Xuhong Li

Researcher, Baidu

Joined

March 2017

Names

Xuhong Li (Preferred)

Xuhong LI

Emails

****@utc.fr (Confirmed)

****@baidu.com (Confirmed)

Personal Links

Google Scholar

DBLP

Career & Education History

Researcher

Baidu (baidu.com)

2019 – Present

PhD student

Heudiasyc, University of Technology of Compiègne, Université de technologie de Compiègne (hds.utc.fr)

2016 – 2019

Advisors, Relations & Conflicts

No relations added

Expertise

No areas of expertise listed

Publications

GiLOT: Interpreting Generative Language Models via Optimal Transport
Xuhong Li, Jiamin Chen, Yekun Chai, Haoyi Xiong
- ICML 2024 Poster
- Readers: Everyone
$\mathcal{M}^4$: A Unified XAI Benchmark for Faithfulness Evaluation of Feature Attribution Methods across Metrics, Modalities and Models
Xuhong Li, Mengnan Du, Jiamin Chen, Yekun Chai, Himabindu Lakkaraju, Haoyi Xiong
- NeurIPS 2023 Datasets and Benchmarks Poster
- Readers: Everyone
Beyond Intuition: Rethinking Token Attributions inside Transformers
Jiamin Chen, Xuhong Li, Lei Yu, Dejing Dou, Haoyi Xiong
- Accepted by TMLR
- Readers: Everyone
Explaining Information Flow Inside Vision Transformers Using Markov Chain
Tingyi Yuan, Xuhong Li, Haoyi Xiong, Hui Cao, Dejing Dou
- Published: 17 Oct 2021, Last Modified: 05 May 2023
- XAI 4 Debugging Workshop @ NEURIPS 2021 Oral
- Readers: Everyone
Interpretable Deep Learning: Interpretations, Interpretability, Trustworthiness, and Beyond
Xuhong Li, Haoyi Xiong, Xingjian Li, Xuanyu Wu, Xiao Zhang, Ji Liu, Jiang Bian, Dejing Dou
- 2021 (modified: 13 Nov 2024)
- CoRR 2021
- Readers: Everyone
Can We Use Gradient Norm as a Measure of Generalization Error for Model Selection in Practice?
Haozhe An, Haoyi Xiong, Xuhong Li, Xingjian Li, Dejing Dou, Zhanxing Zhu
- 28 Sept 2020 (modified: 05 May 2023)
- ICLR 2021 Conference Blind Submission
- Readers: Everyone
Implicit Regularization Effects of Unbiased Random Label Noises with SGD
Haoyi Xiong, Xuhong Li, Boyang Yu, Dejing Dou, Dongrui Wu, Zhanxing Zhu
- 28 Sept 2020 (modified: 05 May 2023)
- ICLR 2021 Conference Blind Submission
- Readers: Everyone
Democratizing Evaluation of Deep Model Interpretability through Consensus
Xuhong Li, Haoyi Xiong, Siyu Huang, Shilei Ji, Yanjie Fu, Dejing Dou
- 28 Sept 2020 (modified: 05 May 2023)
- ICLR 2021 Conference Blind Submission
- Readers: Everyone
Transfer learning in computer vision tasks: Remember where you come from
Xuhong Li, Yves Grandvalet, Franck Davoine, Jingchun Cheng, Yin Cui, Han Zhang, Serge J. Belongie, Yi-Hsuan Tsai, Ming-Hsuan Yang
- 2020 (modified: 21 Apr 2021)
- Image Vis. Comput. 2020
- Readers: Everyone
A baseline regularization scheme for transfer learning with convolutional neural networks
Xuhong Li, Yves Grandvalet, Franck Davoine
- 2020 (modified: 21 Apr 2021)
- Pattern Recognit. 2020
- Readers: Everyone

View all 12 publications

Co-Authors

View all 31 co-authors