Aug 20, 2025 | Our work on LLM oversensitivity will appear in EMNLP Findings! |
Aug 08, 2025 | New on arXiv: LLM roleplay (yes, anime characters π) πβ¨ |
Jul 07, 2025 | Our paper on overthinking in reasoning models got accepted to COLM! |
Jun 16, 2025 | I start my internship at AWS, Santa Clara. |
Jun 10, 2025 | We will be giving a tutorial on multimodal generation evaluation at CVPR 2025 in Nashville πΆπ |
Apr 29, 2025 | Attending NAACL25 in Albuquerque! |
Apr 20, 2025 | New preprint on evaluating and mitigating overthinking is out! |
Jan 22, 2025 | Our paper on removing LLM watermarks has been accepted to NAACL main conference (β’Μα΄β’ ) |
Nov 22, 2024 | Presenting my poster at the SoCal NLP Symposium 2024 hosted at UCSD. |
Nov 10, 2024 | βοΈ to EMNLP Miami, welcome to chat! |
Nov 06, 2024 | New preprint is out! In this work we propose a new Black-Box Scrubbing Attack on LLM Watermarks. |
Oct 18, 2024 | Iβm attending the Responsible Machine Learning Summit 2024 |
Sep 20, 2024 | Our prompt compression paper is accepted to EMNLP-Findings! See you in Miamiβ±οΈ |
Sep 18, 2024 | βοΈ Flying to the US to start my PhD journey! π Excited for this new chapter and the adventures ahead. ππ |