Fanding Huang

I am a master student at Shenzhen International Graduate School, Tsinghua University, co-supervised by Zhi Wang, Jingyan Jiang and Faisal Nadeem Khan. Before that, I got B.S. in Automation from Hangzhou Dianzi University in 2024, supervised by Wenhui Zhou.

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

Google Scholar  /  OpenReview  /  Github  /  Twitter

profile photo
News

  • 2026.06: Our work DEFAR is accepted by ECCV 2026.
  • 2026.04: Our work VERL is accepted by ACL 2026 Findings.
  • 2026.02: Our work IGen is accepted by CVPR 2026.
  • 2025.12: We have released a new paper IGen on data acquisition for robot learning.
  • 2025.11: Our work MoETTA is accepted by AAAI 2026.
  • 2025.09: We have released a new paper VERL on Reinforcement Learning for reasoning LLM.
  • 2025.02: Our work COSMIC is accepted by CVPR 2025.
  • 2023.07: Our work DTBS is accepted by ECAI 2023.
  • Education & Experiences
    Jan. 2026 - Present
    Research Intern, Beijing Academy of Artificial Intelligence (BAAI), China
    Embodied Multimodal Foundation Model Research Center
    Sept. 2024 - Present
    M.S. Student, Tsinghua University SIGS, China
    Data Science and Information Technology
    Sept. 2020 - Jun. 2024
    B.S. Student, Hangzhou Dianzi University, China
    Automation
    Advisor: Wenhui Zhou

    Publications and Preprints

    * indicates equal contribution, † indicates corresponding author

    ChunkTrust
    Anonymous Authors
    In Submission
    [Project Page]
    PRM-as-a-Judge OPD paradigm PRM-as-a-Judge: A Dense Evaluation Paradigm for Fine-Grained Robotic Auditing
    Yuheng Ji*, Yuyang Liu*, Huajie Tan*, Xuchuan Huang, Fanding Huang, Yijie Xu, Cheng Chi, Yuting Zhao, Huaihai Lyu, Peterson Co, Mingyu Cao, Qiongyu Zhang, Zhe Li, Enshen Zhou, Pengwei Wang, Zhongyuan Wang, Shanghang Zhang†, Xiaolong Zheng†
    Preprint, 2026; arXiv:2603.21669
    [Project Page] [Paper] [arXiv] [Code]
    DEFAR qualitative comparison Exposure Bias Can Alleviate Itself via Directional and Frequency Rectification in Flow Matching
    Guanbo Huang*, Jingjia Mao*, Fanding Huang*, Fengkai Liu, Xiangyang Luo, Yaoyuan Liang, Jiasheng Lu, Xiaoe Wang, Pei Liu, Ruiliu Fu†, Ruqi Huang†, Shao-Lun Huang
    European Conference on Computer Vision (ECCV), 2026
    [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
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
    [Project Page] [Paper] [arXiv] [Code]
    dise Semantic-Space Exploration and Exploitation in RLVR for LLM Reasoning
    Fanding Huang*, Guanbo Huang*, Xiao Fan, Yi He, Xiao Liang, Xiao Chen, Qinting Jiang, Faisal Nadeem Khan, Jingyan Jiang†, Zhi Wang
    The 64th Annual Meeting of the Association for Computational Linguistics (ACL Findings), 2026
    [Project Page] [Paper] [arXiv] [Code]
    dise 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]
    dise 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]
    dise 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]
    dise 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

  • Tsinghua Shenzhen Graduate School First-Class Scholarship, 2025. (清华深研院一等奖学金)
  • 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

    © Fanding Huang | Last updated: Jun. 29, 2026