Ph.D. Student

CS department, University of Wisconsin-Madison (UW-Madison)

xdu66 (at) wisc.edu, xuefengdu1 (at) gmail.com

Google Scholar | LinkedIn Twitter Github [CV] [Research Statement] [Teaching Statement] [Diversity Statement]

Hi! I am a fifth-year CS Ph.D. student at UW-Madison advised by Prof. Sharon Yixuan Li. Previously, I was an undergraduate student at Xi'an Jiaotong University (XJTU) majoring in electronic engineering.
My current research focus is to develop theory and algorithms for reliable machine learning, foundation model reliability, and related applications, specifically I work on:

• Out-of-distribution (OOD) research: designing adaptive and interpretable learning algorithms that help ML models detect and generalize on OOD samples, such as semantic/covariate shifts, adversarial and noisy samples.
• Reliability of foundation models: understanding the blindspots of LLMs and VLMs for improved safeguarding efforts, such as model hallucination and harmful prompt detection.
• Applications: Graph embedding, object detection and segmentation.
• Interdisciplinary research: Biometrics, AI-aided cryo-microscopy/protein structural analysis.

[9/25/2024] One paper on LLM hallucination is accepted to NeurIPS 2024 as spotlight presentation.

[9/9/2024] Honored to get selected as Rising Stars in Data Science 2024 (worldwide 30 recipients)!

[6/10/2024] Start my internship in Microsoft Research Redmond working on VLM reliability!

[5/1/2024] One paper is accepted to ICML 2024.

[1/16/2024] One paper is accepted to ICLR 2024.

[2/11/2023] Received the Jane Street Graduate Research Fellowship (6 selected out of 600).

[3/1/2022] One paper is accepted to CVPR 2022 as oral presentation.

[1/15/2021] Join UW-Madison as a PhD student!!

• Research Intern. 2024.06 - 2024.09
  Microsoft Inc.
  Manager: Robert Sim , Jay Stokes, Ahmed Salem, Reshmi Ghosh
• Student Researcher. 2022.05 - 2022.09
  Google Inc.
  Manager: Zizhao Zhang, Ting Chen, Han Zhang
• Research Intern. 2021.03 - 2021.07
  Tencent AI Lab
  Manager: Yu Rong, Junzhou Huang
• Research Assistant. 2020.10 - 2021.02
  Hong Kong Baptist University
  Manager: Bo Han
• Research Engineer Intern. 2020.08 - 2020.09
  Bytedance AI Lab
  Manager: Changhu Wang
• Research Intern. 2019.11 - 2020.07
  AI Theory Group, Noah’s Ark Lab
  Manager: Hang Xu, Chenhan Jiang
• Student Intern. 2018.07 - 2020.01
  Carneige Mellon University
  Manager: Min Xu, Haohan Wang

• Ph.D. in CS. 2020 - 2025 (Expected)
  University of Wisconsin–Madison (UW-Madison), Madison, WI, USA
• B.Eng. in electronic engineering 2016 - 2020
  Xi'an Jiaotong university (XJTU), Xi'an, China

You can also browse my Google Scholar profile. I publish under the name "Xuefeng Du".

1. HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection
   Xuefeng Du, Chaowei Xiao, Yixuan Li.
   NeurIPS 2024.(Spotlight)
   [PDF][Code]
2. Exploring Transition States of Protein Conformational Changes via Out-of-Distribution Detection in the Hyperspherical Latent Space
   Bojun Liu, Jordan G Boysen, Ilona Christy Unarta, Xuefeng Du, Yixuan Li, Xuhui Huang.
   Nature Communications.
   [PDF][Code]
3. Safety-Aware Fine-Tuning of Large Language Models
   Hyeong Kyu Choi, Xuefeng Du, Yixuan Li.
   NeurIPS 2024 Safe Generative AI Workshop.
   [PDF][Code]
4. How Reliable Is Human Feedback For Aligning Large Language Models?
   Min-Hsuan Yeh, Leitian Tao, Jeffrey Wang, Xuefeng Du, Yixuan Li.
   Manuscript 2024.
   [PDF][Code]
5. VLMGuard: Defending VLMs against Malicious Prompts via Unlabeled Data
   Xuefeng Du, Reshmi Ghosh, Robert Sim, Ahmed Salem, Vitor Carvalho, Emily Lawton, Yixuan Li, Jack W. Stokes.
   Manuscript 2024.
   [PDF][Code]
6. The Ghanaian NLP Landscape: A First Look
   Sheriff Issaka, Zhaoyi Zhang, Mihir Heda, Keyi Wang, Yinka Ajibola, Ryan DeMar, Xuefeng Du.
   Manuscript 2024.
   [PDF][Code]
7. Out-of-Distribution Learning with Human Feedback
   Haoyue Bai, Xuefeng Du, Katie Rainey, Shibin Parameswaran, Yixuan Li.
   Manuscript 2024.
   [PDF][Code]
8. When and How Does In-Distribution Label Help Out-of-Distribution Detection?
   Xuefeng Du, Yiyou sun, Yixuan Li.
   ICML 2024 (Poster)
   [PDF][Code]
9. How Does Unlabeled Data Provably Help Out-of-distribution Detection?
   *Xuefeng Du*, *Zhen Fang*, Ilias Diakonikolas, Yixuan Li.
   ICLR 2024 (Poster)
   [PDF] [Code]
10. Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection
    Haoyue Bai, Gregory Canal, Xuefeng Du, Jeongyeol Kwon, Robert D Nowak, Yixuan Li.
    ICML 2023 (Poster)
    [PDF][Code]
11. Dream the Impossible: Outlier Imagination with Diffusion Models
    Xuefeng Du, Yiyou Sun, Xiaojin Zhu, Yixuan Li.
    NeurIPS 2023 (Poster)
    [PDF][Code]
12. Openood v1. 5: Enhanced benchmark for out-of-distribution detection.
    Jingyang Zhang, Jingkang Yang, Pengyun Wang, Haoqi Wang, Yueqian Lin, Haoran Zhang, Yiyou Sun, Xuefeng Du, Kaiyang Zhou, Wayne Zhang, Yixuan Li, Ziwei Liu, Yiran Chen, Hai Li.
    NeurIPS 2023, DistShift Workshop
    [PDF][Code]
13. Non-parametric Outlier Synthesis
    Leitian Tao, Xuefeng Du, Jerry Zhu, Yixuan Li.
    ICLR 2023 (Poster)
    [PDF][Code]
14. Noise-robust Graph Learning by Estimating and Leveraging Pairwise Interactions
    Xuefeng Du, Tian Bian, Yu Rong, Bo Han, Tongliang Liu, Tingyang Xu, Wenbing Huang, Yixuan Li, Junzhou Huang.
    Transactions on Machine Learning Research (TMLR) 2023
    [PDF][Code]
15. SIREN: Shaping Representations for Detecting Out-of-distribution Objects
    Xuefeng Du, Gabriel Gozum, Yifei Ming, Yixuan Li.
    NeurIPS 2022 (Poster)
    [PDF][Code]
16. OpenOOD: Benchmarking Generalized Out-of-Distribution Detection.
    Jingkang Yang, Pengyun Wang, Dejian Zou, Zitang Zhou, Kunyuan Ding, Wenxuan Peng, Haoqi Wang, Guangyao Chen, Bo Li, Yiyou Sun, Xuefeng Du, Kaiyang Zhou, Wayne Zhang, Dan Hendrycks, Yixuan Li, Ziwei Liu.
    NeurIPS 2022, Datasets and Benchmarks Track
    [PDF][Code]
17. Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wild.
    Xuefeng Du, Xin Wang, Gabriel Gozum, Yixuan Li.
    CVPR 2022 (Oral)
    [PDF] [Code]
18. VOS: Learning What You Don’t Know by Virtual Outliers Synthesis.
    Xuefeng Du, Eric Wang, Mu Cai, Yixuan Li.
    ICLR 2022 (Poster)
    [PDF] [Code]
19. Performance-Aware Mutual Knowledge Distillation for Improving Neural Architecture Search.
    Pengtao Xie, Xuefeng Du.
    CVPR 2022 (Poster)
    [PDF][Code]
20. Learning Diverse-Structured Networks for Adversarial Robustness.
    Xuefeng Du, Jingfeng Zhang, Bo Han, Tongliang Liu, Yu Rong, Gang Niu, Junzhou Huang, Masashi Sugiyama.
    ICML 2021 (Poster)
    [PDF][Code]
21. Active learning to classify macromolecular structures in situ for less supervision in cryo-electron tomography.
    Xuefeng Du, Haohan Wang, Zhenxi Zhu, Xiangrui Zeng, Yi-Wei Chang, Jing Zhang, Min Xu.
    Bioinformatics
    [PDF][Code]
22. How to save your annotation cost for Panoptic Segmentation?.
    Xuefeng Du, Chenhan Jiang, Hang Xu, Gengwei Zhang, Zhenguo Li.
