Learning from the Self-future: On-policy Self-distillation for dLLMs Paper • 2606.18195 • Published 27 days ago • 76
Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models Paper • 2606.03988 • Published Jun 3 • 126
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published May 28 • 250