Xuhong Li currently works at Baidu NLP group for ErnieBot (文心一言), the chat LLM of Baidu. Before that he was the scientific Researcher at Big Data Laboratory of Baidu Inc. He received his Ph.D degree from Heudiasyc, Univiersité de technologie de Compiègne in France, advised by Yves Grandvalet and Franck Davoine. He earned both his master and bachelor degrees from Beihang University, China. He is interested in and working on Explainable AI and Transfer Learning, as well as Self-Supervised Learning and Multi-Modal Learning, for both computer vision and natural language processing applications.
He is contributing to the open-source toolkit InterpretDL, which collects many mainstream XAI algorithms.
We are always looking for self-motivated interns. If you are interested in Data-Centric AI, LLM and RL, or other related topics, please drop me an email.
[ICML'24] +1 GiLOT: Interpreting Generative Language Models via Optimal Transport.
[NMI] +1 Multi-purpose RNA Language Modeling with Motif-aware Pre-training and Type-guided Fine-tuning.
[COLING'24] +1 HumanEval-XL: A Multilingual Code Generation Benchmark for Cross-lingual Natural Language Generalization.
[Neurips'23 D&B] +1
[ICDM'23] +1
[TMLR] +1
[AAAI'23] +1
[Artificial Intelligence] +1
[JMLR] +1
[MICCAI'22] +1
[ECML/ML Journal Track] +1
[KAIS] +2
[ML] +1
[ECCV'20] +1
[IVC] +1
[Pattern Recognition] +1
[ICML'18] +1
[IV'18] +1
子课题负责人,科技部 科技创新2030重大项目 (No. 2021ZD0110303), 2022.01--2024.12
[ICML’24] Xuhong Li, Jiamin Chen, Yekun Chai, Haoyi Xiong. GILOT: Interpreting Generative Language Models via Optimal Transport. ICML 2024. pdf|code.
[NeurIPS'23 D&B] Xuhong Li, Mengnan Du, Jiamin Chen, Yekun Chai, Himabindu Lakkaraju, Haoyi Xiong. "M4: A Unified XAI Benchmark for Faithfulness Evaluation of Feature Attribution Methods across Metrics, Modalities and Models." NeurIPS Datasets and Benchmarks track, 2023. forum|pdf|code.
[ICDM'23] Xuhong Li, Xuanyu Wu, Linghe Kong, Xiao Zhang, Siyu Huang, Dejing Dou, Haoyi Xiong. “ContRE: A Complementary Measure for Robustness Evaluation of Deep Networks via Contrastive Examples.” IEEE International Conference on Data Mining 2023. pdf|[code].
[TMLR] Jiamin Chen, Xuhong Li, Lei Yu, Dejing Dou, Haoyi Xiong. “Beyond Intuition: Rethinking Token Attributions inside Transformers.” TMLR. forum|pdf|code.
[AAAI'23] Qingrui Jia, Xuhong Li, Lei Yu, Penghao Zhao, Jiang Bian, Shupeng Li, Haoyi Xiong, Dejing Dou. "Learning from Training Dynamics: Identifying Mislabeled Data Beyond Manually Designed Features". AAAI 2023. pdf|code.
[Artificial IntelligenceI] Xuhong Li, Haoyi Xiong, Xingjian Li, Xiao Zhang, Ji Liu, Haiyan Jiang, Zeyu Chen, Dejing Dou. "G-LIME: Statistical Learning for Local Interpretations of Deep Neural Networks using Global Priors." Artificial Intelligence, 2023. pdf|code.
[JMLR] Xuhong Li, Haoyi Xiong, Xingjian Li, Xuanyu Wu, Zeyu Chen, and Dejing Dou. "InterpretDL: Explaining Deep Models in PaddlePaddle." Journal of Machine Learning Research, 2022. pdf|code.
[MICCAI'22] Weibin Liao, Haoyi Xiong, Qingzhong Wang, Yan Mo, Xuhong Li, Yi Liu, Zeyu Chen, Siyu Huang, and Dejing Dou. "MUSCLE: Multi-task Self-supervised Continual Learning to Pre-train Deep Models for X-ray Images of Multiple Body Parts." Medical Image Computing and Computer Assisted Interventions, 2022. pdf.
[ECML'22/ML Journal Track] Xuhong Li, Haoyi Xiong, Siyu Huang, Shilei Ji and Dejing Dou. "Cross-model consensus of explanations and beyond for image classification models: An empirical study." Machine Learning Journal (for European Conference on Machine Learning 2022 journal track). pdf|code|dataset.
[KAIS] Xuhong Li, Haoyi Xiong, Xingjian Li, Xuanyu Wu, Xiao Zhang, Jiang Bian, and Dejing Dou. "Interpretable Deep Learning: Interpretations, Interpretability, Trustworthiness, and Beyond." Knowledge and Information Systems, 2022, Springer. pdf.
[ML] Xuhong Li, Haoyi Xiong, Yi Liu, Dingfu Zhou, Zeyu Chen, Yaqing Wang, and Dejing Dou. "Distilling Ensemble of Explanations for Weakly-Supervised Pre-Training of Image Segmentation Models." Machine Learning, 2022, Springer. pdf|code|dataset.
[ECCV'20] Di Hu, Xuhong Li, Lichao Mou, Pu Jin, Dong Chen, Liping Jing, Xiaoxiang Zhu, Dejing Dou. "Cross-Task Transfer for Geotagged Audiovisual Aerial Scene Recognition." ECCV, 2020. pdf|code|dataset.
[ICML'18] Xuhong Li, Yves Grandvalet, Franck Davoine. "Explicit inductive bias for transfer learning with convolutional networks." ICML, 2018. pdf|code.