VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation Paper • 2607.28590 • Published 8 days ago • 45
SWE-Pruner Pro: The Coder LLM Already Knows What to Prune Paper • 2607.18213 • Published 18 days ago • 79
MMSkills: Towards Multimodal Skills for General Visual Agents Paper • 2605.13527 • Published May 14 • 123
SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment Paper • 2507.20984 • Published Jul 28, 2025 • 59
SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment Paper • 2507.20984 • Published Jul 28, 2025 • 59