-
Stereo-Talker: Audio-driven 3D Human Synthesis with Prior-Guided Mixture-of-Experts,
arXiv, 2410.23836
, arxiv, pdf, cication: -1Xiang Deng, Youxin Pang, Xiaochen Zhao, ..., Hongwen Zhang, Yebin Liu
-
MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding,
arXiv, 2410.21747
, arxiv, pdf, cication: -1Yuan Wang, Di Huang, Yaqi Zhang, ..., Shixiang Tang, Dan Xu · (humans)
-
MotionCLR: Motion Generation and Training-free Editing via Understanding Attention Mechanisms,
arXiv, 2410.18977
, arxiv, pdf, cication: -1Ling-Hao Chen, Wenxun Dai, Xuan Ju, ..., Shunlin Lu, Lei Zhang
-
Large Body Language Models,
arXiv, 2410.16533
, arxiv, pdf, cication: -1Saif Punjwani, Larry Heck