Submitted by dkliang 126 Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models H-EmbodVis 41 1
Submitted by yawenluo 102 ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling · 8 authors 57 2
Submitted by kpzhang996 26 PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference Shanda AI Research Tokyo 61 1
Submitted by JingweiNi 21 Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills · 9 authors 6
Submitted by omersahintas 10 LongTail Driving Scenarios with Reasoning Traces: The KITScenes LongTail Dataset Karlsruhe Institute of Technology 2
Submitted by zjj1233 8 RealChart2Code: Advancing Chart-to-Code Generation with Real Data and Multi-Task Evaluation Qwen 1
Submitted by xishushu 7 Know3D: Prompting 3D Generation with Knowledge from Vision-Language Models Peking University 5 1
Submitted by Kyudan 5 Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models KAIST AI 1 1
Submitted by che111 1 MedOpenClaw: Auditable Medical Imaging Agents Reasoning over Uncurated Full Studies · 11 authors 1
dkliang 
