AI News

Automating the Expert Eye: A System-Agnostic Deep Learning Framework for Rare Event Discovery in Imbalanced Force Spectroscopy (arxiv.org)

Dense Force Estimation with an Event-based Optical Tactile Sensor (arxiv.org)

Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs (arxiv.org)

PriFT: Prior-Support Guided Supervised Fine-Tuning (arxiv.org)

Zero-Shot Semantic Re-Identification for Autonomous Driving: A VLM Baseline Study (arxiv.org)

SG-OPD: Sign-Gated On-Policy Distillation via Sign-Consistency Gating and Phased Teacher Sampling (arxiv.org)

Multi-View Speech Representation Learning for Parkinson's Disease Detection Using Context-guided Cross-modal Attention (arxiv.org)

SNN-MLIR: An MLIR Dialect for Compiling Neuromorphic SNNs from NIR to Bare-Metal C (arxiv.org)

What Makes Video World Model Latents Action-Relevant: Prediction over Reconstruction (arxiv.org)

SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work? (arxiv.org)

Systematic LLM Translation of Legacy Scientific Code to Differentiable Frameworks: Application to a Land Surface Model (arxiv.org)

Single-Cell Cross-Modal Transfer by Adversarial Fine-Tuning of Foundation Models (arxiv.org)

Transfer learning for causal forest (arxiv.org)

LATTEArena: An Evaluation Framework for LLM-powered Tabular Feature Engineering (Extended Version) (arxiv.org)

Tight Sample Complexity of Transformers (arxiv.org)

Differentially Private Synthetic Data via APIs 4: Tabular Data (arxiv.org)

GPT-Micro: A large language paradigm for accelerated, inexpensive, and thermodynamics-consistent discovery of constitutive models in manufacturing (arxiv.org)

De novo molecular generation with optical property preconditioning at the token level (arxiv.org)

Public Machine Learning Solver Framework for Novices in the Machine Learning Domain (arxiv.org)

REFLECT: Intervention-Supported Error Attribution for Silent Failures in LLM Agent Traces (arxiv.org)

The Token Not Taken: Sampling, State, and the Variability of AI Agent Outputs (arxiv.org)

Baichuan-M4: A Clinical-Grade Medical Agent System for Continuous Care (arxiv.org)

RTL-BenchLS: A Large-Scale Benchmark for RTL Reasoning and Generation with Large Language Models (arxiv.org)

Diverse Thinking Schemata Elicit Better Reasoning in Large Language Models (arxiv.org)

EditSR: Enhancing Neural Symbolic Regression via Edit-based Rectification (arxiv.org)

Neural Field Tokenizations with Hierarchy and Spatial Locality Priors (arxiv.org)

Frequency-Domain Latent Attention Gating for Cross-Domain Token Aggregation (arxiv.org)

Explaining Data Mixing Scaling Laws (arxiv.org)

AttentionCap: Transformer Based Capacitance Matrix Learning Toward Full-Chip Extraction (arxiv.org)

An Effective Router for Vision-Language Model Selection (arxiv.org)

AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models (arxiv.org)

Oversight Has a Capacity: Calibrating Agent Guards to a Subjective, Fatiguing Human (arxiv.org)

Order Matters: Unveiling the Hidden Impact of Macro Placement Sequences via Proxy-Guided LLM Evolution (arxiv.org)

FAME: Forecastability-Aware Mixture of Experts for Heterogeneous Time Series Forecasting (arxiv.org)

Have I Solved This Before? Retrieving Similar Segmentation Problems for Evolutionary Learning (arxiv.org)

TRUST-SCF: Transformer-based Risk Understanding and Scoring for Transactional Supply Chain Finance (arxiv.org)

Conditional Random Ordered Transport Spaces (arxiv.org)

A Unifying View of Attention Sinks: Two Algorithms, Two Solutions (arxiv.org)

Data-driven discovery of governing differential equations across physical systems (arxiv.org)

Can the Environment Speak for Itself? $T^{2}$-GRPO: A Turn-Trajectory Group Relative Policy Optimization for Caregiver Agents (arxiv.org)

Hybrid E-Assessment in Higher Education: Semi-Automated Grading of Paper-Based Written Examinations (arxiv.org)

A Resilience-as-a-Service assessment framework for coordinated disruption response in interdependent urban transit systems (arxiv.org)

ZIPP:Zero-shot Image Personalization from Personas (arxiv.org)

Beyond Pass Rate: A Multilingual, Execution-Grounded Evaluation of Open Code LLMs (arxiv.org)

Constraint-Aware Optimization for Robust Protein Stability Prediction (arxiv.org)

ConSteer-RL: Steering Reasoning Capabilities in Large Language Models via Confidence-Aware Reinforcement Learning (arxiv.org)

DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination (arxiv.org)

Beyond Homophily: Towards Generalized Graph Reconstruction Attack and Defense (arxiv.org)

When Behavioral Safety Evaluation Fails: A Representation-Level Perspective (arxiv.org)

Inference-Time Conformal Reasoning with Valid Factuality Control for Large Language Models (arxiv.org)