An Efficient Heterogeneous Co-Design for Fine-Tuning on a Single GPU Paper • 2603.16428 • Published 26 days ago • 51
HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents Paper • 2604.07430 • Published 4 days ago • 139
INSID3: Training-Free In-Context Segmentation with DINOv3 Paper • 2603.28480 • Published 12 days ago • 5
SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing Paper • 2603.19228 • Published 23 days ago • 68
InCoder-32B: Code Foundation Model for Industrial Scenarios Paper • 2603.16790 • Published 25 days ago • 307
Does Your Reasoning Model Implicitly Know When to Stop Thinking? Paper • 2602.08354 • Published Feb 9 • 263
From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models Paper • 2602.22859 • Published Feb 26 • 151