Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models Paper • 2604.10949 • Published 3 days ago • 36
ClawBench: Can AI Agents Complete Everyday Online Tasks? Paper • 2604.08523 • Published 7 days ago • 253
SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing Paper • 2603.19228 • Published 27 days ago • 68
Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding Paper • 2603.19235 • Published 27 days ago • 95
InCoder-32B: Code Foundation Model for Industrial Scenarios Paper • 2603.16790 • Published 29 days ago • 308
From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models Paper • 2602.22859 • Published Feb 26 • 151
Does Your Reasoning Model Implicitly Know When to Stop Thinking? Paper • 2602.08354 • Published Feb 9 • 263