Leyi Wu 吴乐毅

Fourth-year Undergraduate Student | Computer Vision, Generative Models, Embodied AI
Shenzhen, China (+86) 13607637321 lwu398@connect.hkust-gz.edu.cn Personal Page Github
Profile
Fourth-year undergraduate student at HKUST(GZ) majoring in Artificial Intelligence with research experience across video generation, 3D generation, rendering, VLM reasoning, and embodied AI. Co-author of works accepted to NeurIPS 2026, ECCV 2026, ICLR 2026, and CVPR 2025; ICPC Asia-East Continent Final gold medalist and EgoCross Challenge dual-track champion.

Research Experience

Undergraduate Researcher, Prof. Ying-Cong Chen's Lab
2024 - Present
Generative models for controllable video, 3D assets, rendering, and visual understanding
  • Contribute to diffusion-based rendering, 3D/texture generation, controllable video generation, video-model evaluation, and mechanistic analysis of video generation as world models.
Research Intern, KnowinAI
Sep. 2025 - Present
Robotic garment folding under complex dynamic visual interference
  • Led a real-world robotic folding system under dynamic screen backgrounds and complex colored lighting, integrating visual perception with manipulation control.
  • Validated stable folding of short- and long-sleeve garments in high-interference scenes; prepared the system for public demonstration at FAIR Plus robotics event.

Selected Publications

Seg3DParts: Segmentation-Grounded Controllable Part-Level 3D Generation
NeurIPS 2026 | Jiantao Lin*, Meixi Chen*, Yingjie Xu*, Chenbo Fu, Leyi Wu, Hao Chen, Yinchuan Li, Ying-Cong Chen.
Motion Forcing: Decoupling Ego and Object Motion via Sparse Inputs for Structured Video Generation
NeurIPS 2026 | Tianshuo Xu, Zhifei Chen, Leyi Wu, Hao Lu, Yingcong Chen†.
STANCE: Motion Coherent Video Generation Via Sparse-to-Dense Anchored Encoding
ECCV 2026 | Zhifei Chen*, Tianshuo Xu*, Leyi Wu*, Luozhou Wang, Dongyu Yan, Zihan You, Wenting Luo, Guo Zhang, Yingcong Chen†.
RoboStressBench: Benchmarking VLM Robustness to Physical Visual Stress in Embodied Scenes
Under Review | Leyi Wu*, Yifan Zhao*, Jinjie Zhang*, Suzeyu Chen*, Wosong Chen, Zhifei Chen, Tianshuo Xu, Qingchun He, Hongxin Hu, Haojian Huang, Yangkai Wei, Wenqian Li, Yinchuan Li, Ying-Cong Chen†.
AnimationBench: Are Video Models Good at Character-Centric Animation?
Under Review | Leyi Wu*, Pengjun Fang*, Kai Sun*, Yazhou Xing†, Yinwei Wu, Songsong Wang, Ziqi Huang, Dan Zhou, Yingqing He, Ying-Cong Chen, Qifeng Chen†.
FlexPainter: Flexible and Multi-View Consistent Texture Generation
Under Review | Dongyu Yan*, Leyi Wu*, Jiantao Lin, Luozhou Wang, Tianshuo Xu, Zhifei Chen, Zhen Yang, Lie Xu, Shunsi Zhang, Yingcong Chen†.
Uni-Renderer: Unifying Rendering and Inverse Rendering Via Dual Stream Diffusion
CVPR 2025 | Zhifei Chen*, Tianshuo Xu*, Wenhang Ge*, Leyi Wu, Dongyu Yan, Jing He, Luozhou Wang, Lu Zeng, Shunsi Zhang, Yingcong Chen†.
UniCalli: A Unified Diffusion Framework for Column-Level Generation and Recognition of Chinese Calligraphy
ICLR 2026 | Tianshuo Xu, Kai Wang, Zhifei Chen, Leyi Wu, Tianshui Wen, Fei Chao, Yingcong Chen†.
Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset Generation
CVPR 2025 | Jiantao Lin*, Xin Yang*, Meixi Chen*, Yingjie Xu, Dongyu Yan, Leyi Wu, Xinli Xu, Lie Xu, Shunsi Zhang, Yingcong Chen†.
* Equal contribution. † Corresponding author.
Publications, Honors, and Activities

Selected Impact

6
papers accepted at top-tier venues: NeurIPS, ECCV, ICLR, and CVPR.
5
ICPC/CCPC medals across Asia-level and national contests.
1st
Dual-track global champion of the 1st Cross-Domain EgoCross Challenge at CVPR 2026; team leader of an all-undergraduate team.
1
2025 National Scholarship recipient, the only university-wide annual slot.
10
2026 Litchi Innovation Talent Scholarship recipient, selected from 10 university-wide annual slots.

