Fangyuan Mao

Fangyuan MAO

I am currently a master student at Institute of Computeing Technology, Chinese Academy of Sciences, supervised by Yu Hu and Jilin Mei. I obtained my bachelor's degree from Zhejiang University. I am fortunate to have research experiences at ANS@CASICT, Kling@Kuaishou, AMAP@Alibaba, VIPA@ZJU. I believe math and physics are the answers to artificial intelligence. I am trying to integrate more math knowledge with my research. My interests includes generative model, computer vision. Email: maofangyuan23s[at]ict[dot]ac[dot]cn, fangyuanmaocs[at]gmail[dot]com

Email / CV / Scholar / LinedIn / Github

Education

M.S @ Institute of Computing Technology, Chinese Academy of Sciences, 2023.09-2026.07. Supervisors: Prof. Yu Hu and Prof. Jilin Mei
B.S @ Zhejiang University, 2019.09-2023.06. Supervisors: Prof. Bo Yang and Prof. Yixian Xu

Internships

Research Intern working on Kling AI Infra at Kling@Kuaishou, 2025.12-2026.03. Mentor: Shun Lu.
Research Intern working on Video Generation at AMAP@Alibaba, 2025.04-2025.10. Mentors: Xiangxiang Chu and Jiahong Wu.
Research Intern working on model compression at VIPA@ZJU, 2022.01-2022.06. Supervisors: Mingli Song and Zunlei Feng.

Selected Publication

* indicates equal contribution.

	Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation Fangyuan Mao, Aiming Hao, Jintao Chen, Dongxia Liu, Xiaokun Feng, Jiashu Zhu, Meiqi Wu, Chubin Chen, Jiahong Wu, Xiangxiang Chu AAAI, 2026 paper / video / project page / code / dataset Unified and spatially-controlable visual effects generation pipeline. Omni-Effects supports prompt-guided and SAP-guided Multi-VFX.
	PID: Physics-Informed Diffusion Model for Infrared Image Generation Fangyuan Mao, Jilin Mei, Shun Lu, Fuyang Liu, Liang Chen, Fangzhou Zhao, Yu Hu Pattern Recognition, 2025 paper / code
	Recovering Missing Regions of Earth Magnetic Anomaly Grid data (EMAG2) Using RePaint based on Diffusion Model Fangyuan Mao, Bo Yang, Shenyao Jin Big Data and Earth System, 2025 paper / code
	SEA: Hierarchically Searching Efficient Adapters for Pre-trained Models Shun Lu, Fangyuan Mao, Junkun Chen, Jilin Mei, Chen Min, Yan Xing, Yu Hu Neural Network, 2026 paper / code
	Disassembling Convolutional Segmentation Network Kaiwen Hu, Jing Gao, Fangyuan Mao, Xinhui Song, Lechao Cheng, Zunlei Feng, Mingli Song IJCV, 2023 paper
	CORENet: Cross-Modal 4D Radar Denoising Network with LiDAR Supervision for Autonomous Driving Fuyang Liu, Jilin Mei, Fangyuan Mao, Yu Hu, Chen Min, Yan Xing IROS, 2025 paper / code
	S2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models Chubin Chen, Jiashu Zhu, Xiaokun Feng, Nisha Huang, Meiqi Wu, Fangyuan Mao, Jiahong Wu, Xiangxiang Chu, Xiu Li ICLR, 2026 paper / project page / code
	ImagerySearch: Adaptive Test-Time Search for Video Generation Beyond Semantic Dependency Constraints Meiqi Wu, Jiashu Zhu, Xiaokun Feng, Chubin Chen, Chen Zhu, Bingze Song, Fangyuan Mao, Jiahong Wu, Xiangxiang Chu, Kaiqi Huang AAAI, 2026 paper / code
	Advancing Off-Road Autonomous Driving: The Large-Scale ORAD-3D Dataset and Comprehensive Benchmarks Chen Min, Jilin Mei, Heng Zhai, Shuai Wang, Tong Sun, Fanjie Kong, Haoyang Li, Fangyuan Mao, Fuyang Liu, Shuo Wang, Yiming Nie, Qi Zhu, Liang Xiao, Dawei Zhao, Yu Hu ICRA, 2026 paper / code

Preprints

	UNIV: Unified Foundation Model for Infrared and Visible Modalities Fangyuan Mao, Shuo Wang, Jilin Mei, Shun Lu, Chen Min, Fuyang Liu, Xiaokun Feng, Meiqi Wu, Yu Hu Arxiv, 2025 paper / code
	MIGA: Make Train-Free Infinite Frame Generation Great Again for Consistent Long Videos Xiaokun Feng, Jiashu Zhu, Meiqi Wu, Chubin Chen, Fangyuan Mao, Haiyang Guo, Jiahong Wu, Xiangxiang Chu, Kaiqi Huang

Awards

Zhejiang Province Government Scholarship (Top 3%, 2020 and 2021)
Yifangda Financial Technology Master's Award (Top 2%, 2025)
Outstanding Graduate of Zhejiang University (2023)