AI News

Sparse Priors for Efficient Distribution Learning (arxiv.org)

RegKT: Interpretable and Robust Deep Knowledge Tracing With IRT-Regularizer (arxiv.org)

Efficient Architecture Search under Leave-One-Subject-Out Evaluation (arxiv.org)

An Introduction to Compression-Based Machine Learning (arxiv.org)

WS-NeRF: A Mamba-Driven World-State-Aware Adaptive Deblurring Neural Radiance Field (arxiv.org)

Consistent Relexicalization of Clinical Documents using Graph-Based Approach (arxiv.org)

AgentVidBench: A Multi-Hop Video Question Answering Benchmark for Evaluating MLLM Agents (arxiv.org)

Knowledge-Graph-Augmented Chronos-2 for HEC-RAS Surrogate Forecasting (arxiv.org)

From Memory to Behavior: A Behavior-Aware Role-Playing Framework for Social Media Influencers (arxiv.org)

CESBench: Benchmarking Large Language Models on Cryptographic Engineering Security for IoT Devices (arxiv.org)

Co-Evolving Zero-Day Jamming: Adaptive Attack Synthesis and Graph Attention-Based Online Detection (arxiv.org)

Deep Reinforcement Learning with Buffered Quantile Objectives (arxiv.org)

Authorization Revocation for Long-Running AI Agents: Root-Scoped Quiescence under Delegation and Asynchronous Execution (arxiv.org)

Beyond Exact Match: Task-Aware GRPO for Cross-Domain PCBA Visual Question Answering (arxiv.org)

Verify, Don't Trust: Agentic Model Development for Video Discovery Retrieval at Scale (arxiv.org)

VLA-Scope: Shift-Aware Failure Prediction for Vision-Language-Action Models (arxiv.org)

KnowDemo: Knowledge-Guided Robot Demonstration Generation from Human Videos (arxiv.org)

FOCAL-VLA: Subtask-Guided Geometry Distillation and Implicit World Modeling for Vision-Language-Action Models (arxiv.org)

Hallucination-R1: Robustness-Oriented Paraphrase Generation for Factual Consistency (arxiv.org)

Fewer Steps, Better Actions: Rethinking Flow-Matching Inference for VLA Policies (arxiv.org)

Visual Navigation Transformer with Pose Attention (arxiv.org)

SWE-Proof: Can Language Models Resolve Real-World Issues with Machine-Checked Proofs? (arxiv.org)

The Stochastic Shift: A New Evaluation Paradigm for Text-to-SQL with AI Operators (arxiv.org)

Geometry of Values: Task Vector Composition for Ethical Preference Alignment in Language Models (arxiv.org)

Aligning with Lived Experience: Heterogeneous Benefits of Fine Tuning in Mental Health Support Generation (arxiv.org)

PlantShade: Predicting Plant Shadows for Lighting-Aware Robotic Agricultural Operation (arxiv.org)

How Much of a Real Workload Can LLM-Generated GPU Kernels Actually Reach? (arxiv.org)

Physically Based Rendering in the Latent Space (arxiv.org)

Trustworthy FinAInce: Unpacking How AI-Mediated Financial Advice is Judged (arxiv.org)

Bio-MF: Low-Latency and High-Fidelity EEG-to-fNIRS Cross-Modal Generation for Hybrid Motor-Imagery Brain--Computer Interfaces (arxiv.org)

SpaceDiffusion: Over-the-Orbit Diffusion for Space Generate-and-Forward Communications (arxiv.org)

BI-Agent and BI-Bench: Towards Automating End-to-End Business Intelligence (arxiv.org)

Reinforcement learning for post-coronagraphic wavefront control (arxiv.org)

A Hybrid Computational Intelligence Framework for scRNA-seq Imputation: Integrating scRecover and Random Forests (arxiv.org)

Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design (arxiv.org)

CodeMidas: Scaling Agentic Coding RL Environments from Code Itself (arxiv.org)

A Lie Detector Test for Language Models: Reading Knowledge a Model Won't Reveal (arxiv.org)

Learning Cardiac Features: ECG Biometrics Across Time and~Exercise (arxiv.org)

A Smoothed Discrepancy Principle for Random Feature Methods and Neural Networks (arxiv.org)

Triply-Scalable Equivariant Gaussian Process Modeling (arxiv.org)

Diagonalized Attention for Individualized Regression: Latent-Row Localization and Prediction (arxiv.org)

Sparse Identification for Automatic Large-Scale Screening: A Constraint-Aware Framework with Ultra Fast Decoding Algorithm (arxiv.org)

Signal-Centric Remote Sensing via Alternative Preprocessing and Acoustic Processing for ML-Driven Applications (arxiv.org)

Beyond Benchmark Scores: Auditing Medical Vision-Language Models for Chest X-Ray Tuberculosis Screening (arxiv.org)

Complete Neural Electronic Initialization Accelerates Materials DFT (arxiv.org)

Bayesian classification of astronomical spectra with class uncertainties (arxiv.org)

Brownian Heads for Deep ReLU Representations: Activation Mass and the Cost of Same-Sample Selection (arxiv.org)

Improving the Predictive Performance of Bootstrap Aggregating by Dirichlet Resampling (arxiv.org)

How Many Posterior Samples? Calibrated Stopping for Adaptive Sensing (arxiv.org)

Riemannian Simultaneous Inference for Tangent Vector Field Regression (arxiv.org)