Additional Publications, Preprints, and Surveys

Motion Dreamer: Boundary Conditional Motion Reasoning for Physically Coherent Video Generation
Preprint | Tianshuo Xu*, Zhifei Chen*, Leyi Wu, Hao Lu, Yuying Chen, Lihui Jiang, Bingbing Liu, Yingcong Chen†.
Anvil: Scaling Embodied Spatial Intelligence through Knowledge Recirculation
Under Review, 2026 | Weilin Ruan, Bohan Zhou, Jinghao Li, Yangkai Wei, Wenqian Li, Peiran Dong, Yingjie Xu, Leyi Wu, Haojian Huang, Binghui Xie, Han Yang, Kaiwen Zhou, Yinchuan Li, Ying-Cong Chen, James Cheng.
RoboAware: Learning to Coordinate Embodied Skills from Counterfactual Outcomes
Preprint, 2026 | Bohan Zhou, Xingbei Chen, Emily Huang, Weilin Ruan, Haojian Huang, Yehang Zhang, Zexi Li, Wenqian Li, Qize Yu, Zetian Song, Leyi Wu, Jinghao Li, Mingxuan Song, Xinrun Xu, Zongyang Qiu, Yangkai Wei, Tianyi Zhang, Kaiwen Zhou, Yinchuan Li, James Cheng.
A Mechanistic View on Video Generation as World Models: State and Dynamics
Survey, 2026 | Luozhou Wang*, Zhifei Chen*, Yihua Du, Dongyu Yan, Wenhang Ge, Guibao Shen, Xinli Xu, Leyi Wu, Man Chen, Tianshuo Xu, Peiran Ren, Xin Tao, Pengfei Wan, Yingcong Chen†.
In-Context Learning for Robots: Methods and Applications
Survey, 2026 | Haojian Huang, Zexi Li, Junhao Guo, Yehang Zhang, Wenxuan Peng, Bohan Zhou, Weilin Ruan, Leyi Wu, Chenxu Wang, Jianchong Su, Binghui Xie, Wosong Chen, Yingjie Xu, Tianhao Zhou, Suzeyu Chen, Pukun Zhao, Jiaqi He, Xinyi Li, Runze Li, Peiran Dong, Shaoxiang Dang, Jing Huang, Yingbing Chen, Yifan Chang, Tianyi Zhang, Shiyuan Deng, Haozhi Wang, Yangkai Wei, Wenqian Li, Han Yang, Kaiwen Zhou, Huaping Liu, James Cheng, Rui Shao, Donglin Wang, Yaochu Jin, Jianye Hao, Ying-Cong Chen, Yinchuan Li.
The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answering
Challenge Report, 2026 | Yuqian Fu, Tianwen Qian, Yanjun Li, Yu Li, Kunyu Peng, Xu Zheng, Yongqin Xian, Alessio Tonioni, Yanwei Fu, Xiaoling Wang, Danda Paudel, Federico Tombari, Luc Van Gool, Leyi Wu, Yifan Zhao, Jinjie Zhang, Yinchuan Li, Yingcong Chen, Zixu Li, Zhiwei Chen, Zhiheng Fu, Wenbo Wang, Yupeng Hu, Weili Guan, Liqiang Nie, Takuya Murakawa, Toru Tamaki, Yi Wen, Zhenglin Du, Zhengyang Li, Lingling Li, Licheng Jiao, Wenping Ma.
* Equal contribution. † Corresponding author.

Honors and Scholarships

2025
National Scholarship, the only university-wide annual slot, awarded for academic excellence, research achievements, competitions, and service.
2026
Litchi Innovation Talent Scholarship, HKUST(GZ), selected from 10 university-wide annual slots.
2023-25
Dean's List Award for Fall 2023-2024, Spring 2024-2025, and Fall 2024-2025.

Programming Competitions and Challenges

2026
Dual-Track Champion, 1st Cross-Domain EgoCross Challenge under the 3rd EgoVis Workshop (CVPR 2026); global No. 1 in both tracks, team leader of an all-undergraduate team.
2024
Gold Medal, 16th place, Huawei Cup 2023 ICPC Asia-East Continent Final Contest.
2023
Silver Medal, ICPC Asia Hefei Regional Contest.
2023
Silver Medal, 48th ICPC Asia Regional Contest, Jinan Site.
2023
Silver Medal, China Collegiate Programming Contest, Shenzhen Site.
2023
Bronze Medal, China Collegiate Programming Contest, Harbin Site.

Research Communication

  • Research output was reposted by Hugging Face community influencer AK and received 10k+ impressions, reflecting active academic communication and community reach.