Toggle navigation
首页
教师中心
EN
教育经历
2012.09 – 2017.07 清华大学计算机科学与技术博士，指导导师：孙富春教授
2016.03 – 2017.03 澳大利亚国立大学联合培养博士，联合指导导师：Mehrtash Harandi
2008.09 – 2012.07 北京航空航天大学数学与应用数学学士
工作经历
2023.07 – 至今 中国人民大学高瓴人工智能学院准聘副教授
2022.09 – 2023.07 中国人民大学高瓴人工智能学院准聘助理教授
2019.10 – 2022.09 清华大学计算机系博士后、清华大学智能产业院助理研究员
2017.07 – 2019.09 腾讯公司人工智能实验室高级研究员
研究方向
"There is no royal road to geometry. " --- Euclid
Geometric Learning And Discovery (GLAD) 课题组的研究方向包括但不限于：
1. 几何深度学习基础理论方法：将图像、视频、时空序列、社交网络、科学数据等建模成具有特定对称性结构的几何对象，例如集合、流形、图等，并建立相应机器学习模型对其进行表示和处理。特别在图数据处理和图神经网络GNN设计方面有深入研究，包括图神经网络的表达性、不变与等变性、高效训练、自监督学习、对抗攻击等。
2. 几何深度学习在智能体感知与决策的应用：研究触觉力序列表示、视频分析、声音信号处理、基于多模态信息融合的机器人感知；基于模型的强化学习、不完美信息下的模仿学习等。
3. 科学和社会科学知识嵌入的几何深度学习：致力于将黎曼几何、代数群论、量子力学、计算化学、计算生物、金融工程等学科的知识嵌入到机器学习模型，并将其应用到多体问题、分子动力学模拟、药物分子性质预测、蛋白质对接、抗体设计、晶体设计、金融决策等科学问题中。
这里附上集智平台对课题组研究工作的总结：
1. 报告链接：https://pattern.swarma.org/study_group_issue/485
2. 术语和资源汇总：https://pattern.swarma.org/study_group_issue/485/resource
3. 内容整理：https://pattern.swarma.org/article/243
学生要求
数学基础好、编程能力突出者优先考虑；非常欢迎具有交叉学科背景（物理、计算化学、计算生物、金融工程、计量经济学等）的学生。
（1）在读博士生
2023级：吴黎明，岑嘉诚，李宗钊
2024级：张岳霖，李安亿，李晨
（2）在读硕士生
2023级：黄贸之
2024级：李明泽，李松佑
（3）访问或联合培养学生
矫瑞（清华刘洋老师），孔祥哲（清华刘洋老师），虞子扬（清华刘洋老师），程思婕（清华刘洋老师），陈润发（清华孙富春老师），韩荣（清华陈挺老师），薛方磊（浙大杨易老师，华盛顿David Baker老师）
（4）已毕业学生
韩家琦（去处：斯坦福大学博士生）
教授课程
本科生课程《数字信号处理》秋季学期
本科生课程《多模态机器学习》秋季学期
研究生课程《几何深度学习》秋季学期
科研项目
2023-2025，面向药物发现的图数据大模型技术研究及示范应用，北京市中央引导地方专项，子课题负责人
2023-2026，面向物理空间的通用几何深度学习理论与方法，北京市科技新星计划，项目负责人
2024-2027，离散物理系统的通用几何图学习理论方法，国家自然科学基金面上项目，项目负责人
2020-2024，表征学习基础理论及手部多模态生物特征识别系统验证，科技部科技创新2030 --“新一代人工智能”重大项目，合作单位负责人
2021-2023，图神经网络的可学习理论与方法，国家自然科学基金青年项目，项目负责人
2019-2021，智能体模仿学习的图结构化理论方法，中国博士后科学基金面上资助，项目负责人
长期承担腾讯、华为、阿里等科技公司的科研合作项目。
学术论文
2024
Learning Superconductivity from Ordered and Disordered Material Structures
Pin Chen, Luoxuan Peng, Rui Jiao, Qing Mo, Zhen WANG, Wenbing Huang, Yang Liu, Yutong Lu
Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track
链接：
链接
3D Structure Prediction of Atomic Systems with Flow-based Direct Preference Optimization
Rui Jiao, Xiangzhe Kong, Wenbing Huang, Yang Liu
Annual Conference on Neural Information Processing Systems (NeurIPS)
链接：
链接
Full-Atom Peptide Design with Geometric Latent Diffusion
Xiangzhe Kong, Yinjun Jia, Wenbing Huang, Yang Liu
Annual Conference on Neural Information Processing Systems (NeurIPS)
链接：
链接
Are High-Degree Representations Really Unnecessary in Equivariant Graph Neural Networks?
