Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone Paper • 2512.22615 • Published 26 days ago • 45
Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models Paper • 2512.20557 • Published 30 days ago • 49
TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times Paper • 2512.16093 • Published Dec 18, 2025 • 93
