Fanding Huang

I am a master student at Shenzhen International Graduate School, Tsinghua University. Before that, I got B.S. in Automation from Hangzhou Dianzi University (HDU) in 2024.

My current research focuses on Computer Vision, Embodied Intelligence, Reinforcement Learning, Test-time Adaptation, MLLM & LLM & VLA. Here is my Email: hfd24@mails.tsinghua.edu.cn

Google Scholar / OpenReview / Github / Twitter

News

2025.12: We have released a new paper ReflexFlow for alleviating exposure bias in Flow Matching.

2025.12: We have released a new paper IGen on data acquisition for robot learning.

2025.11: MoETTA is accepted by AAAI 2026.

2025.09: We have released a new paper VERL on Reinforcement Learning for reasoning LLM.

2025.02: COSMIC is accepted by CVPR 2025.

2023.07: DTBS is accepted by ECAI 2023.

Publications and Preprints

* indicates equal contribution, † indicates corresponding author

	ReflexFlow: Rethinking Learning Objective for Exposure Bias Alleviation in Flow Matching Guanbo Huang, Jingjia Mao, Fanding Huang, Fengkai Liu, Xiangyang Luo, Yaoyuan Liang, Jiasheng Lu, Xiaoe Wang, Pei Liu, Ruiliu Fu†, Shao-Lun Huang† Preprint* [Project Page] [Paper] [arXiv] [Code]
	IGen: Scalable Data Generation for Robot Learning from Open-World Images Chenghao Gu, Haolan Kang, Junchao Lin, Jinghe Wang, Duo Wu, Shuzhao Xie, Fanding Huang, Junchen Ge, Ziyang Gong, Letian Li, Hongying Zheng, Changwei Lv, Zhi Wang† Preprint* [Project Page] [Paper] [arXiv] [Code]
	MoETTA: Test-Time Adaptation Under Mixed Distribution Shifts with MoE-LayerNorm Xiao Fan, Jingyan Jiang†, Zhaoru Chen, Fanding Huang, Xiao Chen, Qinting Jiang, Bowen Zhang, Xing Tang, Zhi Wang The 40th Annual AAAI Conference on Artificial Intelligence (AAAI), 2026* [Paper] [arXiv] [Code]
	Beyond the Exploration-Exploitation Trade-off: A Hidden State Approach for LLM Reasoning in RLVR Fanding Huang, Guanbo Huang, Xiao Fan, Yi He, Xiao Liang, Xiao Chen, Qinting Jiang, Faisal Nadeem Khan, Jingyan Jiang†, Zhi Wang† Preprint [Project Page] [Paper] [arXiv] [Code]
	COSMIC: Clique-Oriented Semantic Multi-space Integration for Robust CLIP Test-Time Adaptation Fanding Huang, Jingyan Jiang, Qinting Jiang, Hebei Li, Faisal Nadeem Khan†, Zhi Wang† IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025 [Project Page] [Paper] [arXiv] [Code]
	Mecon: A GNN-based Graph Classification Framework for MEV Activity Detection Zihao Yao, Fanding Huang, Yannan Li†, Wei Duan, Peng Qian, Nan Yang, Willy Susilo Expert Systems with Applications (ESWA, IF=7.5), 2025 [Paper]
	DTBS: Dual-Teacher Bi-directional Self-training for Domain Adaptation in Nighttime Semantic Segmentation Fanding Huang, Zihao Yao, Wenhui Zhou† European Conference on Artificial Intelligence (ECAI), 2023 [Project Page] [Paper] [arXiv] [Code]

Selected Honors and Awards

Outstanding Bachelor Graduate of Hangzhou, 2024. (杭州市优秀毕业生, Top 5% in HDU)

CMC2023 Frist Prize, 2023. (全国大学生数学竞赛非数A类一等奖)

Website Template