AI News

Discrete Neural Interlingua for Ontology-Agnostic EHR Modeling (arxiv.org)

Graph Neural Networks for Astrophysics and Cosmology (arxiv.org)

LOB-Impact Benchmark: Emergent Market Impact in Generative Limit Order Book Models (arxiv.org)

This is SParTA: A modular, efficient and scalable transformer architecture for jet-tagging (arxiv.org)

Ammonia-Hydrogen Phase Equilibria in Planetary Envelopes from First-Principles-Based Machine-Learning Molecular Dynamics (arxiv.org)

Towards Interaction State Recognition in Sensorized Gecko-Inspired Adhesive Interfaces for Orbital Servicing (arxiv.org)

Constructing Challenging Browser-Use Tasks by Controlled Environment Interventions (arxiv.org)

ROSS: Relearning from Self-Generated Rollouts through Selective Supervision (arxiv.org)

$S^3$: Spectral Null-Space Swap Makes Reasoning Models Efficient (arxiv.org)

Retargeting Motions to Diverse Skeletons via Learnable Flattening (arxiv.org)

Cross-disorder Learning of Imaging-derived Joint Mophometric Markers in Alzheimer's and Parkinson's Diseases (arxiv.org)

On the Fragility of Tasks under Composition: Implicit Budgeting in Language Models (arxiv.org)

Low Residuals, Wrong Value: Learning the Viscosity Solution of Hamilton-Jacobi-Isaacs Equations with PINNs (arxiv.org)

Neighborhood-Aware Unlearning for Generative Recommendation (arxiv.org)

TxnQA: Benchmarking Analytical Reasoning and Evidence Grounding over Transaction Event Sequences (arxiv.org)

BridgeCast: Bridging Ocean Wave Forecasts to Reanalysis via Flow Matching with Exogenous Variables (arxiv.org)

EDISCO: Equivariant DIScrete Diffusion for Euclidean Combinatorial Optimization (arxiv.org)

Guided Diffusion for Trustworthy Synthetic Text Generation (arxiv.org)

Universal Online Convex Optimization With Delayed Feedback (arxiv.org)

Pareto-Optimal RTL Code Generation via Multi-Objective Reinforcement Learning with Large Language Models (arxiv.org)

MuPACE: Learning to Pace Muon for LoRA Fine-Tuning (arxiv.org)

Adaptive Pullback: Reweighting Supervision at Penalty Jumps in On-Policy Distillation (arxiv.org)

Large language model and reinforcement learning based autonomous construction and progress updates (arxiv.org)

MedPAO-Assist: Edge-Deployable, Modality-Aware Agentic AI for Radiology Report Structuring (arxiv.org)

DataPraxis: Scaling Analytics Tasks via Verified Workspace Evolution (arxiv.org)

Industrial Agentic AI: LLM-Driven New-Generation Agents for Smart Manufacturing (arxiv.org)

Fix, Not Just Resample: Bounded Compiler-Guided Repair in Lean 4 (arxiv.org)

PULSE: Personalized Opportunistic Learning for Wearable Devices (arxiv.org)

From Complex Histories to Simple Predictors: Predictive Dimension in Dynamic Graph Learning (arxiv.org)

Causal Discovery for Linear Models with Latent Confounding via Multi-domain Identifiable Representation Learning (arxiv.org)

Curriculum Learning for Generative Flexible Docking (arxiv.org)

Coincidence-Maximizing Customer Clustering Using Smart Meter Data (arxiv.org)

MAMath-Bench: Process-Aware and Robust Evaluation of Multimodal Multi-Agent Mathematical Reasoning (arxiv.org)

LightCRS: Lightweight Multi-Domain Conversational Recommendation System (arxiv.org)

When Planning Problems Become Hard for LLMs: Separating Structural Complexity from Semantic Interpretability (arxiv.org)

SPEM: Structure-Aware Procedural Memory for Efficient Skill Use in LLM Agents (arxiv.org)

Global Security Blind Spots: Translation as a Safety Bypass in Low-Resource Languages (arxiv.org)

Parameter-Efficient Adaptation of Time Series Foundation Models for Electrical Load Forecasting (arxiv.org)

Reframing Object-Centric Reinforcement Learning: From Absolute to Relative Representations (arxiv.org)

JAXbounce: A Continuous-Control Pong-Like Benchmark for Active Inference Beyond Low Dimensional Environments (arxiv.org)

TPO: Tri-level Distributionally Robust Learning for OOD Direct Preference Optimization (arxiv.org)

PW-Pruning: Phase-Aware Expert Selection for Speech-Centric Omni-Modal Models (arxiv.org)

Does Multi-Agent Collaboration Reduce Hallucination in Clinical Tasks? (arxiv.org)

Teaching AI Agent to Play Poker Strategically Through Preference Optimization (arxiv.org)

M-Plan: Comprehensive Planning For LLM Agents with Memory Arrangement (arxiv.org)

Physical AI: Concepts, Techniques, and Challenges (arxiv.org)

Learning Normal Coordinates on Riemannian Manifolds with Flow Charts (arxiv.org)

Recommending Bacterial Cultivation Conditions from 16S rRNA (arxiv.org)

Manifold-Informed Neural Networks for Low-Label ECG Electrolyte Inference (arxiv.org)

Observation Assimilation Transformer: Probabilistic Weather Analysis from Sparse Station Observations (arxiv.org)