Jiacheng Cen, Anyi Li, Ning Lin, Yuxiang Ren, Zihe Wang, Wenbing Huang
Annual Conference on Neural Information Processing Systems (NeurIPS)
链接：
链接
Improving Equivariant Graph Neural Networks on Large Geometric Graphs via Virtual Nodes Learning
Yuelin Zhang, Jiacheng Cen, Jiaqi Han, Zhiqiang Zhang, Jun Zhou, Wenbing Huang
International Conference on Machine Learning (ICML)
链接：
链接
Generalist Equivariant Transformer Towards 3D Molecular Interaction Learning
Xiangzhe Kong, Wenbing Huang, Yang Liu
International Conference on Machine Learning (ICML)
链接：
链接
Equivariant Diffusion for Crystal Structure Prediction
Peijia Lin, Pin Chen, Rui Jiao, Qing Mo, Cen Jianhuan, Wenbing Huang, Yang Liu, Dan Huang, Yutong Lu
International Conference on Machine Learning (ICML)
链接：
链接
EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site Prediction
Yang zhang, Zhewei Wei, Ye Yuan, Chongxuan Li, Wenbing Huang
International Conference on Machine Learning (ICML), Oral
链接：
链接
Subequivariant Reinforcement Learning in 3D Multi-Object Physical Environments
Runfa Chen, Ling Wang, Yu Du, Fuchun Sun, Tianrui Xue, Jianwei Zhang, Wenbing Huang
International Conference on Machine Learning (ICML)
链接：
链接
Macro Graph Neural Networks for Online Billion-Scale Recommender Systems
Hao Chen, Yuanchen Bei, Qijie Shen, Yue Xu, Sheng Zhou, Wenbing Huang, Feiran Huang, Senzhang Wang, Xiao Huang
The Web Conference (WWW)
链接：
链接
Rigid Protein-Protein Docking via Equivariant Elliptic-Paraboloid Interface Prediction
Ziyang Yu, Wenbing Huang, Yang Liu
The International Conference on Learning Representations (ICLR)
链接：
链接
Space Group Constrained Crystal Generation
Rui Jiao, Wenbing Huang, Yu Liu, Deli Zhao, Yang Liu
The International Conference on Learning Representations (ICLR)
链接：
链接
2023
MPerformer: An SE(3) Transformer-based Molecular Perceptron
Fanmeng Wang, Hongteng Xu, Xi Chen, Shuqi Lu, Yuqing Deng, Wenbing Huang
ACM International Conference on Information and Knowledge Management (CIKM)
Equivariant Spatio-Temporal Attentive Graph Networks to Simulate Physical Dynamics
Liming Wu, Zhichao Hou, Jirui Yuan, Yu Rong, Wenbing Huang
Annual Conference on Neural Information Processing Systems (NeurIPS)
链接：
链接
Crystal Structure Prediction by Joint Equivariant Diffusion
Rui Jiao, Wenbing Huang, Peijia Lin, Jiaqi Han, Pin Chen, Yutong Lu, Yang Liu
Annual Conference on Neural Information Processing Systems (NeurIPS)
链接：
链接
Structure-Aware DropEdge Towards Deep Graph Convolutional Networks
Jiaqi Han, Wenbing Huang, Yu Rong, Tingyang Xu, Fuchun Sun, Junzhou Huang
IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
链接：
链接
End-to-End Full-Atom Antibody Design
Xiangzhe Kong, Wenbing Huang, Yang Liu
International Conference on Machine Learning (ICML)
链接：
链接
Subequivariant Graph Reinforcement Learning in 3D Environments
Runfa Chen, Jiaqi Han, Fuchun Sun, Wenbing Huang
International Conference on Machine Learning (ICML), Oral
链接：
链接
Compacting Binary Neural Networks by Sparse Kernel Selection
Yikai Wang, Wenbing Huang, Yinpeng Dong, Fuchun Sun, Anbang Yao
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
链接：
链接
Conditional Antibody Design as 3D Equivariant Graph Translation
Xiangzhe Kong, Wenbing Huang, Yang Liu
The International Conference on Learning Representations (ICLR) , Outstanding Paper Honorable Mention
链接：
链接
Planning Assembly Sequence with Graph Transformer
Lin Ma, Jiangtao Gong, Hao Xu, Hao CHEN, Hao Zhao, Wenbing Huang, Guyue Zhou
IEEE International Conference on Robotics and Automation (ICRA)
