PLT: Part-Wise Latent Tokens as Adaptable Motion Priors for Physically Simulated Characters
Jinseok Bae, Younghwan Lee, Donggeun Lim, Young Min Kim
2025Year
1Citations
2Top-tier citations
Abstract
part-wise expansion of motion priors, where the physically simulated character incrementally adapts partial motion and produces unique combinations of whole-body motion, significantly diversifying motions.
Ask about this paper
Ask your agent about it.
Lune has read the top-tier papers around this one, so every answer names the papers it rests on.
Cited by top-tier papers2
- GPC: Large-Scale Generative Pretraining for Transferable Motor ControlYi Shi, Yifeng Jiang, Chen Tessler, Xue Bin PengSIGGRAPH 2026
- MaskAdapt: Learning Flexible Motion Adaptation via Mask-Invariant Prior for Physics-Based CharactersSoomin Park, Eunseong Lee, Kwang Bin Lee, Sung-Hee LeeCVPR 2026
Related papers
- PMP: Learning to Physically Interact with Environments using Part-wise Motion PriorsJinseok Bae, Jungdam Won, Donggeun Lim, Cheol-Hui Min et al.SIGGRAPH 2023 · 27 citations
- Discovering diverse athletic jumping strategiesZhiqi Yin, Zeshi Yang, Michiel van de Panne, KangKang YinSIGGRAPH 2021 · 46 citations
- Composite Motion Learning with Task ControlPei Xu, Xiumin Shang, Victor B. Zordan, Ioannis KaramouzasSIGGRAPH 2023 · 27 citations
- UniPhys: Unified Planner and Controller with Diffusion for Flexible Physics-Based Character ControlYan Wu, Korrawe Karunratanakul, Zhengyi Luo, Siyu TangICCV 2025 · 3 citations
- Learning Uniformly Distributed Embedding Clusters of Stylistic Skills for Physically Simulated CharactersNian Liu, Zilong Zhang, Zi Wang, Tengyu Liu et al.ACM MM 2025 · 1 citation
