AI News

Integrating Feature Understandability into Feature Selection for Human-Centred Tabular Explanations (arxiv.org)

Answer It or Not? Towards Prompt-Adapted Adversarial Images on Vision Language Models (arxiv.org)

MixLID: Token-Level Language Identification in Mixed-Language Text (arxiv.org)

Towards Modality-Agnostic Seizure Classification: A Unified Deep Learning Framework for Heterogeneous EEG and Intracranial EEG Signals (arxiv.org)

VLA-GAUGE: Systematically Evaluating Generalization and Robustness in Vision-Language-Action Models (arxiv.org)

Heuristics are Not Enough: Calibrated and Corrected Caching for Video Diffusion Acceleration (arxiv.org)

PatTransBench: an ipc-stratified, multi-dimensional benchmark for patent machine translation evaluation (arxiv.org)

pi-Net: Empirical Latent Representations for Differentiable Physics Heads in Data-Scarce Systems (arxiv.org)

From Caricature to Collective Artifact: How Persona Construction Drives Polarization in Generative Social Simulations (arxiv.org)

NeuronDiscover: Agent-in-Twin for Mechanistic Discovery in Neuronal Microenvironments with World Action Models (arxiv.org)

Deep kernel hedging (arxiv.org)

TimeES: Probabilistic and Deterministic Time Series Forecasting via Evolutionary Spectra (arxiv.org)

DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecasting (arxiv.org)

Growing and Transferring Pathways for LLM Reinforcement Learning (arxiv.org)

A Versatile Variational Quantum Kernel Framework for Non-Trivial Classification (arxiv.org)

AI Discovery in Combinatorics: From Problems to Solutions and Back to Bigger Problems (arxiv.org)

Making Language the Low-Rate Code of Vision: Successive Refinement from Words to Pixels (arxiv.org)

Overtaught, Underlearned: Learner-Centered Distillation from Multi-Agent Discussion (arxiv.org)

Does the Explanation Drift Before the Guarantee? Label-Free Early Warning on Evolving Graphs (arxiv.org)

Rule-based and reinforcement-learning policies for resource allocation in a pediatric echo lab: a simulation study (arxiv.org)

EAU: Environment-Agent-User Co-evolution for Training User-Centric Agents (arxiv.org)

Boosting the Learning for Ranking Patterns (arxiv.org)

PXRD-Bench: How Close Are We to Determining Crystal Structures from Powder Diffraction? (arxiv.org)

XAI-Guided Fourier Domain Generalisation for Pure-Simulation Sim-to-Real Deep Reinforcement Learning (arxiv.org)

RAP-WAM: Learning World-Action Models through Predictive Rehearsal and Action Perturbations (arxiv.org)

Hierarchical Residual Policy Learning for Real-World Mobile Manipulation with Sparse Human Guidance (arxiv.org)

Modeling and Understanding Neural Weights of Humanoid Policies with Diffusion (arxiv.org)

Co-Evolving Acting and Forecasting for Language Agents (arxiv.org)

Price of Anarchy of First-Price Auctions in Agentic Markets (arxiv.org)

Latent Compaction with Test-Time Training (arxiv.org)

PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis (arxiv.org)

ActiveEvidence: Decision-Focused Evidence Graphs with Verifiable Acquisition Gaps (arxiv.org)

VASPO: Self-Distillation with Privileged Value Estimation (arxiv.org)

VascuSR: Iterative Anatomy-Aware Diffusion for CT Super-Resolution (arxiv.org)

The Anatomy of a Blind Spot: What an LLM Judge Must Be Shown, and How Much (arxiv.org)

Chain Dimension Scaling: Communication-Efficient Loop-Style Scaling for Industrial Short-Video Ranking (arxiv.org)

SLS-Bench: A Benchmark for Incident Log Summarization with Synthetic Observability Data (arxiv.org)

Complex materials engineering via Provenance Action Graphs: potential, structure and demonstration (arxiv.org)

EvoWeb: A Benchmark for Coding Agents on Evolving Web Applications (arxiv.org)

Recursive Environment Scaling for General Long-Horizon Agents (arxiv.org)

RetroPlanner: Multi-Route Expansion and Multi-Objective Reasoning for LLM-Based Retrosynthesis Planning (arxiv.org)

World Models Need a Physical Registry: Learning Internal Predictive States for Physically Plausible World Models (arxiv.org)

Long-Horizon RL Needs Muon (arxiv.org)

SafeAdapt-Poker: Counterfactual Risk Calibration for Budgeted Adaptation under Opponent Shift (arxiv.org)

The COUNT: Counting N-grams Unlocks Scaling on Host Memory and Training-Free Adaptation (arxiv.org)

Generation of data on discontinuous manifolds via continuous stochastic non-invertible networks (arxiv.org)

Same Operation, Different Permission: Evaluating Whether Guardrails Honor Authorization (arxiv.org)

ChronoScribe: Semantic-Numerical Specialization for Instruction-Driven Time Series Forecasting (arxiv.org)

Efficient Multi-Agent Reasoning via Confidence-Guided Adaptive Debate (arxiv.org)

TRAP: Tool-result Replay Attack for Probing Misbinding in LLM Agents (arxiv.org)