To be started from Fall 2025. Below are tentative schedules.
If you are interested to attend or present, feel free to drop me an email (see main page) at any time.
18 Aug 2025.
Learning with adversarial label noise via gradient methods. Presenter: Rita Adhikari.
To be scheduled:
Danny Halawi, Alex Wei, Eric Wallace, Tony Wang, Nika Haghtalab, and Jacob Steinhardt. Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation.