Publications

*: Equal contribution or alphabetic ordering.
†: Corresponding author.

Conference Papers

• Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models.
  Lai Wei*, Zhiquan Tan*, Chenghai Li, Jindong Wang, Weiran Huang†.
  Conference on Neural Information Processing Systems (NeurIPS), 2024.
  [code] [slides] [知乎]

• SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models.
  Linglan Zhao*, Xuerui Zhang*, Ke Yan†, Shouhong Ding, Weiran Huang†.
  Conference on Neural Information Processing Systems (NeurIPS), 2024.

• AutoEval-Video: An Automatic Benchmark for Assessing Large Vision Language Models in Open-Ended Video Question Answering.
  Xiuyuan Chen, Yuan Lin†, Yuchen Zhang†, Weiran Huang†.
  European Conference on Computer Vision (ECCV), 2024.
  [code] [知乎]

• Provable Contrastive Continual Learning.
  Yichen Wen*, Zhiquan Tan*, Kaipeng Zheng, Chuanlong Xie, Weiran Huang†.
  International Conference on Machine Learning (ICML), 2024.
  [知乎]

• OTMatch: Improving Semi-Supervised Learning with Optimal Transport.
  Zhiquan Tan, Kaipeng Zheng, Weiran Huang†.
  International Conference on Machine Learning (ICML), 2024.

• Unveiling the Dynamics of Information Interplay in Supervised Learning.
  Kun Song*, Zhiquan Tan*, Bochao Zou, Huimin Ma†, Weiran Huang†.
  International Conference on Machine Learning (ICML), 2024.
  [知乎]

• A Statistical Theory of Regularization-Based Continual Learning.
  Xuyang Zhao, Huiyuan Wang, Weiran Huang†, Wei Lin†.
  International Conference on Machine Learning (ICML), 2024.

• Information Flow in Self-Supervised Learning.
  Zhiquan Tan, Jingqin Yang, Weiran Huang, Yang Yuan, Yifan Zhang.
  International Conference on Machine Learning (ICML), 2024.
  [code]

• Matrix Information Theory for Self-Supervised Learning.
  Yifan Zhang*, Zhiquan Tan*, Jingqin Yang*, Weiran Huang, Yang Yuan.
  International Conference on Machine Learning (ICML), 2024.

• TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones.
  Zhengqing Yuan, Zhaoxu Li, Weiran Huang, Yanfang Ye, Lichao Sun.
  ICML 2024 Workshop on Advancing Neural Network Training (ICML Workshop), 2024.

• DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation.
  Kaipeng Zheng, Huishuai Zhang, Weiran Huang†.
  Conference on Neural Information Processing Systems (NeurIPS), 2023.
  [code] [知乎]

• FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning.
  Kun Song, Huimin Ma†, Bochao Zou, Huishuai Zhang, Weiran Huang†.
  Conference on Neural Information Processing Systems (NeurIPS), 2023.
  [code] [知乎]

• When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method. (Oral, Top 1.8%)
  Manyi Zhang*, Xuyang Zhao*, Jun Yao, Chun Yuan†, Weiran Huang†.
  International Conference on Computer Vision (ICCV), 2023. (Best Paper Finalist, Top 0.2%)

• Rethinking Weak Supervision in Helping Contrastive Representation Learning.
  Jingyi Cui*, Weiran Huang*, Yifei Wang*, Yisen Wang.
  International Conference on Machine Learning (ICML), 2023.

• Towards the Generalization of Contrastive Self-Supervised Learning.
  Weiran Huang*†, Mingyang Yi*, Xuyang Zhao*, Zihao Jiang.
  International Conference on Learning Representations (ICLR), 2023.
  [code] [slides] [知乎]

• ArCL: Enhancing Contrastive Learning with Augmentation-Robust Representations.
  Xuyang Zhao*, Tianqi Du*, Yisen Wang, Jun Yao, Weiran Huang†.
  International Conference on Learning Representations (ICLR), 2023.

• Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embedding.
  Tianyang Hu, Zhili Liu, Fengwei Zhou, Wenjia Wang, Weiran Huang†.
  International Conference on Learning Representations (ICLR), 2023.
  [code]

• AggNCE: Asymptotically Identifiable Contrastive Learning. (Oral, Top 5.6%)
  Jingyi Cui*, Weiran Huang*, Yifei Wang, Yisen Wang.
  NeurIPS 2022 Workshop on Self-Supervised Learning Theory and Practice (NeurIPS Workshop), 2022.
  [video]

• Variational Energy-Based Models: A Probabilistic Framework for Contrastive Self-Supervised Learning.
  Tianqi Du*, Yifei Wang*, Weiran Huang, Yisen Wang.
  NeurIPS 2022 Workshop on Self-Supervised Learning Theory and Practice (NeurIPS Workshop), 2022.

• Can Pretext-Based Self-Supervised Learning Be Boosted by Downstream Data? A Theoretical Analysis.
  Jiaye Teng*, Weiran Huang*†, Haowei He*.
  International Conference on Artificial Intelligence and Statistics (AISTATS), 2022.
  [slides] [poster] [video] [知乎] [B 站]

• Locally Differentially Private (Contextual) Bandits Learning.
  Kai Zheng, Tianle Cai, Weiran Huang, Zhenguo Li, Liwei Wang.
  Conference on Neural Information Processing Systems (NeurIPS), 2020.
  [code] [video] [知乎]

• Boosting Few-Shot Learning with Adaptive Margin Loss.
  Aoxue Li, Weiran Huang, Xu Lan, Jiashi Feng, Zhenguo Li, Liwei Wang.
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
  [slides] [patent] [知乎]

• Few-Shot Learning with Global Class Representations.
  Aoxue Li, Tiange Luo, Tao Xiang, Weiran Huang, Liwei Wang.
  International Conference on Computer Vision (ICCV), 2019.
  [code] [poster] [patent] [知乎]

• Community Exploration: From Offline Optimization to Online Learning.
  Xiaowei Chen, Weiran Huang, Wei Chen, John C.S. Lui.
  Conference on Neural Information Processing Systems (NeurIPS), 2018.
  [poster]

• Multi-Round Influence Maximization. (Oral, Top 10.9%)
  Lichao Sun, Weiran Huang, Philip S. Yu, Wei Chen.
  ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2018.
  

Preprints and Manuscripts

• InstructionGPT-4: A 200-Instruction Paradigm for Fine-Tuning MiniGPT-4.
  Lai Wei, Zihao Jiang, Weiran Huang†, Lichao Sun.
  [200 selected data] [机器之心]