AI News

Architectural Design, Not Only Model Intelligence, Governs Multi-Agent LLM Performance (arxiv.org)

A Neuropsychologically Grounded Evaluation of LLM Cognitive Abilities (arxiv.org)

FOCAL: Fine-Grained Optimal-Transport-Driven Contrastive Alignment of Language and ECGs with Waveform Enhancement (arxiv.org)

TetrisCNN for interpretable detection of phases of matter from experimental quantum simulator data (arxiv.org)

Stable Movement for Nondual Lipschitz Convex Optimization: Efficiency and Nearly Optimal Oracle Rates (arxiv.org)

MILER: Semantic Mid-Level Representation for Sim-to-Real Reinforcement Learning in Unstructured Autonomous Driving (arxiv.org)

OPTED: On-Policy Fine-Tuning for End-to-End Driving using a Render-Free Teacher (arxiv.org)

Agile-WAM: An Agile Tactile World Action Model for Contact-Rich Robot Control (arxiv.org)

How Does Distribution Shift Shape Pretraining Gains in Neural PDE Surrogates? (arxiv.org)

Embedding Models Measure in Peculiar Ways (arxiv.org)

AntiGrounding: Executable Robot Trajectories as Visual Prompts for VLM-Guided Manipulation (arxiv.org)

MetaRTL: Meta-path Attention Enhanced Relational Table Learning (arxiv.org)

A Dual-Process Perspective on Nudge Susceptibility in LLM-Based GUI Agents (arxiv.org)

Constraint-Safe Graph-Context Scoring for Stable Point-Feature Labels Under Text-Width and Accessibility-Inspired Profiles (arxiv.org)

Reproducibility is not construct validity: LLM measurement of institutionally situated communication (arxiv.org)

Physical knowledge on historical data matters more than enforcing physical constraints on the forecast (arxiv.org)

TRACE: Accountable Agentic Retrieval for Source Discovery in Digital Archives (arxiv.org)

For Your Eyes Only: Evaluating Coordination Between Isolated Language Model Instances (arxiv.org)

CoreSense: Traceable Failure Recall and Conflict-Aware Belief Gating for Auditable Robot Decisions (arxiv.org)

AURORA: A Natural Language-Driven Agentic Framework for Understanding, Reasoning, and Orchestrating Reliable Air-Ground Co-Simulation (arxiv.org)

Detecting Soft Errors in Parallel Software with LLM-tuned Instruction Duplication (arxiv.org)

FacetCRS: Multi-Faceted Preference Learning for Pricking Filter Bubbles in Conversational Recommender System (arxiv.org)

Music Hallucination in Audio-Language Models: A Hierarchical Formulation and Empirical Study (arxiv.org)

MAS-Shield: A Defense Framework for Secure and Efficient LLM MAS (arxiv.org)

FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations (arxiv.org)

CoMa: Contextual Massing Generation with Vision-Language Models (arxiv.org)

Sim-and-Human Co-training for Data-Efficient and Scene-Generalizable Bimanual Manipulation (arxiv.org)

Cross-Sectional Asset Retrieval via Future-Aligned Soft Contrastive Learning (arxiv.org)

When Consistency Becomes Bias: Interviewer Effects in Semi-Structured Clinical Interviews (arxiv.org)

Large language models eroding science understanding: an empirical study of malignment (arxiv.org)

Interactive proofs for verifying (quantum) learning and testing (arxiv.org)

Perspective of Software Engineering Researchers on Machine Learning Practices Regarding Research, Review, and Education (arxiv.org)

A Large-Scale Vision-Language Dataset Derived from Open Scientific Literature to Advance Biomedical Generalist AI (arxiv.org)

Traffic Engineering in Large-scale Networks with Generalizable Graph Neural Networks (arxiv.org)

Enabling automatic transcription of child-centered audio recordings from real-world environments (arxiv.org)

Evaluating Out-of-Distribution Robustness in Graph-Based Android Malware Classification: A New Principled Benchmark (arxiv.org)

Learn2Drive: A neural network-based framework for socially compliant automated vehicle control (arxiv.org)

Comparison of Image Processing Models in Quark Gluon Jet Classification (arxiv.org)

UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation (arxiv.org)

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation (arxiv.org)

Understanding Role Switching in Human-AI Collaboration through Multimodal Behavioral Signals (arxiv.org)

BuildBench: Benchmarking LLM Agents on Compiling Real-World Open-Source Software (arxiv.org)

Waymo in Singapore (waymo.com)

Mantle (www.producthunt.com)

WhaleRead (www.producthunt.com)

Stile.iD (www.producthunt.com)

I built the fastest PHP webserver in the world (qbixserver.com)

Pre-Greek: The lost language hidden within Ancient Greek (linguisticdiscovery.com)

Code Scans (devin.ai)

Polishory (www.producthunt.com)