![me.png](/assets/img/me.png?9361274b2b7ad11edef4e3b4e41a85ca)
Li Xiao (李潇)
Ph.D. student at the Department of Computer Science and Technology, Tsinghua University.
lixiao20@mails.tsinghua.edu.cn; xiaoli.cst@gmail.com
Google Scholar Github
I am looking for a full-time position in industry or academia. Feel free to reach out to me!
Affiliation:
Department of Computer Science and Technology,
State Key Laboratory of Intelligent Technology and Systems (CSAI),
Tsinghua University, Beijing 100084, China;
Tsinghua Laboratory of Brain and Intelligence (THBI);
IDG/McGovern Institute for Brain Research at Tsinghua.
I am a Ph.D. student at the Department of Computer Science and Technology in Tsinghua University, advised by Prof. Xiaolin Hu and Prof. Bo Zhang. I am a member of TSAIL Group, which is directed by Prof. Bo Zhang and Prof. Jun Zhu. I received my Bachelor’s degree at Department of Computer Science and Technology from Tsinghua University in 2020.
My research interests lie at the intersection of computer vision (CV) and machine learning (ML), with the goal of developing trustworthy multimodal computer vision systems that can achieve human‐level visual understanding and out-of-distribution (OOD) generalization. I have explored the following areas:
news
Aug 1, 2024 | We propose the ADBM model, which can significantly improves the robustness of visual models on OOD examples. We show theoretically and empirically that ADBM outperforms the original DDPM. This work is now available on arXiv. Read more |
---|---|
Jul 7, 2024 | We released the PartImageNet++ dataset and further improved the part-based recogntion models. The paper has been accepted by ECCV 2024. Read more |
Mar 18, 2024 | One paper on the relation between adversarial robustness and privacy is accepted by IEEE TIFS 2024. Read more |
Feb 26, 2024 | One paper on achiving zero-shot adversarial robustness with multimodal CLIP models is accepted by CVPR 2024. The proposed LAAT method uses language-driven anchors to guide adversarial training of vision models. Read more |
May 27, 2023 | One paper on how to improving robustness of object detectors with upstream adversarial pre-training is available on arXiv. Read more |
Jan 18, 2023 | One paper inspired by cognitive psychology theory is accepted by IEEE TPAMI 2023. The proposed ROCK method can significantly improve both adversarial robusntess and generalization on out-of-distribution examples. Read more |
Jul 14, 2022 | One paper is accepted by IJCV 2022, which is an extended version of the BPR paper. Read more |
Mar 1, 2021 | One paper on instance segmentatiion is accepted to CVPR 2021. The proposed BPR method reached 1st place on the Cityscapes leaderboard (instance segmentation track). Read more |
selected publications
2024
- ECCVPartImageNet++ Dataset: Scaling up Part-based Models for Robust RecognitionEuropean Conference on Computer Vision (ECCV), 2024
- arXivADBM: Adversarial diffusion bridge model for reliable adversarial purificationarXiv preprint arXiv:2408.00315, 2024
- CVPRLanguage-Driven Anchors for Zero-Shot Adversarial RobustnessIn IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
2023
- TPAMIRecognizing Object by Components With Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023