Zhaoyang Li

I am a Ph.D. candidate in the Department of Automation at the University of Science and Technology of China (USTC), advised by Prof. Tianzhu Zhang. I received my bachelor's degree in Computer Science and Technology from Central South University in 2022.

My research interests include video generation, efficient vision-language models, and world model. I am especially interested in building visual and multimodal systems that remain reliable under limited supervision, domain shift, and complex real-world conditions.

I have published papers at ICLR, ICML, ICCV, CVPR, ECCV, NeurIPS, and IJCAI. I also worked as an AIGC algorithm intern at ByteDance with Kai Su and Zehuan Yuan, focusing on subject-to-video generation and large-scale model post-training.

I am currently a research intern in the World Models team at AceRobotics, supervised by Dr. Fei Wang. I expect to graduate in Fall 2027 and welcome opportunities to connect.

News

[05/2026] SpecFlow was accepted to ICML 2026.
[01/2026] BindWeave was accepted to ICLR 2026.
[09/2025] ECOCSeg was accepted to NeurIPS 2025.
[06/2025] LARM was accepted to ICCV 2025.
[05/2025] BLDA was accepted to ICML 2025.
[03/2025] DATO and VISA were accepted to CVPR 2025.
[12/2024] I received 1st place in the WSI-level Glomeruli Detection track of the Kidney Pathology Image Segmentation Challenge at MICCAI 2024.
[07/2024] DLE was accepted to ECCV 2024.
[04/2024] DENet was accepted to IJCAI 2024.
[09/2023] I received 1st place in the Cell Detection from Cell-Tissue Interaction Challenge at MICCAI 2023.
[12/2022] I received Meritorious Winner, ranked 4/102, in the Weakly Supervised Cell Segmentation in Multi-modality High-Resolution Microscopy Images Challenge at NeurIPS 2022.

Publications

Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models
Zhaoyang Li, Yanjun Li, Wangkai Li, Yujia Chen, Tianzhu Zhang
ICML 2026

[paper] | [code]

BindWeave: Subject-Consistent Video Generation via Cross-Modal Integration
Zhaoyang Li, Dongjun Qian, Kai Su, Qishuai Diao, Xiangyang Xia, Chang Liu, Wenfei Yang, Tianzhu Zhang, Zehuan Yuan
ICLR 2026

[page] | [paper] | [code]

Adaptive Augmentation-Aware Latent Learning for Robust LiDAR Semantic Segmentation
Wangkai Li, Zhaoyang Li, Yuwen Pan, Rui Sun, Yujia Chen, Tianzhu Zhang
ICLR 2026

[paper]

Towards Robust Pseudo-Label Learning in Semantic Segmentation: An Encoding Perspective
Wangkai Li, Rui Sun, Zhaoyang Li, Tianzhu Zhang
NeurIPS 2025

[paper] | [code]

Generalized Few-Shot Point Cloud Segmentation via LLM-Assisted Hyper-Relation Matching
Zhaoyang Li, Yuan Wang, Guoxin Xiong, Wangkai Li, Yuwen Pan, Tianzhu Zhang
ICCV 2025

[paper]

Balanced Learning for Domain Adaptive Semantic Segmentation
Wangkai Li, Rui Sun, Bohao Liao, Zhaoyang Li, Tianzhu Zhang
ICML 2025

[page] | [code]

Dual-Agent Optimization Framework for Cross-Domain Few-Shot Segmentation
Zhaoyang Li, Yuan Wang, Wangkai Li, Tianzhu Zhang, Xiang Liu
CVPR 2025

[paper]

Unbiased Video Scene Graph Generation via Visual and Semantic Dual Debiasing
Yanjun Li, Zhaoyang Li, Honghui Chen, Lizhi Xu
CVPR 2025

[paper]

Localization and Expansion: A Decoupled Framework for Point Cloud Few-Shot Semantic Segmentation
Zhaoyang Li, Yuan Wang, Wangkai Li, Rui Sun, Tianzhu Zhang
ECCV 2024

[paper]

Aggregation and Purification: Dual Enhancement Network for Point Cloud Few-Shot Segmentation
Guoxin Xiong, Yuan Wang, Zhaoyang Li, Wenfei Yang, Tianzhu Zhang, Xu Zhou, Shifeng Zhang, Yongdong Zhang
IJCAI 2024

[paper]

Honors and Awards

Huawei PhD Fellowship.
Wu Weiren Deep Space Exploration Scholarship.
First-class Scholarship, Graduate School of USTC, awarded four times.
First-class Scholarship, Undergraduate School of Central South University.
1st place, Cell Detection from Cell-Tissue Interaction Challenge, MICCAI 2023.
Meritorious Winner, Weakly Supervised Cell Segmentation Challenge, NeurIPS 2022.

Education and Experience

2022.09 - present, Ph.D. student, Department of Automation, University of Science and Technology of China.
2026.05 - present, Research Intern, World Models team, AceRobotics.
2025.06 - 2025.12, AIGC Research Intern, ByteDance, Shanghai.
2022.12 - 2024.06, Institute of Artificial Intelligence, Hefei Comprehensive National Science Center.
2018.09 - 2022.06, B.Eng. in Computer Science and Technology, Central South University.

Reviewer Service

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025, 2026.
International Conference on Computer Vision (ICCV), 2025.
International Conference on Learning Representations (ICLR), 2026.
European Conference on Computer Vision (ECCV), 2026.
Advances in Neural Information Processing Systems (NeurIPS), 2026.
International Conference on Machine Learning (ICML), 2026.