InfoBodied AI Lab

Yanchao Yang

Yanchao Yang

Assistant Professor
School of Computing and Data Science
Electrical and Computer Engineering
Institute of Data Science
The University of Hong Kong
Email: yanchaoy at hku dot hk
Office: Room 714, Chow Yei Ching Building, HKU

About Me

    The InfoBodied AI Lab at HKU is building the next generation of embodied AI systems — robots and autonomous agents that can perceive complex 3D environments in real time, discover actionable concepts from unlabelled data, and learn generalizable manipulation policies that operate reliably in the open world.

    I am an Assistant Professor at the School of Computing and Data Science (CDS), HKU, jointly appointed by the Department of Electrical and Computer Engineering (ECE) and the HKU Musketeers Foundation Institute of Data Science (IDS). I was a Postdoctoral Research Fellow at Stanford University with Leonidas J. Guibas and received my Ph.D. from the University of California, Los Angeles (UCLA) with Stefano Soatto. Earlier, I obtained my Master's and Bachelor's degrees from KAUST and USTC, respectively.

    Our research tackles core challenges in robot manipulation, 3D scene understanding and real-time reconstruction, visuomotor control, and the grounding of large vision-language foundation models in the physical world — with a particular focus on reducing dependence on costly human annotation. A unifying thread across this work is the use of efficient mutual information estimators as a principled tool for representation learning, concept discovery, and policy optimization, forming the basis of our research program in InfoBodied AI. Our work has appeared at CVPR, NeurIPS, ICLR, ECCV, ICML, CoRL, ICRA, and SIGGRAPH, among others.

    Ph.D. students, postdocs and interns!

    We are looking for highly motivated researchers who want to work on open problems at the frontier of embodied intelligence. Backgrounds in computer vision, robotics, machine learning, or related areas are all welcome. Please reach out via email with a CV and a brief description of your research interests.

    *Students can choose either CDS, ECE, or IDS when applying, but make sure to notify me after the submission.

    *Strong Ph.D. candidates are welcome to apply for HKPFS and HKUPS (all year around).

    *We are now considering applications for 2026/2027 enrollment; the main round and clearing rounds application deadlines can be found at this link.

    *We are also accepting interns via the HKU Summer Research Programme (SRP) and the HKU CDS Research Internship Programme.

News

  • [03/2026] Serving as an Area Chair for Neural Information Processing Systems (NeurIPS 2026).
  • [12/2025] Serving as an Area Chair for Robotics: Science and Systems (RSS 2026).
  • [12/2025] Serving as an Area Chair for the European Conference on Computer Vision (ECCV 2026).
  • [10/2025] We are hosting the HKU AI Forum 2025!
  • [08/2025] Serving as an Area Chair for the Conference on Computer Vision and Pattern Recognition (CVPR 2026).
  • [08/2025] Serving as an Area Chair for the International Conference on Learning Representations (ICLR 2026).
  • [08/2025] Serving as an Area Chair for the AAAI Conference on Artificial Intelligence (AAAI 2026).
  • [07/2025] I am teaching Embodied AI 101 at HKU this summer.
  • [04/2025] Our work SLAM3R has won the China3DV Top1 Paper Award. Congrats to the team!
  • [01/2025] I am glad to receive the CPAL Rising Stars Award of year 2025!

Publications

See Google Scholar for a full list of papers. *: equal contributions, †: corresponding author

himacon

HiMaCon: Discovering Hierarchical Manipulation Concepts from Unlabeled Multi-Modal Data

Ruizhe Liu, Pei Zhou, Qian Luo, Li Sun, Jun Cen, Yibing Song, Yanchao Yang

NeurIPS 2025

arXiv/code/project page

gazevlm

Gaze-VLM: Bridging Gaze and VLMs via Attention Regularization for Egocentric Understanding

Anupam Pani, Yanchao Yang

NeurIPS 2025

arXiv/code/project page

hypergoalnet

Hyper-GoalNet: Goal-Conditioned Manipulation Policy Learning with HyperNetworks

Pei Zhou, Wanting Yao, Qian Luo, Xunzhe Zhou, Yanchao Yang

NeurIPS 2025

arXiv/code/project page

hypertasr

HyperTASR: Hypernetwork-Driven Task-Aware Scene Representations for Robust Manipulation

Li Sun*, Jiefeng Wu*, Feng Chen, Ruizhe Liu, Yanchao Yang

CoRL 2025

arXiv/code/project page

humocon

HuMoCon: Concept Discovery for Human Motion Understanding

Qihang Fang, Chengcheng Tang, Bugra Tekin, Shugao Ma, Yanchao Yang

CVPR 2025

arXiv/code/project page

reloc3r

Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization

Siyan Dong*, Shuzhe Wang*, Shaohui Liu, Lulu Cai, Qingnan Fan, Juho Kannala, Yanchao Yang

CVPR 2025

arXiv/code/project page

slam3r

SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos

Yuzheng Liu*, Siyan Dong*, Shuzhe Wang, Yingda Yin, Yanchao Yang, Qingnan Fan, Baoquan Chen

CVPR 2025, Spotlight

arXiv/code/project page

hypogen

HyPoGen: Optimization-Biased Hypernetworks for Generalizable Policy Generation

Hanxiang Ren*, Li Sun*, Xulong Wang, Pei Zhou, Zewen Wu, Siyan Dong, Difan Zou, Youyi Zheng, Yanchao Yang

ICLR 2025

arXiv/code/project page

autocgp

AutoCGP: Closed-Loop Concept-Guided Policies from Unlabeled Demonstrations

Pei Zhou*, Ruizhe Liu*, Qian Luo*, Fan Wang, Yibing Song, Yanchao Yang

ICLR 2025, Spotlight

arXiv/code/project page

infogs

InfoGS: Efficient Structure-Aware 3D Gaussians via Lightweight Information Shaping

Yunchao Zhang, Guandao Yang, Leonidas Guibas, Yanchao Yang

ICLR 2025

arXiv/code/project page

Members

Awards & Professional Service

  • Awards:
    • CPAL Rising Star Award, 2025
    • China3DV Top1 Paper Award, 2025
    • RGC Early Career Award, 2024
    • Alibaba Innovative Research Award, 2024
    • Microsoft Accelerate Foundation Models Research Award, 2023
    • Meta Research Award, 2023
    • Outstanding Reviewer Award, CVPR, ICLR, NeurIPS
    • AWS Nominated Paper Award, 2019

  • Area Chair:
    • Neural Information Processing Systems (NeurIPS), 2026
    • Robotics: Science and Systems (RSS), 2026
    • International Conference on Learning Representations (ICLR), 2026
    • Conference on Computer Vision and Pattern Recognition (CVPR), 2024, 2025, 2026
    • European Conference on Computer Vision (ECCV), 2024, 2026
    • AAAI Conference on Artificial Intelligence (AAAI), 2026

  • Program Committee / Reviewer:
    • Conferences: CVPR, ICCV, ECCV, ICML, ICLR, IJCAI, AAAI, ICRA, NeurIPS, CoRL
    • Journals: TPAMI, TIP, IJCV, RAL, T-RO