Text-to-Motion generation aims to synthesize 3D human motion from natural language. While diffusion models naturally capture motion continuity, they often underperform discrete token-based approaches. Emerging applications such as motion editing and multimodal control, however, require fine-grained control, composition...
Guangtao Lyu, Xin-Yi Cheng, Qi Liu et al.· Proceedings of the 34th ACM...· 0 citations
Text-to-Motion generation aims to synthesize 3D human motion from natural language. While diffusion models naturally capture motion continuity, they often underperform discrete token-based approaches. Emerging applications such as motion editing and multimodal control, however, require fine-grained control, composition...
Guangtao Lyu, Xin-Yi Cheng, Qi Liu et al.· Proceedings of the 34th ACM...· 0 citations
This paper proposes TemMEGA (Temporal Masked Generative Modeling), a unified framework capable of handling both online and offline camera movement generation, and demonstrates its superiority in both online and offline camera movement synthesis.
Cheng-Hao Xu, Guangtao Lyu, Jiexi Yan et al.· Neural Information Processin...· 2 citations
Long-horizon robot policies require compact access to recent observations and reusable experience without expanding the vision-language-action (VLA) context. We introduce Remember Smarter (RS), a plug-and-play module with complementary visual-history and hyperbolic experience-memory branches. Its visual branch compress...
This work proposes "raise one and infer three" diffusion policy (ROITDP), a novel approach that introduces two complementary mechanisms, including a reasoning mechanism built upon the Chain-of-Skill Noise Watermark, which enables temporally coherent multi-step reasoning throughout the diffusion process under distributi...
Yi-Hang Zhu, Yuxuan Wang, Tong Li et al.· Proceedings of the Thirty-Fi...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.