Bin Li - AImpressionist
 |
Bin Li
Email: libin AT fudan DOT edu DOT cn |
Biography
I'm a Professor of Computer Science and Artificial Intelligence at Fudan University. I joined Fudan University in 2017. Prior to this, I was a Research Fellow at Institut TELECOM SudParis from 2009 to 2010, a Lecturer at University of Technology Sydney (UTS) from 2011 to 2013, and a Senior Research Scientist of Machine Learning at CSIRO's Data61 (formerly NICTA) from 2013 to 2017. I received my PhD degree in Computer Science from Fudan University in 2009. My current research interests lie in machine learning, visual cognition, generative AI, and their applications in physical scene understanding, intelligent document processing, visual content generation, abstract visual reasoning, and multi-model big data analytics; I'm particularly interested in foundational problems at the intersection of deep latent variable models and visual intelligence.
I am seeking undergraduate, master and PhD students. 博士生：对于博士生申请，优先考虑组成式场景建模与视觉认知方向（相关研究内容可参考Research中的”Compositional Scene Modeling and Object-Centric Learning“和”Abstract Visual Reasoning and Visual Cognition“）。在发送申请邮件之前，请先了解我相关方向的研究工作并在邮件中陈述你的见解。硕士生：对于申请2026秋入学的硕士生，欢迎对以下研究方向感兴趣的同学联系我：“AI+文博”内容生成、“AI+CAD”工业设计、3D场景重建与世界模型、智能文档处理（IDP）、多模态大模型与智能体相关应用研究。本科生：本课题组常年向本科生开放，欢迎AI相关专业的本科生加入！也欢迎文博、生医等专业的本科生加入进行AI交叉融合方面的研究！
News
2025-03: A textbook I co-edited (in Chinese "数据治理与认知安全") is published.
2023-06: A real-world dataset of tabletop scenes OCTScenes for benchmarking Object-Centric Learning is released online.
2023-06: Compositional Scene Representation Learning via Reconstruction: A Survey is published in IEEE TPAMI.
2022-06: A survey with a toolbox for Compositional Scene Representation Learning is released online.
2022-01: A technical report with a data collection for benchmarking Chinese text recognition is released online.
2021-05: A software package Dr.Hash -- Data Representation with Hashing Toolbox is released online.
2021-04: Bayesian Nonparametric Space Partitions: A Survey is published in IJCAI-21 Survey Track.
2021-01: A software package Sparti -- Spatial Partition Inference Toolbox is released online.
2020-09: A Review for Weighted MinHash Algorithms is published in IEEE TKDE.
Research
Some selected research topics are listed below. The full list of my publications can be found here.
Scene Text Recognition, Segmentation and Super-Resolution
Haiyang Yu, Teng Fu, Bin Li, Xiangyang Xue, EAFormer: Scene Text Segmentation with Edge-Aware Transformers, ECCV-24. [code]
Haiyang Yu, Jingye Chen, Bin Li, Xiangyang Xue, Chinese Character Recognition with Radical-Structured Stroke Trees, Machine Learning, 2024. [code]
Xinyan Zu, Haiyang Yu, Bin Li, Xiangyang Xue, Weakly-Supervised Text Instance Segmentation, MM-23. [code]
Haiyang Yu, Xiaocong Wang, Ke Niu, Bin Li, Xiangyang Xue, Scene Text Segmentation with Text-Focused Transformers, MM-23. [code]
Haiyang Yu, Xiaocong Wang, Bin Li, Xiangyang Xue, Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning, ICCV-23. [code]
Haiyang Yu, Xiaocong Wang, Bin Li, Xiangyang Xue, Orientation-Independent Chinese Text Recognition in Scene Images, IJCAI-23. [code]
Xinyan Zu, Haiyang Yu, Bin Li, Xiangyang Xue, Towards Accurate Video Text Spotting with Text-wise Semantic Reasoning, IJCAI-23. [code]
Xinyan Zu, Haiyang Yu, Bin Li, Xiangyang Xue, Chinese Character Recognition with Augmented Character Profile Matching, MM-22. [code]