Energy-Motivated Equivariant Pretraining for 3D Molecular Graphs
Rui Jiao, Jiaqi Han, Wenbing Huang, Yu Rong, Yang Liu
AAAI Conference on Artificial Intelligence (AAAI)
链接：
链接
2022
Geometrically Equivariant Graph Neural Networks: A Survey
Jiaqi Han, Yu Rong, Tingyang Xu, Wenbing Huang
arXiv
链接：
链接
Learning Physical Dynamics with Subequivariant Graph Neural Networks
Jiaqi Han, Wenbing Huang, Hengbo Ma, Jiachen Li, Joshua B. Tenenbaum, Chuang Gan
Annual Conference on Neural Information Processing Systems (NeurIPS), Spotlight
下载：
链接：
链接
Equivariant Graph Hierarchy-based Neural Networks
Jiaqi Han, Wenbing Huang, Tingyang Xu, Yu Rong
Annual Conference on Neural Information Processing Systems (NeurIPS), Spotlight
链接：
链接
Molecule Generation by Principal Subgraph Mining and Assembling
Xiangzhe Kong, Wenbing Huang, Zhixing Tan, Yang Liu
Annual Conference on Neural Information Processing Systems (NeurIPS), Oral
链接：
链接
When to Update Your Model: Constrained Model-based Reinforcement Learning
Tianying Ji, Yu Luo, Fuchun Sun, Mingxuan Jing, Fengxiang He, Wenbing Huang
Annual Conference on Neural Information Processing Systems (NeurIPS), Spotlight
链接：
链接
SNAKE: Shape-aware Neural 3D Keypoint Field
Chengliang Zhong, Peixing You, Xiaoxue Chen, Hao Zhao, Fuchun Sun, Guyue Zhou, Xiaodong Mu, Chuang Gan, Wenbing Huang
Annual Conference on Neural Information Processing Systems (NeurIPS), Spotlight
链接：
链接
Benefits of Permutation-Equivariance in Auction Mechanisms
Tian Qin, Fengxiang He, Dingfeng Shi, Wenbing Huang, Dacheng Tao
Annual Conference on Neural Information Processing Systems (NeurIPS)
链接：
链接
Learning Active Camera for Multi-Object Navigation
Peihao Chen, Dongyu Ji, Kunyang Lin, Weiwen Hu, Wenbing Huang, Thomas H. Li, Mingkui Tan, Chuang Gan
Annual Conference on Neural Information Processing Systems (NeurIPS), Spotlight
链接：
链接
Equivariant Graph Mechanics Networks with Constraints
Wenbing Huang, Jiaqi Han, Yu Rong, Tingyang Xu, Fuchun Sun, and Junzhou Huang
The International Conference on Learning Representations (ICLR)
链接：
链接
Sound Adversarial Audio-Visual Navigation
Yinfeng Yu, Wenbing Huang, Fuchun Sun, Changan Chen, Yikai Wang, and Xiaohong Liu
The International Conference on Learning Representations (ICLR)
链接：
链接
Learning Representations by Graphical Mutual Information Estimation and Maximization
Zhen Peng, Minnan Luo, Wenbing Huang, Jundong Li, Qinghua Zheng, Fuchun Sun, and Junzhou Huang
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
链接：
链接
Bridged Transformer for Vision and Point Cloud 3D Object Detection
Yikai Wang, TengQi Ye, Lele Cao, Wenbing Huang, Fuchun Sun, Fengxiang He, and Dacheng Tao
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
链接：
链接
Multimodal Token Fusion for Vision Transformers
Yikai Wang, Xinghao Chen, Lele Cao, Wenbing Huang, Fuchun Sun, and Yunhe Wang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
链接：
链接
Adversarial Attack Framework on Graph Embedding Models with Limited Knowledge
Heng Chang, Yu Rong, Tingyang Xu, Wenbing Huang, Honglei Zhang, Peng Cui, Xin Wang, and Wenwu Zhu
IEEE Transactions on Knowledge and Data Engineering (TKDE)
Cross-Dependent Graph Neural Networks for Molecular Property Prediction
Hehuan Ma, Yatao Bian, Yu Rong, Wenbing Huang, Tingyang Xu, Weiyang Xie, Geyan Ye, and Junzhou Huang
Bioinformatics
2021
Adversarial Option-Aware Hierarchical Imitation Learning
Mingxuan Jing, Wenbing Huang, Fuchun Sun, Xiaojian Ma, Tao Kong, Chuang Gan, and Lei Li
International Conference on Machine Learning (ICML)
链接：
链接
