Speaker: Yi Zhou, Senior AI Scientist at Roblox
Time: 14:00, Dec. 29th
Location: 1A-200, SIST
Host: Prof. Lan Xu
Abstract:
This talk explores how AI can learn from humans and co-create with humans to capture the richness of human appearance, motion, interactions, and personality. I will present three lines of work: (1) building large-scale 4D datasets such as HUMOTO, which capture human–human and human–object interactions with industry-standard fidelity; (2) developing novel 3D representations and differentiable simulations, including DMesh and Digital Salon, for efficient modeling of complex geometry and dynamics; and (3) designing generative tools that enable intuitive, user-guided creation of digital humans and their interactions and behaviors in scenes. Together, these efforts advance a vision of human-centric generative AI: systems that learn about humans, collaborate with humans, and empower creativity across 2D, 3D, and 4D domains.
Bio:
Yi Zhou is a Senior AI Scientist at Roblox and previously a Research Scientist at Adobe Research, specializing in human-centric AI, computer graphics, and machine learning. Her work focuses on modeling and generating realistic autonomous 3D and 4D avatars, with an emphasis on human–human, human–object, and human–scene interactions. Zhou has published over 30 papers at leading venues including SIGGRAPH, CVPR, ICCV, ECCV, NeurIPS, and ICLR, and is the inventor of nine issued US, Chinese, and global patents, with 18 more pending. Her presentation of Project Posable at Adobe MAX 2023 received over two million views on Twitter, highlighting the broad impact of her research. She has served on the Technical Papers Committees for SIGGRAPH (2023, 2026), SIGGRAPH Asia (2024, 2025), and the Eurographics 2025 Short Papers Committee. Zhou’s broader vision is to advance human-centric AI systems that learn from humans and collaborate with humans to enable creativity, design, and embodied intelligence.
沪公网安备 31011502006855号
