About Me
Here is Xilie Xu (徐曦烈).
I am a third-year (Aug. 2021-present) Ph.D. student at the School of Computing of the National University of Singapore fortunately advised by Prof. Mohan Kankanhalli. Before that, I received my bachelor’s degree in Computer Science from Taishan College at Shandong University in 2021.
News
- [Apr 2024]: I will give a talk titled as "Towards Effective and Efficient Evaluation of Large Language Model's Adversarial Robustness" at N-CRiPT Technical Workshop, NUS.
- [Mar 2024]: I gave a talk titled as "An LLM can Fool Itself: A Prompt-Based Adversarial Attack" at N-CRiPT Seminar, NUS.
- [Feb 2024]: Our blog titled as ''Towards Robust Foundation Models: Adversarial Contrastive Learning'' was published at ICLR Blogposts 2024'!
- [Jan 2024]: Two papers---both AutoLoRa and PromptAttack, were accepted by ICLR'24! Congratulations to Keyi!
- [Dec 2023]: Our PromptAttack was accepted by AAAI'24 Workshop on Responsible Language Models!
- [Dec 2023]: I was invited as a reviewer for ICML'24.
- [Dec 2023]: I will attend NeurIPS 2023 conference at New Orleans, US. See you there! Welcome to check our Spotlight Poster and Poster!
- [Dec 2023]: I posted a tutorial to our NeruIPS'23 works regarding adversarial contrastive learning on 知乎 (Chinese Quora)! 欢迎大家关注点赞👍！An English version of the tutorial is here!
- [Nov 2023]: I gave a talk titled as "Towards Building Robust Foundation Models" at N-CRiPT Seminar, NUS.
- [Oct 2023]: We are glad to release RobustSSL Benchmark: a benchmark for robustness transferability of robust self-supervised learning (RobustSSL)!
- [Sep 2023]: Two papers regarding efficient and effective robust self-supervised pre-training were accepted by NeurIPS'23!
- [Sep 2023]: I was invited as a reviewer for ICLR'24.
- [Aug 2023]: I gave a talk titled as "Towards Effective and Efficient Self-Supervised Robust Pre-training" at AIGC’23, Shanghai, China.
- [Apr 2023]: I built the homepage of N-CRiPT Technical Workshop 2023 and presented a poster at the workshop.
- [Dec 2022]: I successfully passed the PhD Qualification Examination!
- [May 2022]: One paper regarding robustness of two-sample tests was accepted by ICML'22!