Jingye Chen, Haiyang Yu, Jianqi Ma, Bin Li, Xiangyang Xue, Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution, AAAI-22. [code]
Jingye Chen, Bin Li, Xiangyang Xue, Zero-Shot Chinese Character Recognition with Stroke-Level Decomposition, IJCAI-21. [code]
Jingye Chen, Bin Li, Xiangyang Xue, Scene Text Telescope: Text-Focused Scene Image Super-Resolution, CVPR-21. [code]
Compositional Scene Modeling and Object-Centric Learning
Tonglin Chen, Yinxuan Huang, Jinghao Huang, Bin Li, Xiangyang Xue, Unsupervised Learning of Global Object-Centric Representations for Compositional Scene Understanding, IEEE TVCG, 2025. [code]
Tonglin Chen, Yinxuan Huang, Zhimeng Shen, Jinghao Huang, Bin Li, Xiangyang Xue, Learning Global Object-Centric Representations via Disentangled Slot Attention, Machine Learning, 2025. [code]
Yinxuan Huang, Chengmin Gao, Bin Li, Xiangyang Xue, Improving Viewpoint-Independent Object-Centric Representations through Active Viewpoint Selection, NeurIPS-24. [code]
Jinyang Yuan, Tonglin Chen, Zhimeng Shen, Bin Li, Xiangyang Xue, Unsupervised Object-Centric Learning from Multiple Unspecified Viewpoints, IEEE TPAMI, 2024. [code]
Tonglin Chen, Zhimeng Shen, Bin Li, Xiangyang Xue, Compositional Scene Modeling with Global Object-Centric Representations, Machine Learning, 2024. [code]
Jinyang Yuan, Tonglin Chen, Bin Li, Xiangyang Xue, Compositional Scene Representation Learning via Reconstruction: A Survey, IEEE TPAMI, 2023. [code]
Chengmin Gao, Bin Li, Time-Conditioned Generative Modeling of Object-Centric Representations for Video Decomposition and Prediction, UAI-23. [code]
Jinyang Yuan, Bin Li, Xiangyang Xue, Unsupervised Learning of Compositional Scene Representations from Multiple Unspecified Viewpoints, AAAI-22. [code]
Jinyang Yuan, Bin Li, Xiangyang Xue, Knowledge-Guided Object Discovery with Acquired Deep Impressions, AAAI-21. [code]
Jinyang Yuan, Bin Li, Xiangyang Xue, Generative Modeling of Infinite Occluded Objects for Compositional Scene Representation, ICML-19. [code]
Jinyang Yuan, Bin Li, Xiangyang Xue, Spatial Mixture Models with Learnable Deep Priors for Perceptual Grouping, AAAI-19. [code]
Abstract Visual Reasoning and Visual Cognition
Fan Shi, Bin Li, Xiangyang Xue, Abstracting Concept-Changing Rules for Solving Raven's Progressive Matrix Problems, IEEE TPAMI, 2026. [code]
Fan Shi, Bin Li, Xiangyang Xue, Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoning, ICML-25. [code]
Fan Shi, Bin Li, Xiangyang Xue, Towards Generative Abstract Reasoning: Completing Raven’s Progressive Matrix via Rule Abstraction and Selection, ICLR-24. [code]
Fan Shi, Bin Li, Xiangyang Xue, Compositional Law Parsing with Latent Random Functions, ICLR-23. [code]
Fan Shi, Bin Li, Xiangyang Xue, Raven's Progressive Matrices Completion with Latent Gaussian Process Priors, AAAI-21. [code]
Federated Learning and Privacy-Preserving Training
Mingzhao Yang, Shangchao Su, Bin Li, Xiangyang Xue, One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Models, ICML-25. [code]
Mingzhao Yang, Shangchao Su, Bin Li, Xiangyang Xue, FedDEO: Description-Enhanced One-Shot Federated Learning with Diffusion Models, MM-24. [code]
Shangchao Su, Bin Li, Xiangyang Xue, FedRA: A Random Allocation Strategy for Federated Tuning to Unleash the Power of Heterogeneous Clients, ECCV-24. [code]
Mingzhao Yang, Shangchao Su, Bin Li, Xiangyang Xue, Exploring One-Shot Semi-supervised Federated Learning with Pre-trained Diffusion Models, AAAI-24. [code]
Shangchao Su, Mingzhao Yang, Bin Li, Xiangyang Xue, Federated Adaptive Prompt Tuning for Multi-Domain Collaborative Learning, AAAI-24. [code]
