Yukang Cao 操雨康

I am a Postdoctoral Research Fellow at MMLab Nanyang Technological University in Singapore, working with Prof. Ziwei Liu. I received my Ph.D. in Computer Science from The University of Hong Kong, advised by Prof. Kwan-Yee K. Wong, and my B.Eng. from Zhejiang University in 2020 (ranked 3/66).

My research explores computer vision and machine learning, with a focus on embodied AI, modeling of human-related interactions, spatial intelligence, agentic modeling, and generative modeling.

Embodied AI Human-related Interactions Spatial Intelligence Agentic Modeling Generative Models

RESEARCH MAP

Research Directions

My work aims to connects embodied systems, human-related interactions, 3D understanding, and generative models across four complementary directions.

Embodied AI & Human-related Interactions

Connecting embodied perception and physical reasoning with controllable models of human–object and collective interactions.

Embodied AI

ACE-Data-0 HSImul3R Apple-PI

Human-related interactions

AvatarGO CrowdMoGen

3D Generative Modeling

Generating controllable 3D/4D humans, objects, and dynamic content from text, images, motion, and interaction cues.

DreamAvatar GS-VTON HeadSculpt

Wukong Splat4D AniFeats AudCast

3D Spatial Intelligence

Reconstructing geometry, semantics, humans, and interactions to create structured, simulation-ready representations of the world.

Survey: 4D Spatial Intelligence SeSDF JIFF IGGT

2D & Language Generative Modeling

Exploring diffusion language models, agentic content creation, image morphing, subject generation, and human video synthesis.

AURORA-LM FreeMorph VibeGame ArtiFade

LATEST

News

Recent papers, releases, and milestones.

2026 · 08We release VibeGame, an agentic framework for game development.
2026 · 08We release AURORA-LM, a diffusion language model for continuous-latent text modeling.
2026 · 07We release ACE-Data-0, a human-centric ambient capture engine for embodied AI.
2026 · 07We release Apple-PI, a benchmark for evaluating physical understanding in video models.
2026 · 06HSImul3R, our work on real-to-sim-to-real modeling, is accepted by ECCV 2026.
2026 · 06AniFeats, our work on human animation, is accepted by TVCG 2026.
2026 · 03GS-VTON, our work on 3D virtual try-on, is accepted by IJCV 2026.
2026 · 01IGGT, our work on instance-grounded 3D semantic reconstruction, is accepted by ICLR 2026. Congratulations to Hao Li!
2025 · 09CrowdMoGen, our work on collective motion generation, is accepted by IJCV 2025.
2025 · 09Wukong, our work on 3D morphing, is accepted by NeurIPS 2025. Congratulations to Minghao!
2025 · 07We release a survey on reconstructing 4D spatial intelligence.
2025 · 06FreeMorph, our training-free approach to 2D image morphing, is accepted by ICCV 2025.
2025 · 05We release CrowdMoGen for zero-shot collective 3D human motion generation.
2025 · 03One paper is accepted by SIGGRAPH 2025. Congratulations to Minghao!
2025 · 02Two papers, ArtiFade and AudCast, are accepted by CVPR 2025.
2025 · 01AvatarGO is accepted by ICLR 2025.
2024 · 10We release AvatarGO for zero-shot 4D human-object interaction generation and animation.
2024 · 10We release GS-VTON for controllable 3D virtual try-on.
2024 · 09We release ArtiFade for generating high-quality subjects from blemished images.
2024 · 08I begin a new chapter at NTU, working with Prof. Ziwei Liu.
2024 · 06We post a survey on 3D human avatar modeling.
2024 · 04I successfully defend my Ph.D.
2024 · 02DreamAvatar is accepted by CVPR 2024.
2023 · 09HeadSculpt is accepted by NeurIPS 2023.
2023 · 08We release Guide3D for transferring multi-view generated images to 3D avatars.
2023 · 06We release HeadSculpt for editable 3D head generation from text.
2023 · 04We release DreamAvatar for controllable 3D avatar generation from text.
2023 · 03MA-NeRF is accepted by ICME 2023.
2023 · 02SeSDF is accepted by CVPR 2023.
2022 · 03JIFF is accepted by CVPR 2022.

