news
| Jul 07, 2025 |  My first-author paper LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks accepted in COLM 2025 ! |
|---|---|
| Jun 25, 2025 | Excited to serve as a volunteer for ICML 2025! |
| Jun 10, 2025 | A short version of my first-author paper Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs accepted as an oral an MUGen @ ICML'25 ! This is an exciting work in progress 🤩 |
| Jun 02, 2025 | 🤩 I am starting a summer internship as a Computing Scholar Intern at Lawrence Livermore National Laboratory. |
| Apr 17, 2025 | Our paper Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning accepted in ICML 2025 ! |