5 papers
Oneira: From Open-Ended Generation to Open-World Interaction in Video World Models
Xindi Yang, Baolu Li, Liam Lee +8
Generative video world models can now synthesize open-ended environments that agents can navigate and interact with in simple ways. Yet open-ended generation does not imply full in…
OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence
Jianhui Liu, Haoze Sun, Wenbo Li +11
Spatial understanding is a fundamental cornerstone of human-level intelligence. Nonetheless, current research predominantly focuses on domain-specific data production, leaving a cr…
Learning to Control Physically-simulated 3D Characters via Generating and Mimicking 2D Motions
Jianan Li, Xiao Chen, Tao Huang +1
Video data is more cost-effective than motion capture data for learning 3D character motion controllers, yet synthesizing realistic and diverse behaviors directly from videos remai…
Physics-Grounded Motion Forecasting via Equation Discovery for Trajectory-Guided Image-to-Video Generation
Tao Feng, Xianbing Zhao, Zhenhua Chen +4
Recent advances in diffusion-based and autoregressive video generation models have achieved remarkable visual realism. However, these models typically lack accurate physical alignm…
VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior
Xindi Yang, Baolu Li, Yiming Zhang +8
Video diffusion models (VDMs) have advanced significantly in recent years, enabling the generation of highly realistic videos and drawing the attention of the community in their po…