Publications (9)
Skeleton2Humanoid: Animating Simulated Characters for Physically-plausible Motion In-betweening
Yunhao Li, Zhenbo Yu, Yucheng Zhu +3
Human motion synthesis is a long-standing problem with various applications in digital twins and the Metaverse. However, modern deep learning based motion synthesis approaches bare…
GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training
Yuelin Hu, Zhenbo Yu, Zhengxue Cheng +2
Hybrid post-training usually combines supervised fine-tuning and reinforcement learning, but fixed mixing schedules cannot adapt when the relative noise of the two signals changes…
Maximizing Rollout Informativeness under a Fixed Budget: A Submodular View of Tree Search for Tool-Use Agentic Reinforcement Learning
Yuelin Hu, Zhenbo Yu, Zhengxue Cheng +2
We formalize Rollout Informativeness under a Fixed Budget (RIFB) as the expected non-vanishing policy-gradient mass that a tool-use rollout set injects into Group Relative Policy O…
GCPO: Diagnosing and Constraining Subspace Geometry in Rollout RL for LLMs
Kai Yang, Jingwei Xu, Wanyu Wang +4
On-policy rollout methods such as GRPO are central to post-training of large language models, yet they frequently suffer from training instabilities, cross-task capability degradat…
Inferring Fluid Dynamics via Inverse Rendering
Jinxian Liu, Ye Chen, Bingbing Ni +2
Humans have a strong intuitive understanding of physical processes such as fluid falling by just a glimpse of such a scene picture, i.e., quickly derived from our immersive visual…
Object Wake-up: 3D Object Rigging from a Single Image
Ji Yang, Xinxin Zuo, Sen Wang +5
Given a single image of a general object such as a chair, could we also restore its articulated 3D shape similar to human modeling, so as to animate its plausible articulations and…