Yuke Zhu

University of Texas at Austin, NVIDIA Research

NVIDIA Research

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Robotics & Embodied AI (3)Multimodal Models (2)World Models & Planning (2)Computer Vision (1)

Frequent co-authors

Ruijie Zheng (2)Dantong Niu (2)Dantong Niu (2)Yuqi Xie (2)

Papers (3)

Feb 18, 2026

NVIDIA3w ago·also BAIR, Google Research, Stanford HAI, UT Austin

EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data

Forget synthetic data—scaling up human egocentric video by 20x unlocks surprisingly effective dexterous robot manipulation, even transferring to robots with different hand configurations.

Ruijie Zheng, Dantong Niu, Dantong Niu +14

Computer Vision Data Curation & Synthetic Data Robotics & Embodied AI

Feb 17, 2026

NVIDIA3w ago·also BAIR, Microsoft Research, KAIST, UT Austin +1

World Action Models are Zero-shot Policies

Forget painstakingly engineering robot behaviors: DreamZero learns directly from video of other robots or even humans, adapting to new tasks and bodies with just minutes of data.

Seonghyeon Ye, Seonghyeon Ye, Kaiyuan Zheng +56

Multimodal Models Robotics & Embodied AI World Models & Planning

Oct 28, 2025

NVIDIAOct 28, 2025·also Georgia Tech, KAIST, NUDT, Stevens +2

World Simulation with Video Foundation Models for Physical AI

Forget synthetic data that looks like it came from a PS2 game: NVIDIA's new Cosmos-Predict2.5 generates high-fidelity videos for training embodied AI, opening the door to more realistic and reliable simulations.

Nvidia Arslan Ali, Junjie Bai, Maciej Bala +8536