Shangchao Su, Bin Li, Xiangyang Xue, One-shot Federated Learning without Server-side Training, Neural Networks, 2023. [code]
Bin Li, Mingmin Chi, Jianping Fan, Xiangyang Xue, Support Cluster Machine, ICML-07. [code]
Stochastic Partitions and Stochastic Point Processes
Xuhui Fan, Bin Li, Prosha A Rahman, Scott A. Sisson, Data-Dependent Rectangular Bounding Processes, IEEE TPAMI, 2026. [code]
Xuhui Fan, Yaqiong Li, Ling Chen, Bin Li, Scott A. Sisson, Hawkes Processes with Stochastic Exogenous Effects for Continuous-Time Interaction Modelling, IEEE TPAMI, 2023. [code]
Xuhui Fan, Bin Li, Feng Zhou, Scott A. Sisson, Continuous-Time Edge Modelling using Non-Parametric Point Processes, NeurIPS-21. [code]
Xuhui Fan, Bin Li, Yaqiong Li, Scott A. Sisson, Poisson-Randomised DirBNs: Large Mutation is Needed in Dirichlet Belief Networks, ICML-21. [code]
Xuhui Fan, Bin Li, Ling Luo, Scott A. Sisson, Bayesian Nonparametric Space Partitions: A Survey, IJCAI-21. [code]
Xuhui Fan, Bin Li, Scott A. Sisson, Online Binary Space Partitioning Forests, AISTATS-20. [code]
Xuhui Fan, Bin Li, Scott A. Sisson, Caoyuan Li, Ling Chen, Scalable Deep Generative Relational Models with High-Order Node Dependence, NeurIPS-19. [code]
Xuhui Fan, Bin Li, Scott A. Sisson, Binary Space Partitioning Forests, AISTATS-19. [code]
Xuhui Fan, Bin Li, Scott A. Sisson, Rectangular Bounding Process, NeurIPS-18. [code]
Xuhui Fan, Bin Li, Scott A. Sisson. The Binary Space Partitioning-Tree process, AISTATS-18. [code]
Xuhui Fan, Bin Li, Yi Wang, Yang Wang, Fang Chen, The Ostomachion Process, AAAI-16.
Yi Wang, Bin Li, Xuhui Fan, Yang Wang, Fang Chen, Bayesian Optimization of Partition Layouts for Mondrian Processes, IJCAI-16.
Yi Wang, Bin Li, Yang Wang, Fang Chen, Metadata Dependent Mondrian Processes, ICML-15.
Structured Data Representation with Recursive Hashing
Wei Wu, Bin Li, Chuan Luo, Wolfgang Nejdl, Xuan Tan, MPSketch: Message Passing Networks via Randomized Hashing for Efficient Attributed Network Embedding, IEEE TCYB, 2024. [code]
Wei Wu, Bin Li, Ling Chen, Junbin Gao, Chengqi Zhang, A Review for Weighted MinHash Algorithms, IEEE TKDE, 2022. [code]
Wei Wu, Bin Li, Chuan Luo, Wolfgang Nejdl, Hashing-Accelerated Graph Neural Networks for Link Prediction, WWW-21. [code]
Dingqi Yang, Paolo Rosso, Bin Li, Philippe Cudré-Mauroux, NodeSketch: Highly-Efficient Graph Embeddings via Recursive Sketching, KDD-19.
Wei Wu, Bin Li, Ling Chen, Chengqi Zhang, Philip S. Yu, Improved Consistent Weighted Sampling Revisited, IEEE TKDE, 2019. [code]
Dingqi Yang, Bin Li, Laura Rettig, Philippe Cudré-Mauroux, D2HistoSketch: Discriminative and Dynamic Similarity-Preserving Sketching of Streaming Histograms, IEEE TKDE, 2019.
Wei Wu, Bin Li, Ling Chen, Chengqi Zhang, Efficient Attributed Network Embedding via Recursive Randomized Hashing, IJCAI-18. [code]
Wei Wu, Bin Li, Ling Chen, Ling Chen, Xingquan Zhu, Chengqi Zhang, $K$-Ary Tree Hashing for Fast Graph Classification, IEEE TKDE, 2018. [code]
Dingqi Yang, Bin Li, Laura Rettig, Philippe Cudré-Mauroux, HistoSketch: Fast Similarity-Preserving Sketching of Streaming Histograms with Concept Drift, ICDM-17.
Wei Wu, Bin Li, Ling Chen, Chengqi Zhang, Consistent Weighted Sampling Made More Practical, WWW-17. [code]
Dingqi Yang, Bin Li, Philippe Cudré-Mauroux, POIsketch: Semantic Place Labeling over User Activity Streams, IJCAI-16.
Lianhua Chi, Bin Li, Xingquan Zhu, Context-Preserving Hashing for Fast Text Classification, SDM-14.