Elastic Tactile Simulation Towards Tactile-Visual Perception
Yikai Wang, Wenbing Huang, Fuchun Sun, Bin Fang, and Chang Li
ACM International Conference on Multimedia (ACMMM)
链接：
链接
Knowledge Representation Learning with Contrastive Completion Coding
Bo Ouyang, Wenbing Huang, Runfa Chen, Zhixing Tan, Yang Liu, Maosong Sun, and Jihong Zhu
The 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP) (Findings)
Graph Convolutional Module for Temporal Action Localization in Videos
Runhao Zeng, Wenbing Huang, Mingkui Tan, Yu Rong, Peilin Zhao, Junzhou Huang, Chuang Gan
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
链接：
链接
2020
Tackling Over-Smoothing for General Graph Convolutional Networks
Wenbing Huang, Yu Rong, Tingyang Xu, Fuchun Sun, Junzhou Huang
arXiv
链接：
链接
DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
Yu Rong, Wenbing Huang, Tingyang Xu, and Junzhou Huang
The International Conference on Learning Representations (ICLR)
链接：
链接
Self-Supervised Graph Transformer on Large-Scale Molecular Data
Yu Rong, Yatao Bian, Tingyang Xu, Weiyang Xie, Ying Wei, Wenbing Huang, and Junzhou Huang
Annual Conference on Neural Information Processing Systems (NeurIPS)
链接：
链接
Deep Multimodal Fusion by Channel Exchanging
Yikai Wang, Wenbing Huang, Fuchun Sun, Tingyang Xu, Yu Rong, and Junzhou Huang
Annual Conference on Neural Information Processing Systems (NeurIPS)
链接：
链接
Reusing Discriminators for Encoding: Towards Unsupervised Image-to-Image Translation
Runfa Chen, Wenbing Huang, Binghui Huang, Fuchun Sun, and Bin Fang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
链接：
链接
Dense Regression Network for Video Grounding
Runhao Zeng, Haoming Xu, Wenbing Huang, Peihao Chen, Mingkui Tan, and Chuang Gan
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
链接：
链接
Reinforcement Learning from Imperfect Demonstrations under Soft Expert Guidance
Mingxuan Jing, Xiaojian Ma, Wenbing Huang, Fuchun Sun, Chao Yang, Bin Fang, and Huaping Liu
AAAI Conference on Artificial Intelligence (AAAI), Spotlight
链接：
链接
Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networks
Tian Bian, Xi Xiao, Tingyang Xu, Peilin Zhao, Wenbing Huang, Yu Rong, and Junzhou Huang
AAAI Conference on Artificial Intelligence (AAAI)
链接：
链接
The General Black-box Attack Method for Graph Neural Networks
Heng Chang, Yu Rong, Tingyang Xu, Wenbing Huang, Honglei Zhang, Peng Cui, Wenwu Zhu, and Junzhou Huang
AAAI Conference on Artificial Intelligence (AAAI)
Graph Representation Learning via Graphical Mutual Information Maximization
Zhen Peng, Wenbing Huang, Minnan Luo, Qinghua Zheng, Yu Rong, Tingyang Xu, and Junzhou Huang
The Web Conference (WWW)
链接：
链接
2019
Toward efficient action recognition: Principal backpropagation for training two-stream networks
Wenbing Huang, Lijie Fan, Mehrtash Harandi, Lin Ma, Huaping Liu, Wei Liu, and Chuang Gan
IEEE Transactions on Image Processing (TIP)
Imitation learning from observations by minimizing inverse dynamics disagreement
Chao Yang, Xiaojian Ma, Wenbing Huang, Fuchun Sun, Huaping Liu, Junzhou Huang, and Chuang Gan
Annual Conference on Neural Information Processing Systems (NeurIPS), Spotlight
链接：
链接
Neural collaborative subspace clustering
Tong Zhang, Pan Ji, Mehrtash Harandi, Wenbing Huang, and Hongdong Li
International Conference on Machine Learning (ICML)
链接：
链接
Graph convolutional networks for temporal action localization
Runhao Zeng, Wenbing Huang, Mingkui Tan, Yu Rong, Peilin Zhao, Junzhou Huang, and Chuang Gan
International Conference on Computer Vision (ICCV)
链接：
链接
