5 papers
WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG
Zhen Li, Zian Meng, Shuwei Shi +5
Dynamical systems theory and reinforcement learning view world evolution as latent-state dynamics driven by actions, with visual observations providing partial information about th…
PyVision-RL: Forging Open Agentic Vision Models via RL
Shitian Zhao, Shaoheng Lin, Ming Li +4
Reinforcement learning for agentic multimodal models often suffers from interaction collapse, where models learn to reduce tool usage and multi-turn reasoning, limiting the benefit…
SVBench: Evaluation of Video Generation Models on Social Reasoning
Wenshuo Peng, Gongxuan Wang, Tianmeng Yang +4
Recent text-to-video generation models have made remarkable progress in visual realism, motion fidelity, and text-video alignment, yet they still struggle to produce socially coher…
Yume: An Interactive World Generation Model
Xiaofeng Mao, Shaoheng Lin, Zhen Li +7
Yume aims to use images, text, or videos to create an interactive, realistic, and dynamic world, which allows exploration and control using peripheral devices or neural signals. In…
T3M: Text Guided 3D Human Motion Synthesis from Speech
Wenshuo Peng, Kaipeng Zhang, Sai Qian Zhang
Speech-driven 3D motion synthesis seeks to create lifelike animations based on human speech, with potential uses in virtual reality, gaming, and the film production. Existing appro…