum Bayes Estimator in Dense Multi-Emitter Localization (arxiv.org)

Deep Learning-Based Classification of Cognitive and Resting States Using Electroencephalography Signals (arxiv.org)

Distributionally Robust Federated Learning with Multi-Source Data (arxiv.org)

GAVEL: Graph World Models for Verified and Efficient Long-Horizon LLM Task Planning (arxiv.org)

Physics-Informed Hemodynamic Modeling for Data-Free Prediction and Sparse-Data Assimilation (arxiv.org)

Robust Conformal Intrusion Detection via Traffic-Aware Calibration and Attack-Orbit Invariance (arxiv.org)

Mammography Foundation Models for Opportunistic Prediction of Major Adverse Cardiovascular Events (arxiv.org)

Can Vision-Language Models Judge Olympic Diving? From Reasoning to Scores in Zero-Shot Action Quality Assessment (arxiv.org)

Why Pretraining Fails to Share Cross-Lingual Knowledge (arxiv.org)

Advantage Scale Calibration Imbalance in Group-Relative Optimization under Low-Variance Rewards: Diagnosis and Bounded Recovery (arxiv.org)

YNU-HPCC at SemEval-2025 Task 11: Bridging the Gap in Text-Based Emotion Using Multiple Prediction Headers (arxiv.org)

The AR Fairness Metamodel: A Structured Framework for Fairness Measures (arxiv.org)