A fast and accurate one-stage approach to visual grounding
Zhengyuan Yang, Boqing Gong, Liwei Wang, Wenbing Huang, Dong Yu, and Jiebo Luo
International Conference on Computer Vision (ICCV), Oral
Controllable image-to-video translation: A case study on facial expression generation
Lijie Fan, Wenbing Huang, Chuang Gan, Junzhou Huang, and Boqing Gong
AAAI Conference on Artificial Intelligence (AAAI), Oral
链接：
链接
Task transfer by preference-based cost learning
Mingxuan Jing, Xiaojian Ma, Wenbing Huang, Fuchun Sun, and Huaping Liu
AAAI Conference on Artificial Intelligence (AAAI)
链接：
链接
Beyond rnns: Positional self-attention with co-attention for video question answering
Xiangpeng Li, Jingkuan Song, Lianli Gao, Xianglong Liu, Wenbing Huang, Xiangnan He, and Chuang Gan
AAAI Conference on Artificial Intelligence (AAAI)
Semi-supervised graph classification: A hierarchical graph perspective
Jia Li, Yu Rong, Hong Cheng, Helen Meng, Wenbing Huang, and Junzhou Huang
The Web Conference (WWW)
链接：
链接
2018
Adaptive sampling towards fast graph representation learning
Wenbing Huang, Tong Zhang, Yu Rong, and Junzhou Huang
Annual Conference on Neural Information Processing Systems (NeurIPS)
链接：
链接
Weakly supervised dense event captioning in videos
Xuguang Duan, Wenbing Huang, Chuang Gan, Jingdong Wang, Wenwu Zhu, and Junzhou Huang
Annual Conference on Neural Information Processing Systems (NeurIPS)
链接：
链接
End-to-end learning of motion representation for video understanding
Lijie Fan, Wenbing Huang, Chuang Gan, Stefano Ermon, and Boqing Gong
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Spotlight
链接：
链接
LDS-FCM: A linear dynamical system based fuzzy C-means method for tactile recognition
Chunfang Liu, Wenbing Huang, Fuchun Sun, Minnan Luo, and Chuanqi Tan
IEEE Transactions on Fuzzy Systems
2017
Efficient Optimization for Linear Dynamical Systems with Applications to Clustering and Dictionary Learning
Wenbing Huang, Mehrtash Harandi, Tong Zhang, Lijie Fan, Fuchun Sun, and Junzhou Huang
Annual Conference on Neural Information Processing Systems (NeurIPS)
链接：
链接
2016
Sparse Coding and Dictionary Learning with Linear Dynamical Systems
Wenbing Huang, Fuchun Sun, Lele Cao, Deli zhao, Huaping Liu, and Mehrtash Harandi
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Oral
链接：
链接
Learning Stable Linear Dynamical Systems using the Weighted Least Square Method
Wenbing Huang, Lele Cao, Fuchun Sun, Deli zhao, Huaping Liu, and Shanshan Yu
International Joint Conference on Artificial Intelligence (IJCAI)
链接：
链接
2015
Scalable Gaussian Process Regression using Deep Neural Networks
Wenbing Huang, Deli Zhao, Fuchun Sun, Huaping Liu, and Edward Chang
International Joint Conference on Artificial Intelligence (IJCAI)
链接：
链接
荣誉奖励
2024年 斯坦福大学全球前2%顶尖科学家年度榜单
2023年 斯坦福大学全球前2%顶尖科学家年度榜单
2023年 2022年度腾讯AI Lab犀牛鸟专项研究计划卓越奖（27项受资助项目排名第一）
2023年 北京科技新星计划
2023年 ICLR Outstanding Paper Honorable Mention (< 0.19%)
2022年 NeurIPS Open Catalyst 竞赛冠军
2022年 斯坦福大学全球前2%顶尖科学家年度榜单
2021年 2020年度腾讯AI Lab犀牛鸟专项研究及访问学者计划卓越奖（27项受资助项目排名第一）
2021年 NeurIPS Outstanding Reviewer Award (Top 8%)
2021年 AAAI Top SPC award (Top 25%)
2020年 IROS 开放云机器人桌面整理挑战赛（OCRTOC）季军
2020年 MSRA铸星计划学者
2020年 腾讯犀牛鸟学者
2019年 清华大学水木学者
2019年 腾讯卓越运营奖
社会兼职
Area Chair: NeurIPS 2024, ICLR 2025, ICML 2025
Action Editor: TMLR
SPC Member: AAAI 2021-2022, IJCAI 2021
Reviewer for IEEE TPAMI, IEEE TIP, IEEE TMM, IEEE TNNLS, IEEE TKDE
中国人工智能学会组织工委委员
中国人工智能学会认知系统与信息处理专委会委员
中国计算机学会人工智能与模式识别专业委员会执行委员
中国自动化学会认知计算与系统专委会委员
联系
电话：--
邮箱：hwenbing@126.com, hwenbing@ruc.edu.cn
个人网页：--
办公地址：--