AI News

A Quantum Machine Learning Approach to Content-Based Media Recommendation (arxiv.org)

From Perception to Prediction and Intervention: Benchmarking Proactive Video Assistants in Real-Life Scenarios (arxiv.org)

Do Agents Need a New Kind of Paper? SPRA: Structured Paper Representation for Agents (arxiv.org)

Learning from Interaction Experience via Localized Context Distillation (arxiv.org)

Incentivizing Tool-Use Reinforcement Learning for Post-Arrival Emergency Care Prediction (arxiv.org)

Agent Status Protocol (ASP): A Lightweight Specification for State Reporting in Multi-Agent Systems (arxiv.org)

Reinforcement Learning-driven Diffusion Models: Language, Vision, and Beyond (arxiv.org)

ClaimScope: Label-Blind Witness Verification for Mathematical Claim Auditing (arxiv.org)

LOADBench: A Large Open Analog Dataset and Benchmark for Machine Learning in IC Design (arxiv.org)

LoopAhead: Speculating Ahead for Faster Decoding in Looped Language Models (arxiv.org)

Evaluating Inquiry Learning in LLM-Based Agents: Hypothesizing, Reasoning, and Exploration (arxiv.org)

Learning Intrinsic Dynamics in Latent World Models (arxiv.org)

Representation Redistribution in Sparse Autoencoders (arxiv.org)

AgentPerturb: Evaluating LLM Agent Robustness under Controlled Interaction Perturbations (arxiv.org)

The Self-Improvement Problem (arxiv.org)

Co2In: a Bi-level Memory Incremental Learning Framework with Knowledge Encoding, Consolidation, and Integration (arxiv.org)

Prism-1: Position- and Rival-Independent Scoring for System One Models (arxiv.org)

When Reasoning Is Not Enough: Proactive Inquiry for Cross-Modal Safety in Multimodal Large Language Models (arxiv.org)

Learning from Unverified Peers via Shared Residual Distillation (arxiv.org)

PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents (arxiv.org)

The World Won't Wait: Evaluating and Teaching Agents Under a Live Clock (arxiv.org)

Provably Efficient Risk-Sensitive Offline Reinforcement Learning via Optimized Certainty Equivalents (arxiv.org)

Second Maximum of a Gaussian Random Field and Exact (t-)Spacing test (arxiv.org)

A Closed Form Depth-Width Law for Neural Collapse in Deep Linear Networks (arxiv.org)

STAMP: Symmetric Temporal Averaging Message Passing for Domain Adaptation in Chronologically Split Graphs (arxiv.org)

Parallel Layer Normalization for Universal Approximation (arxiv.org)

Multi-task Neural Diffusion Processes (arxiv.org)

Graph Additive Models disentangling feature, topology, and interactions (arxiv.org)

Shortcut Sensitivity in Agent-Safety Evaluations (arxiv.org)

Ranked Right, Sized Wrong: Ensemble Spread Fails Silently at Streamflow Extremes (arxiv.org)

SelectPFN: Amortized Bayesian Variable Selection for Sparse Nonlinear Regression with Prior-Data Fitted Networks (arxiv.org)

A Mixture-of-Experts Framework for Multi-Stream Quickest Change Detection (arxiv.org)

The Tilted Sampling Problem: Optimism, Posterior Sampling, and Logarithmic Regret (arxiv.org)

Follow the Perturbed Leader for Linear Bandits: $\sqrt{T}$ Regret over General Convex Sets (arxiv.org)

TimeCap: A Scalable Open-Source Pipeline for Captioning Wearable Health Time-Series Data (arxiv.org)

Feature Elicitation for SAE Steering of Deceptive Behaviour in Small LLMs (arxiv.org)

Ranking and Partitioning of Attention Heads for Sparse and Continual Reinforcement Learning Fine-tuning (arxiv.org)

Does On-Policy Distillation Need to Complete Every Rollout? (arxiv.org)

Online Quantile Omniprediction for Proper Losses (arxiv.org)

MSP: Modality Self-Play for Training Multimodal LLMs Without Paired Cross-Modal Data (arxiv.org)

DocPilot: Interactive Agent Orchestration and Training for Long Visual Document Understanding (arxiv.org)

Quantum Versus Classical Machine Learning for Neuropsychiatric Disorders: A Feature-Matched Multi-Cohort Evaluation (arxiv.org)

ARGUS: An Agenda-Driven Framework for Reliable User Simulation (arxiv.org)

MemCut: Every Secret Leaves a Trail in the Long-Term Memory of LLM Agents (arxiv.org)

Same Answer, New Box: How Much of RLVR's Out-of-Domain Gain Is Answer Format? (arxiv.org)

KNOU-Flood: Advancing global streamflow forecasting with lead-aware probabilistic machine learning (arxiv.org)

TurboMamba: Faster Inference, Faster Training, and Better Prediction with Lexical Memory (arxiv.org)

Causal Syntax Circuits in CodeLMs: Budget and Probe Decide What Looks Localised (arxiv.org)

DST-Net: Decomposed Spatio-Temporal Network for Time Series Forecasting (arxiv.org)

FedSkillGit: Federated Skill Evolution via Version Control (arxiv.org)