SELECTED WORK

Publications

^* Equal contribution · ^# Corresponding author

Under submissionAgentic game modeling

VibeGame: Prompt-to-Game Development with AI-Native Engine and Self-Evolving Adversarial Agent Team

Wenbo Hu^*, Ken Li^*, Jiazhe Wei^*, Yukang Cao, Weiyi Hong, Jiayi Dai, Chenjun Bai, Jiajun Liang, Yucheng Liao, Ruichuan An, Zeyu Lou, Haofan Wang, Wende Tan, Liucheng Guo, Yueming Lyu, Ziwei Liu, Chenyang Si^#

Under submission, 2026

Project Code BibTeX

Technical ReportDiffusion language modeling

AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling

Jiajun Liang^*, Yucheng Liao^*, Yukang Cao^*, Jiazhe Wei, Ken Li, Wende Tan, Jiankun Zhang, ZY Cui, Jingkang Yang, Liucheng Guo, Shiqi Yang, B. Yang, Caifeng Shan, Ziwei Liu, Chenyang Si^#

Technical Report, 2026

Project Paper Code BibTeX

Technical ReportAmbient Capture Engine for Embodied AI

ACE-Data-0: Human-Centric Ambient Capture as Embodied Data Engine

Yukang Cao^*, Haozhe Xie^*, Beichen Wen^*, Runmao Yao, Yinghao Liu, Yue Huang, Zhichao Liao, Yunxiang Wang, Haiheng Liu, Xingshun Tian, Dawei Su, Long Zhuo, Dacheng Tao, Xiaogang Wang, Liang Pan^#, Ziwei Liu^#

Technical Report, 2026

Project Paper HuggingFace BibTeX

Under submissionPhysics benchmark for video models

Apple-PI: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence

Runmao Yao^*, Kairui Hu^*, Yukang Cao, Ruisi Wang, Shulin Tian, Ziang Cao, Weichen Fan, Ziqi Huang, Yuhao Dong, Hao Li, Zhaoxi Chen, Zhongang Cai, Lei Yang, Ziwei Liu^#

Under submission, 2026

Project Paper Code HF Dataset BibTeX

ECCV 2026Simulation-ready HSI reconstruction

HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human–Scene Interactions

Yukang Cao, Haozhe Xie, Fangzhou Hong, Long Zhuo, Zhaoxi Chen, Liang Pan, Ziwei Liu^#

European Conference on Computer Vision, 2026

Project Paper Code BibTeX

TVCG 2026Video-based human animation

AniFeats: Animate 3D Feature Meshes for Character Video Generation

Beijia Lu, Zekai Gu, Zhiyang Dou, Haotian Yuan, Yuan Liu, Chenyang Si, Yukang Cao, Yuming Jiang, Wenping Wang, Ziwei Liu^#

IEEE Transactions on Visualization and Computer Graphics, 2026

Paper BibTeX

IJCV 20263D virtual try-on

GS-VTON: Controllable 3D Virtual Try-on with Gaussian Splatting

Yukang Cao^*, Masoud Hadi^*, Liang Pan^#, Ziwei Liu^#

International Journal of Computer Vision, 2026

Project Paper Code BibTeX

ICLR 20263D reconstruction

IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction

Hao Li^*, Zhengyu Zou^*, Fangfu Liu^*, Xuanyang Zhang, Fangzhou Hong, Yukang Cao, Yushi Lan, Manyuan Zhang, Gang Yu, Dingwen Zhang^#, Ziwei Liu

