Submitted by dkliang 103 Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models H-EmbodVis 41 1
Submitted by yawenluo 96 ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling · 8 authors 57 2
Submitted by kpzhang996 13 PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference Shanda AI Research Tokyo 61 1
Submitted by JingweiNi 12 Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills · 9 authors 6
Submitted by xishushu 4 Know3D: Prompting 3D Generation with Knowledge from Vision-Language Models Peking University 5 1
Submitted by Kyudan 2 Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models KAIST AI 1
dkliang 
