Le Gan

Le Gan

Nanjing University

Le Gan is an associate researcher in the department of computer science and technology at the Nanjing University (NJU). Le received his Ph.D. degree from Nanjing University, China in August 2018. After that, he became an assistant researcher in the department of computer science and technology of Nanjing University.

News

  • 2023.09: 1 papers have been accepted by NeurIPS 2023.

Publications [Google Scholar] [DBLP]

Conference Publications

  • Hai-Long Sun, Da-Wei Zhou, Hanbin Zhao, Le Gan, De-Chuan Zhan, Han-Jia Ye. MOS: Model Surgery for Pre-Trained Model-Based Class-Incremental Learning, In: Proceedings of the 39th AAAI Conference on Artificial Intelligence (AAAI’25, CCF-A), Pennsylvania, USA, 2025.
  • Kaichen Huang, Minghao Shao, Shenghua Wan, Hai-Hang Sun, Le Gan, Shuai Feng, De-Chuan Zhan. Leveraging Separated World Model for Exploration in Visually Distracted Environments, In: Advances in Neural Information Processing Systems 37 (NeurIPS’24, CCF-A), Vancouver, Canada, 2024.
  • Yichu Xu, Xin-Chun Li, Le Gan, De-Chuan Zhan. Weight Scope Alignment: A Frustratingly Easy Method for Model Merging, In: Proceedings of the 27th European Conference on Artificial Intelligence(ECAI’24, CCF-B), Santiago de Compostela, 2024.
  • Wen-Shu Fan, Su Lu, Xin-Chun Li, De-Chuan Zhan, Le Gan. Revisit the Essence of Distilling Knowledge through Calibration, In: Proceedings of the 41th International Conference on Machine Learning (ICML’24, CCF-A), Vienna, Austria, 2024.
  • Yucen Wang, Shenghua Wan, Le Gan, Shuai Feng, De-Chuan Zhan. AD3: Implicit Action is the Key for World Models to Distinguish the Diverse Visual Distractors. [Paper], In: Proceedings of the 41th International Conference on Machine Learning (ICML’24, CCF-A), Vienna, Austria, 2024.
  • Shenghua Wan, Ziyuan Chen, Le Gan, Shuai Feng, De-Chuan Zhan. SeMOPO: Learning High-quality Model and Policy from Low-quality Offline Visual Datasets, In: Proceedings of the 41th International Conference on Machine Learning (ICML’24, CCF-A), Vienna, Austria, 2024.
  • Shenghua Wan, Hai-Hang Sun, Le Gan, De-Chuan Zhan. MOSER: Learning Sensory Policy for Task-specific Viewpoint via View-conditional World Model, In: Proceedings of the 33th International Joint Conference on Artificial Intelligence (IJCAI’24, CCF-A), Jeju, Korea, 2024.

  • Jia-Qi Yang, De-Chuan Zhan, Le Gan. Beyond Probability Partitions: Calibrating Neural Networks with Semantic Aware Grouping, In: Advances in Neural Information Processing Systems 36 (NeurIPS’23, CCF-A), New Orleans, LA, 2023. [Paper]

  • Xin-Chun Li , Yan-Jia Wang, Le Gan, De-Chuan Zhan. Exploring Transferability Measures and Domain Selection in Cross-Domain Slot Filling. In: Proceedings of the 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP’22, CCF-B), Virtual, Singapore, 2022. [Paper]

  • Xin-Chun Li, Jin-Lin Tang, Shaoming Song, Bingshuai Li, Yinchuan Li, Yunfeng Shao, Le Gan, De-Chuan Zhan. Avoid Overfitting User Specific Information in Federated Keyword Spotting. In: Proceedings of the 2022 Conference of the International Speech Communication Association (Interspeech’22, CCF-C), Incheon, Korea. 2022. [Paper] [code]

  • Su Lu, Han-Jia Ye, Le Gan, De-Chuan Zhan. Towards Enabling Meta-Learning from Target Models. In: Advances in Neural Information Processing Systems 34 (NeurIPS’21, CCF-A), Virtual, 2021. [Paper] [code]

Journal Publications

Preprints

  • Kaichen Huang, Minghao Shao, Shenghua Wan, Hai-Hang Sun, Shuai Feng, Le Gan, De-Chuan Zhan. SENSOR: SENSOR: Imitate Third-Person Expert’s Behaviors via Active Sensoring.[Paper]
  • Kaichen Huang, Hai-Hang Sun, Shenghua Wan, Minghao Shao, Shuai Feng, Le Gan, De-Chuan Zhan. DIDA: Denoised Imitation Learning based on Domain Adaptation. [Paper]

Correspondence

  • Email: ganle@nju.edu.cn; ganleatlas@gmail.com
  • Office: Room A201, Yi-fu Building, Xianlin Campus of Nanjing University
  • Address: National Key Laboratory for Novel Software Technology, Nanjing University, Xianlin Campus Mailbox 603, 163 Xianlin Avenue, Qixia District, Nanjing 210023, China