International Conference on Learning Representations, 2026

Project Paper Code BibTeX

NeurIPS 20253D morphing

Wukong’s 72 Transformations: High-fidelity 3D Morphing via Flow Models

Minghao Yin, Yukang Cao, Kai Han^#

Neural Information Processing Systems, 2025

Project Paper BibTeX

Preprint 2025Survey

Reconstructing 4D Spatial Intelligence: A Survey

Yukang Cao, Jiahao Lu, Zhisheng Huang, Zhuowen Shen, Chengfeng Zhao, Fangzhou Hong, Zhaoxi Chen, Xin Li, Wenping Wang, Yuan Liu^#, Ziwei Liu^#

Preprint, 2025

Project Paper BibTeX

ICCV 2025Image morphing

FreeMorph: Tuning-Free Generalized Image Morphing with Diffusion Model

Yukang Cao^*, Chenyang Si^*, Jinghao Wang, Ziwei Liu^#

International Conference on Computer Vision, 2025

Project Paper Code BibTeX

IJCV 2025Motion generation

CrowdMoGen: Zero-Shot Text-Driven Collective Motion Generation

Yukang Cao^*, Xinying Guo^*, Mingyuan Zhang, Haozhe Xie, Chenyang Gu, Ziwei Liu^#

International Journal of Computer Vision, 2025

Project Paper Code BibTeX

SIGGRAPH 20254D generation

Splat4D: Diffusion-Enhanced 4D Gaussian Splatting for Temporally and Spatially Consistent Content Creation

Minghao Yin, Yukang Cao, Songyou Peng, Kai Han^#

ACM SIGGRAPH, 2025

BibTeX

CVPR 2025Human video

AudCast: Audio-Driven Human Video Generation by Cascaded Diffusion Transformers

Jiazhi Guan, Kaisiyuan Wang, Zhiliang Xu, Quanwei Yang, Yasheng Sun, Shengyi He, Borong Liang, Yukang Cao, Yingying Li, Haocheng Feng, Errui Ding, Jingdong Wang, Youjian Zhao^#, Hang Zhou^#, Ziwei Liu^#

IEEE Conference on Computer Vision and Pattern Recognition, 2025

Project Paper Code BibTeX

ICLR 2025Human-object interaction

AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animation

Yukang Cao, Liang Pan^#, Kai Han, Kwan-Yee K. Wong, Ziwei Liu^#

International Conference on Learning Representations, 2025

Project Paper Code BibTeX

CVPR 2025Subject generation

ArtiFade: Learning to Generate High-quality Subject from Blemished Images

Shuya Yang^*, Shaozhe Hao^*, Yukang Cao^#, Kwan-Yee K. Wong^#

IEEE Conference on Computer Vision and Pattern Recognition, 2025

Paper BibTeX

Preprint 2024Survey

A Survey on 3D Human Avatar Modeling — From Reconstruction to Generation

Ruihe Wang^*, Yukang Cao^*#, Kai Han, Kwan-Yee K. Wong

Preprint, 2024

Paper BibTeX

CVPR 2024Avatar generation

DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models

Yukang Cao^*, Yan-Pei Cao^*, Kai Han^#, Ying Shan, Kwan-Yee K. Wong

IEEE Conference on Computer Vision and Pattern Recognition, 2024

Project Paper Code BibTeX

arXiv 2023Avatar generation

Guide3D: Create 3D Avatars from Text and Image Guidance

Yukang Cao, Yan-Pei Cao, Kai Han^#, Ying Shan, Kwan-Yee K. Wong

arXiv, 2023

Paper Code BibTeX

NeurIPS 2023Head avatars

HeadSculpt: Crafting 3D Head Avatars with Text

Xiao Han^*, Yukang Cao^*, Kai Han, Xiatian Zhu, Jiankang Deng, Yi-Zhe Song, Tao Xiang^#, Kwan-Yee K. Wong^#

Neural Information Processing Systems, 2023

Project Paper Code BibTeX

CVPR 2023Human reconstruction

SeSDF: Self-evolved Signed Distance Field for Implicit 3D Clothed Human Reconstruction

