INSID3: Training-Free In-Context Segmentation with DINOv3 Paper • 2603.28480 • Published 3 days ago • 3
SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing Paper • 2603.19228 • Published 14 days ago • 67
InCoder-32B: Code Foundation Model for Industrial Scenarios Paper • 2603.16790 • Published 16 days ago • 306
Does Your Reasoning Model Implicitly Know When to Stop Thinking? Paper • 2602.08354 • Published Feb 9 • 262
From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models Paper • 2602.22859 • Published Feb 26 • 151