AI News

Offline Apprenticeship Learning for Human-Centric Environments (arxiv.org)

Big Claims, Small Margins: Do Reported GraphLLM Gains Survive Simple Baselines? (arxiv.org)

STAR-XPC: Set Transformer for Estimating X-ray Transmission in Polymer Composites (arxiv.org)

SimHack: Predicting the onset of detectable reward hacking before RL training (arxiv.org)

Scalable Stress-Constrained Topology Optimization: A Super-resolution and Simultaneous Approach Based on Machine Learning (arxiv.org)

Reinforcement learning for hardware acceleration and system-level optimization on FPGA and integrated-circuit platforms: A survey (arxiv.org)

Interaction-Gated Time-Frequency Learning for Parameter-Efficient PPG-Based Heart Rate Estimation (arxiv.org)

To Keep or Not to Keep: Learning KV Cache Retention in Disaggregated LLM Serving Systems (arxiv.org)

Design and Tuning of Multi-Agent Systems Using Bayesian Evolutionary Optimization (arxiv.org)

Recursive Self-Improvement on a Budget: Scoring Code Edits Before They Run (arxiv.org)

SU(2)-Equivariant Spinor Message Passing for Molecular Magnetism (arxiv.org)

DriftNeRF: Cross-Ray Density Drifting for Sparse-View Neural Radiance Fields (arxiv.org)

Dual-Channel Contrastive Encoding of Sperm Whale Coda (arxiv.org)

OccJEPA: Occlusion as Masking for Amodal Video Segmentation (arxiv.org)

Our Own Jev: Typed Decisions in One Forward Pass, from an In-House Judge to Open LoRA Models (arxiv.org)

Target Regeneration Shrinks the Gains of Draft-Training Objectives in Speculative Decoding (arxiv.org)

The Optimal Sampler for Diverse TSP Solutions: Characterization, Limits, and Learning (arxiv.org)

AgentPolicyForge: From Executable Environments to Policy Benchmarks and Adaptive Guards (arxiv.org)

Can Quantum Layers offer Performance and Security Advantages in Vision-Language Models? (arxiv.org)

HyperDrone: Simulation-to-Reality Transfer at Millions of Frames per Second (arxiv.org)

One Policy, Many Styles: Where to Aggregate Preferences for Steerable Humanoid Control? (arxiv.org)

JaxMARL-BC: Multi-Agent Reinforcement Learning for Macroeconomic Modelling, in Seconds (arxiv.org)

Tropical Cyclone Attributes in Sparse Autoencoder Features of an AI Weather Model (arxiv.org)

CSD: Common-Support Distillation for Cross-Tokenizer Knowledge Transfer (arxiv.org)

DualHeads: Reward-tilted few-step diffusion made simple (arxiv.org)

Self-Supervised Tuning of Low-Fidelity Optimization Models via High-Fidelity Feedback (arxiv.org)

KIRA: A Full-Stack Reading Screening System with Dual-Pathway Analysis for Children (arxiv.org)

Sketch2Sim: an end-to-end modular framework for hand-drawn circuit analysis (arxiv.org)

Brittle by Design? Multi-Scenario Reinforcement Learning for Robust Mission Coordination in Systems of Systems (arxiv.org)

Combining Long-Term Memory and LLMs Comes at a High Cost: From Prompt Injection to Persistent Compromise (arxiv.org)

Is Anyone Enforcing the Cartel? What Reinforcement Learning Teaches LLM Agents in Markets (arxiv.org)

SkillEval: Learning Interpretable Ability Profiles of LLMs via Cognitive Diagnosis Models (arxiv.org)

Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild? (arxiv.org)

ROCOCO: Robust Outline Completion of Occluded Curvilinear Objects (arxiv.org)

GPU-Accelerated Construction of the Gabriel Graph: Parallelization Strategies and Applications to Large-Margin Classification and Graph-Based Clustering (arxiv.org)

Understanding the Inner Workings of a State-Space Foundation Model for Limit Order Books (arxiv.org)

Scaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual Worlds (arxiv.org)

Solar System Surface Technosignatures: Searching for Signs of Artificial Design on Extraterrestrial Terrain (arxiv.org)

What Git Does Not Record: Provenance Legibility in Two AI-Assisted Research Repositories (arxiv.org)

Machine-learned spectral PDE solvers for fluids and plasmas (arxiv.org)

Data Schedules and Learning Rate Schedules Should Be Designed Together (arxiv.org)

Benchmarking and Error Analysis of Deep Search and Deep Research LLM Agents (arxiv.org)

Reader--Writer Coupling in Transformer MLPs (arxiv.org)

BrainCodes: A Lightweight EEG Foundation Model over Discrete Neural Codes (arxiv.org)

YingLan: A Multimodal Ocean Foundation Model for Unified Representation Learning from Heterogeneous Observations (arxiv.org)

Interpretable Cutting Plane Selection for Mixed-Integer Linear Programming Using Genetic Programming (arxiv.org)

Flat-RLVR: Sharpness-Aware Reinforcement Learning with Verifiable Rewards for Reasoning Capacity in LLMs (arxiv.org)

Active Learning under Simulated Class Imbalance and Label Shift in Binary Semantic Segmentation (arxiv.org)

Optimized Conformal Selection: Powerful Selective Inference After Data-Dependent Score Construction (arxiv.org)

Multi-Label Sentiment Analysis on 100 Languages with Dynamic Weighting for Label Imbalance (arxiv.org)