Angelica Chen

Logo

angelica[dot]chen[at]nyu.edu

View My GitHub Profile

Selected Papers | Invited Talks | Google Scholar | Twitter

Hi! I’m a senior research scientist at Google DeepMind, currently working on Gemini training algorithms. My research broadly focuses on reinforcement learning algorithms, LLM training dynamics (both pre-training and post-training), and recursive self-improvement. I am also interested in the application of LLMs to biomedical fields, including both drug design and hospital decision-making. Before DeepMind, I completed my PhD at NYU in the Machine Learning for Language group, where I was fortunate to be advised by Kyunghyun Cho. I have also previously worked or interned for Google Brain, Meta FAIR, and Prescient Design at Genentech.

Outside of my research, I enjoy running, thrift flipping, and baking more pastries than I can feasibly eat. I also volunteer as a NYSDOH-certified rape and domestic violence crisis counselor/victim advocate for the NYC Crime Victims Treatment Center at local hospital EDs, and work with the NYC chapter of the DSA.

News

Selected Papers

My work is largely split into three general directions – improving how LLMs learn from feedback, understanding LLM training, and the application of LLMs to biomedical settings. For a more complete list of my papers, please see Semantic Scholar.

Improving How LLMs Learn From Feedback

EvoPrompting: Language Models for Code-Level Neural Architecture Search
NeurIPS 2023
Chen, Angelica, David M. Dohan and David R. So
[OpenReview] [Arxiv]

Learning from Natural Language Feedback
Transactions on Machine Learning Research (2024)
Chen, Angelica*, Jérémy Scheurer*, Tomasz Korbak, Jon Ander Campos, Jun Shern Chan, Samuel R. Bowman, Kyunghyun Cho, Ethan Perez
[OpenReview] [GitHub]

Pretraining Language Models with Human Preferences
ICML 2023 (oral)
Korbak, Tomasz, Kejian Shi, Angelica Chen, Rasika Bhalerao, Christopher L. Buckley, Jason Phang, Sam Bowman and Ethan Perez
[Arxiv]

Diverse Preference Optimization
Jack Lanchantin, Angelica Chen, Shehzaad Dhuliawala, Ping Yu, Jason Weston, Sainbayar Sukhbaatar, Ilia Kulikov
[Arxiv]

Understanding LLM Training

Preference Learning Algorithms Do Not Learn Preference Rankings
NeurIPS 2024
Oral at ICML 2024 Workshop on Models of Human Feedback for AI Alignment (MHFAIA)
Chen, Angelica, Sadhika Malladi, Lily H. Zhang, Xinyi Chen, Qiuyi Zhang, Rajesh Ranganath, Kyunghyun Cho.
[Arxiv] [GitHub]

Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs
ICLR 2024 (Spotlight)
Chen, Angelica, Ravid Shwartz-Ziv, Kyunghyun Cho, Matthew L. Leavitt, Naomi Saphra.
[OpenReview] [Arxiv] [GitHub]

Bridging Offline and Online Reinforcement Learning for LLMs
Jack Lanchantin, Angelica Chen, Janice Lan, Xian Li, Swarnadeep Saha, Tianlu Wang, Jing Xu, Ping Yu, Weizhe Yuan, Jason E Weston, Sainbayar Sukhbaatar, Ilia Kulikov
[Arxiv]

Latent State Models of Training Dynamics
Transactions on Machine Learning Research
Michael Y. Hu, Angelica Chen, Naomi Saphra, Kyunghyun Cho
[Arxiv] [OpenReview]

LLMs for Biomedical Applications

Generalist Foundation Models Are Not Clinical Enough for Hospital Operations
Under Review
Lavender Y Jiang*, Angelica Chen*, Xu Han, Xujin Chris Liu, Radhika Dua, Kevin Eaton, Frederick Wolff, Robert Steele, Jeff Zhang, Anton Alyakin, Qingkai Pan, Yanbing Chen, Karl L Sangwon, Daniel A Alber, Jaden Stryker, Jin Vivian Lee, Yindalon Aphinyanaphongs, Kyunghyun Cho, Eric Karl Oermann
[Arxiv]

Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks
ICML 2025
(Spotlight) NeurIPS 2024 Workshop on AI for New Drug Modalities (AIDrugX)
Angelica Chen, Samuel D. Stanton, Frances Ding, Robert G. Alberstein, Andrew M. Watkins, Richard Bonneau, Vladimir Gligorijević, Kyunghyun Cho, Nathan C. Frey
[Arxiv] [Github]

Invited Talks