    AAAI 2021 (Poster)
    [PDF][Code]
23. Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embedding.
    Lin Lan, Pinghui Wang, Xuefeng Du, Kaikai Song, Jing Tao, Xiaohong Guan.
    NeurIPS 2020 (Poster)
    [PDF] [Code]
24. Learning by Passing Tests, with Application to Neural Architecture Search.
    Xuefeng Du, Pengtao Xie.
    arXiv preprint arXiv:2011.15102
    [PDF]
25. Skillearn: Machine Learning Inspired by Humans' Learning Skills.
    Pengtao Xie, Xuefeng Du, Hao Ban.
    arXiv preprint arXiv:2012.04863
    [PDF]
26. Small-Group Learning, with Application to Neural Architecture Search.
    Xuefeng Du, Pengtao Xie.
    arXiv preprint arXiv:2012.12502
    [PDF]
27. A deep biometric hash learning framework for three advanced hand‐based biometrics.
    Huikai Shao, Dexing Zhong, Xuefeng Du.
    IET Biometrics
    [PDF]
28. Few-shot learning for palmprint recognition via meta-siamese network.
    Huikai Shao, Dexing Zhong, Xuefeng Du, Shaoyi Du, Raymond NJ Veldhuis.
    IEEE transactions on instrumentation and measurement
    [PDF]
29. Deep distillation hashing for unconstrained palmprint recognition.
    Huikai Shao, Dexing Zhong, Xuefeng Du.
    IEEE transactions on instrumentation and measurement
    [PDF] [Code]
30. Cross-domain palmprint recognition via regularized adversarial domain adaptive hashing.
    Xuefeng Du, Dexing Zhong, Huikai Shao.
    IEEE Transactions on Circuits and Systems for Video Technology
    [PDF]
31. Towards efficient unconstrained palmprint recognition via deep distillation hashing.
    Huikai Shao, Dexing Zhong, Xuefeng Du.
    Manuscript 2020.
    [PDF]
32. Effective deep ensemble hashing for open-set palmprint recognition.
    Huikai Shao, Dexing Zhong, Xuefeng Du.
    Journal of Electronic Imaging.
    [PDF]
33. Cross-domain palmprint recognition based on transfer convolutional autoencoder.
    Huikai Shao, Dexing Zhong, Xuefeng Du.
    IEEE International Conference on Image Processing 2019.
    [PDF]
34. Building an active palmprint recognition system.
    Xuefeng Du, Dexing Zhong, Huikai Shao.
    IEEE International Conference on Image Processing 2019.
    [PDF]
35. Continual palmprint recognition without forgetting.
    Xuefeng Du, Dexing Zhong, Huikai Shao.
    IEEE International Conference on Image Processing 2019.
    [PDF] [Code]
36. Low-shot palmprint recognition based on meta-siamese network.
    Xuefeng Du, Dexing Zhong, Pengna Li.
    IEEE International Conference on Multimedia and Expo 2019.
    [PDF]
37. A hand-based multi-biometrics via deep hashing network and biometric graph matching.
    Dexing Zhong, Huikai Shao, Xuefeng Du.
    IEEE Transactions on Information Forensics and Security.
    [PDF]
38. Decade progress of palmprint recognition: A brief survey.
    Dexing Zhong, Xuefeng Du, Kuncai Zhong.
    Neurocomputing.
    [PDF]
39. Classification in cryo-electron tomograms.
    Ilja Gubins, Gijs van der Schot, Remco C Veltkamp, Friedrich Forster, Xuefeng Du, Xiangrui Zeng, Zhenxi Zhu, Lufan Chang, Min Xu, Emmanuel Moebel, Antonio Martinez-Sanchez, Charles Kervrann, Tuan M Lai, Xusi Han, Genki Terashi, Daisuke Kihara, Benjamin A Himes, Xiaohua Wan, Jingrong Zhang, Shan Gao, Yu Hao, Zhilong Lv, Xiaohua Wan, Zhidong Yang, Zijun Ding, Xuefeng Cui, Fa Zhang.
    Eurographics 2019.
    [PDF]
40. Semi-supervised Macromolecule Structural Classification in Cellular Electron Cryo-Tomograms using 3D Autoencoding Classifier.
    Siyuan Liu, Xuefeng Du,, Rong Xi, Fuya Xu, Xiangrui Zeng, Bo Zhou, Min Xu.
    BMVC 2019.
    [PDF]
41. Efficient deep palmprint recognition via distilled hashing coding.
    Huikai Shao, Dexing Zhong, Xuefeng Du.
    CVPR Workshop 2019.
    [PDF]
42. Open-set Recognition of Unseen Macromolecules in Cellular Electron Cryo-Tomograms by Soft Large Margin Centralized Cosine Loss.
    Xuefeng Du, Xiangrui Zeng, Bo Zhou, Alex Singh, Min Xu.
    BMVC 2019.
    [PDF]
43. Palm vein recognition with deep hashing network.
    Dexing Zhong, Shuming Liu, Wenting Wang, Xuefeng Du.
    Pattern Recognition and Computer Vision 2019.
    [PDF]
44. Palmprint recognition using siamese network.
    Dexing Zhong, Yuan Yang, Xuefeng Du.
    13th Conference of Biometric Recognition, CCBR 2018.
    [PDF]