Bin Li, Xingquan Zhu, Lianhua Chi, Chengqi Zhang, Nested Subtree Hash Kernels for Large-scale Graph Classification over Streams, ICDM-12.
Collaborative Filtering and User Behaviour Modeling
Ling Luo, Bin Li, Xuhui Fan, Yang Wang, Irena Koprinska, Fang Chen, Dynamic Customer Segmentation via Hierarchical Fragmentation-Coagulation Processes, Machine Learning, 2023.
Ling Luo, Bin Li, Irena Koprinska, Shlomo Berkovsky, Fang Chen, Tracking the Evolution of Customer Purchase Behavior Segmentation via a Fragmentation-Coagulation Process, IJCAI-17.
Bin Li, Xingquan Zhu, Ruijiang Li, Chengqi Zhang, Rating Knowledge Sharing in Cross-Domain Collaborative Filtering, IEEE TCYB, 2015.
Bin Li, Xingquan Zhu, Ruijiang Li, Chengqi Zhang, Xiangyang Xue, XindongWu, Cross-Domain Collaborative Filtering over Time, IJCAI-11.
Ruijiang Li, Bin Li, Cheng Jin, Xiangyang Xue, Xingquan Zhu, Tracking User-Preference Varying Speed in Collaborative Filtering, AAAI-11.
Bin Li, Qiang Yang, Xiangyang Xue, Transfer Learning for Collaborative Filtering via a Rating-Matrix Generative Model, ICML-09.
Bin Li, Qiang Yang, Xiangyang Xue, Can Movies and Books Collaborate? Cross-Domain Collaborative Filtering for Sparsity Reduction, IJCAI-09.
Team
My current PhD students and some team alumni are listed below. I was external PhD supervisor at UTS, USyd and UNSW when I worked for NICTA/CSIRO in Australia.
Research Students
Xiaodong Ge (PhD'25 Student@Fudan) supervised 2025~Now.
Shuchun Liu (PhD'25 Student@Fudan) supervised 2025~Now.
Yuchuan Wu (PhD'24 Student@Fudan) supervised 2024~Now.
Teng Fu (PhD'23 Student@Fudan) co-supervised 2023~Now.
Yinxuan Huang (PhD'22 Student@Fudan) co-supervised 2023~Now.
Fan Shi (PhD'22/MSc'19 Student@Fudan) supervised 2019~Now.
Team Alumni
Haiyang Yu (PhD@Fudan) supervised 2020~2025 on Chinese Text Recognition. [National Scholarship]
Mingzhao Yang (PhD@Fudan) supervised 2020~2025 on One-Shot Federated Learning.
Tonglin Chen (PhD@Fudan) supervised 2018~2024 on Object-Centric Learning.
Shangchao Su (PhD@Fudan) supervised 2018~2024 on Federated Learning in Heterogeneous Scenarios.
Xinyan Zu (MEng@Fudan) supervised 2020~2023 on Chinese Text Recognition. [Shanghai Computer Society Outstanding Theses Award]
Jinyang Yuan (PhD@Fudan) co-supervised 2018~2022 on Compositional Scene Modeling.
Jingye Chen (MEng@Fudan) supervised 2019~2022 on Scene Text Recognition. [National Scholarship | Shanghai Computer Society Outstanding Theses Award]
Yaqiong Li (PhD@UTS) co-supervised 2017~2021 on Bayesian Dynamic Network Modeling.
Wei Wu (PhD@UTS) co-supervised 2015~2018 on Structured Data Hashing.
Ling Luo (PhD@USyd) co-supervised 2015~2017 on Temporal Behavior Modeling. [Google PhD Fellowship | Springer Theses]
Xuhui Fan (Postdoc@CSIRO) supervised 2015~2017 on Bayesian Nonparametric Space Partitions.
Yi Wang (PhD@UNSW) co-supervised 2014~2016 on Bayesian Nonparametric Clustering.
Lianhua Chi (PhD@UTS) co-supervised 2012~2015 on Structured Data Hashing.
Ruijiang Li (PhD@Fudan) co-supervised 2009~2013 on Bayesian Subspace Clustering.
Teaching
Mathematical Foundations of Artificial Intelligence (Undergraduate): 2023Fall, 2024Fall, 2025Fall
Statistical Learning (Undergraduate): 2020Fall, 2021Fall, 2022Fall, 2023Fall, 2024Fall
Big Data Analytics and Applications (Graduate): 2018Fall, 2019Fall, 2020Fall, 2021Fall, 2022Fall, 2024Spring, 2025Spring
Software
