Yao Feng

I'm a Postdoc at Stanford, working with Karen Liu, Jennifer Hicks, and Scott L. Delp. I received my PhD from ETH Zürich and Max Planck Insistitute Intelligence Systems under the supervision of Michael J. Black and Marc Pollefeys. I also worked as a research scientist at Meshcapade for one year. My research focuses on building scalable foundation models that perceive, understand, and interact with people in the physical world, with applications across computer vision, computer graphics, machine learning, and robotics.

Email / Scholar / Twitter / Github

I will join Tsinghua University as an Assistant Professor in the College of AI (led by Prof. Andrew Chi-Chih Yao).

🎓 Recruiting: Looking for postdocs, PhD students, undergraduates, interns, and visiting scholars to join my lab, and am also open to research collaborations. Welcome to reach out!

📝 Prospective students: please fill out this form (no need to email me — I check it frequently).

📧 Collaborators: please email me directly.

News

Mar 2026 Meshcapade, where I previously worked as a Research Scientist, has been acquired by Epic Games!

Nov 2025 Give a talk at the University of Michigan.

Sep 2025 Give a talk at Stanford SVL.

June 2025 Give a talk at CVPR 2025 Workshop.

June 2025 Co-organize CVPR 2025 Workshops: 3DHuman (A 2025 Perspective on 3D Human Perception, Reconstruction, and Synthesis) and Scene Understanding (5th 3D Scene Understanding for Vision, Graphics, and Robotics).

May 2025 Received Eurographics PhD Award Honorable Mention.

Oct 2024 Passed my PhD thesis defense: Learning Digital Humans from Vision and Language.

Oct 2024 Selected as MIT Rising Stars in EECS.

Sep 2024 Organize ECCV 2024 Workshop, Foundation Models for 3D Humans.

Jul 2024 Selected as WiGRAPH Rising Stars in Computer Graphics.

Research

My ultimate goal is to build digital humans that reflect who we are: how we look, how we move, and how we think, whether in virtual worlds or embodied in robots. Toward this vision of human-centric physical AI, I build scalable models that learn directly from everyday vision and language, enabling lifelike bodies and intelligent behaviors that perceive, understand, and act with people in the physical world. Ultimately, I hope to shape a future where AI interacts with the world, and with people, as naturally as we do.

▸ Human-Centric Perception. Sensing humans and their physical surroundings — high-fidelity reconstruction of human and environment from images, videos, and multimodal signals. This perceptual foundation lets embodied agents see, model, and ground themselves in a world shared with people. DECA, PIXIE, SCARF, HaPTIC.

▸ Human-Centric Understanding. Reasoning about human behavior, intent, and interaction by building on top of large language models — bridging language, vision, and action so agents can dialogue with, learn from, and respond to people. ChatPose, ChatHuman, ChatGarment.

▸ Human-Centric Embodiment. Generating physically grounded interaction behavior, human-robot collaborative policies, to enable a single agent to act across digital humans, virtual characters, and physical robots, and operate in environments shared with people. PRIMAL, GentleHumanoid, YSuit.

Publications

(show selected / show all by date)