Yukang Cao, Kai Han, Kwan-Yee K. Wong

IEEE Conference on Computer Vision and Pattern Recognition, 2023

Project Paper BibTeX

CVPR 2022 · OralHuman reconstruction

JIFF: Jointly-aligned Implicit Face Function for High Quality Single View Clothed Human Reconstruction

Yukang Cao, Guanying Chen, Kai Han, Wenqi Yang, Kwan-Yee K. Wong

IEEE Conference on Computer Vision and Pattern Recognition, 2022

Project Paper Code BibTeX

PROFESSIONAL BACKGROUND

Employment

Research collaborations across academia and industry.

Primary appointments

Aug 2024–Present
Research Fellow · MMLab@NTU
Worked with Prof. Ziwei Liu.
Sep 2020–Jun 2024
Postgraduate Researcher · The University of Hong Kong
Worked with Prof. Kwan-Yee K. Wong and Prof. Kai Han.

Research internships

Mar–Jun 2024
Research Intern · Shanghai AI Laboratory
Worked with Dr. Liang Pan and Prof. Ziwei Liu.
Dec 2022–Jun 2023
Research Intern · Tencent PCG, ARC Lab
Worked with Dr. Yan-Pei Cao.

ACADEMIC BACKGROUND

Education

Doctoral and undergraduate education in computer science and engineering.

Degrees

2020–2024
Ph.D. in Computer Science · The University of Hong Kong
Advised by Prof. Kwan-Yee K. Wong.
2016–2020
Bachelor of Engineering · Zhejiang University
Graduated with a class rank of 3/66.

Early research experience

Jul–Nov 2019
Research Student · The University of Texas at Austin
Worked with Dr. Chandrajit Bajaj.
Sep–Dec 2019
Research Student · Peking University
Worked with Dr. Dehua Xiong.
Jul–Oct 2018
Research Student · Tsinghua University
Worked with Dr. Zuoqiang Shi.

MENTORSHIP

Teaching

2022–2023 COMP 3270 Artificial Intelligence, Teaching Assistant · HKU
2021–2022 COMP 2396 Object-Oriented Programming and Java, Teaching Assistant · HKU

INVITED

Talks

Aug 2026 “ACE-Data-0: Human-Centric Ambient Capture as Embodied Data Engine” · Qingke Community
Mar 2026 “HSImul3R: Physics-in-the-loop Reconstruction of Simulation-ready Human-Scene Interactions” · WiseModel
Apr 2025 “Modeling Virtual Worlds: Humans, Objects, Scenes & Interactions via Generative AI” · Huawei InnovWave
Oct 2024 “GS-VTON: Controllable 3D Virtual Try-on with Gaussian Splatting” · AnySyn3D
Dec 2023 “3D Human Modelling from Image and Text Guidance” · NTU MMLab
Jul 2023 “Avatar-X: Text Guided Controllable and Editable 3D Human Avatar Generation” · GAP Lab, CUHK-Shenzhen

RECOGNITION

Awards

HKU Presidential Scholarship2020–2024 · Highest distinction in Hong Kong
M. Braun Postgraduate Prize2023
Arthur and Louise May Memorial Fund Scholarship2022, 2023, 2024
HK China Gas Co. Ltd. Postgraduate Prize2022
Y. S. and Christabel Lung Postgraduate Scholarship2021
Zhejiang Provincial Government Scholarship2016–2017 · Top distinction in Zhejiang Province
Honorable Mention · Mathematical Contest in Modeling2018
Zhejiang University Outstanding Second Class Scholarship2016–2018

ACADEMIC SERVICE

Professional activities

Conference reviewer

CVPR · ICCV · NeurIPS · SIGGRAPH Asia · Pacific Graphics · AAAI · ICLR · ICML · ECCV · ACCV

Journal reviewer

TPAMI · IJCV · TMM · TVCG · TCSVT