5 papers
Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
Shuailei Ma, Jiaqi Liao, Xinyang Wang +24
Despite the recent promise in robot control, video generative models suffer from a domain mismatch due to their primary focus on content creation. For example, their design inheren…
Tele-Catch: Adaptive Teleoperation for Dexterous Dynamic 3D Object Catching
Weiguang Zhao, Junting Dong, Rui Zhang +3
Teleoperation is a key paradigm for transferring human dexterity to robots, yet most prior work targets objects that are initially static, such as grasping or manipulation. Dynamic…
TeleOpBench: A Simulator-Centric Benchmark for Dual-Arm Dexterous Teleoperation
Hangyu Li, Qin Zhao, Haoran Xu +10
Teleoperation is a cornerstone of embodied-robot learning, and bimanual dexterous teleoperation in particular provides rich demonstrations that are difficult to obtain with fully a…
SIGMAN:Scaling 3D Human Gaussian Generation with Millions of Assets
Yuhang Yang, Fengqi Liu, Yixing Lu +8
3D human digitization has long been a highly pursued yet challenging task. Existing methods aim to generate high-quality 3D digital humans from single or multiple views, but remain…
GAS: Generative Avatar Synthesis from a Single Image
Yixing Lu, Junting Dong, Youngjoong Kwon +3
We present a unified and generalizable framework for synthesizing view-consistent and temporally coherent avatars from a single image, addressing the challenging task of single-ima…