	GentleHumanoid: Learning Upper-body Compliance for Contact-rich Human and Object Interaction Qingzhou Lu, Yao Feng, Baiyu Shi, Michael Piseno, Zhenan Bao, C. Karen Liu arXiv, 2025 project page / arXiv / code
	Textile suit for anywhere full-body motion capture Huanbo Sun, Yao Feng, Pei-Chun Kao, Michael J. Black, Rebecca Kramer-Bottiglio Science Advances, 2026
	PRIMAL: Physically Reactive and Interactive Motor Model for Avatar Learning Yan Zhang, Yao Feng, Alpár Cseke, Nitin Saini, Nathan Bajandas, Nicolas Heron, Michael J. Black ICCV, 2025 project page / arXiv / code
	HaPTIC: Predicting 4D Hand Trajectory from Monocular Videos Yufei Ye, Yao Feng, Omid Taheri, Haiwen Feng, Shubham Tulsiani, Michael J. Black arXiv, 2025 project page / arXiv / code
	ChatHuman: Chatting about 3D Humans with Tools Jing Lin, Yao Feng, Weiyang Liu, Michael J. Black CVPR, 2025 project page / arXiv
	ChatGarment: Garment Estimation, Generation and Editing via Large Language Models Siyuan Bian, Chenghao Xu, Yuliang Xiu, Artur Grigorev, Zhen Liu, Cewu Lu, Michael J. Black, Yao Feng CVPR, 2025 project page / arXiv / code
	DiffLocks: Generating 3D Hair from a Single Image using Diffusion Models Radu Alexandru Rosu, Keyu Wu, Yao Feng, Youyi Zheng Michael J. Black CVPR, 2025 project page / arXiv / code
	ChatPose: Chatting about 3D Human Pose Yao Feng, Jing Lin, Sai Kumar Dwivedi, Yu Sun, Priyanka Patel, Michael J. Black CVPR, 2024 project page / arXiv / code
	TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation Sai Kumar Dwivedi, Yu Sun, Priyanka Patel, Yao Feng, Michael J. Black CVPR, 2024 project page / paper / code
	MonoHair: High-Fidelity Hair Modeling from a Monocular Video Keyu Wu, Lingchen Yang, Zhiyi Kuang, Yao Feng, Xutao Han, Yuefan Shen, Hongbo Fu, Kun Zhou, Youyi Zheng CVPR, 2024 project page / arXiv / code
	Ghost on the Shell: An Expressive Representation of General 3D Shapes Zhen Liu, Yao Feng, Yuliang Xiu, Weiyang Liu, Liam Paull, Michael J. Black, Bernhard Schölkopf ICLR, 2024 project page / arXiv / code
	BOFT: Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization Weiyang Liu, Zeju Qiu, Yao Feng, Yuliang Xiu, Yuxuan Xue, Longhui Yu, Haiwen Feng, Zhen Liu, Juyeon Heo, Songyou Peng, Yandong Wen, Michael J. Black, Adrian Weller, Bernhard Schölkopf ICLR, 2024 project page / arXiv
	TECA: Text-Guided Generation and Editing of Compositional 3D Avatars Hao Zhang, Yao Feng, Peter Kulits, Yandong Wen, Justus Thies, Michael J. Black 3DV, 2024 project page / arXiv / code
	DELTA: Learning Disentangled Avatars with Hybrid 3D Representations Yao Feng, Weiyang Liu, Timo Bolkart, Jinlong Yang, Marc Pollefeys, Michael J. Black project page / arXiv / code
	MeshDiffusion: Score-based Generative 3D Mesh Modeling Zhen Liu, Yao Feng, Michael J. Black, Derek Nowrouzezahrai, Liam Paull, Weiyang Liu ICLR, 2023 project page / arXiv / code
	SCARF: Capturing and Animation of Body and Clothing from Monocular Video Yao Feng, Jinlong Yang, Marc Pollefeys Michael J. Black Timo Bolkart Siggraph Asia Conference, 2022 project page / arXiv / code
	PIXIE: Collaborative Regression of Expressive Bodies using Moderation Yao Feng, Vasileios Choutas, Timo Bolkart, Dimitrios Tzionas, Michael J. Black 3DV, 2021 project page / paper / code
	DECA: Learning an Animatable Detailed 3D Face Model from In-The-Wild Images Yao Feng, Haiwen Feng, Michael J. Black, Timo Bolkart SIGGRAPH, 2021 project page / arXiv / code
	PRNet: Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network Yao Feng, Fan Wu, Xiaohu Shao, Yanfeng Wang, Xi Zhou ECCV, 2018 project page / paper / code

This guy makes a nice webpage.