MAE I Trust Myself? Self-Evaluating VLA Action Generation with Markov Attention Entropy
Research
Research News
New papers, breakthroughs and academic AI research
Molecular D\'ej\`a Vu: Digit-Level Retrieval of Molecular Properties in Frontier Language Models
Research
How to Reduce Localization Ambiguity? Geometry-Semantic Constrained BEV Representation Learning for Satellite-Ground Localization
Research
Perceptual Color Difference Modeling Using Machine Learning and Human Similarity Judgments
Research
GeoGAT: Bidirectional Temporal Sampling Meets Hierarchical Graph Attention for Global Video Geo-localization
Research
Asking the World: Generalist Physical Reasoning through Agentic World Modeling and Probing
Research
Uncertainty-Aware Consistency Distillation for Few-Step Video Generation
Research
When Can Text Replace Vision? Structural Bottlenecks in Diagram Reasoning
Research
MindWorldBench: Evaluating Mental-State-to-Behavior Reasoning in Image-to-Video Generation
Research
TripleFlow: Training-Free Video Object Removal by Bridging Residual Editing and Native Generation
Research
Feature-Aware Token Attack for Compression-Triggered Stealthy Failures in Large Vision-Language Models
Research
Act First, Reason Later: Accelerating On-Policy Distillation for Multi-Turn Agents via Reference-Conditioned Inverse Dynamics
Research