Yihan Wang
Hi, I am a Ph.D. candidate at UCLA in Computer Science, working with Prof. Cho-Jui Hsieh. I received my B.Eng. degree in Computer Science and Technology from Tsinghua University in June 2020. My research interest is machine learning, especially improving trustworthiness and generalization of machine learning models. I am currently supported by Amazon Fellowship.
For anyone interested in my research: Please feel free to email me if you are interested in a discussion on research or potential collaborations.
selected publications
* indicates equal contribution.
- Arxiv PreprintDefending LLMs against Jailbreaking Attacks via BacktranslationarXiv preprint arXiv:2402.16459, 2024
- TACLRed teaming language model detectors with language modelsTransactions of the Association for Computational Linguistics, 2024
- NeurIPS 2023Universality and limitations of prompt tuningAdvances in Neural Information Processing Systems, 2024
- ICLR 2024Two-stage LLM Fine-tuning with Less Specialization and More GeneralizationIn The Twelfth International Conference on Learning Representations , 2023
- ICLR 2022On the Convergence of Certified Robust Training with Interval Bound PropagationIn International Conference on Learning Representations , 2021
- NeurIPS 2021Fast certified robust training with short warmupAdvances in Neural Information Processing Systems, 2021
- ICML 2020On lp-norm robustness of ensemble decision stumps and treesIn International Conference on Machine Learning , 2020
- NeurIPS 2020Automatic perturbation analysis for scalable certified robustness and beyondAdvances in Neural Information Processing Systems, 2020