Hi!

I’m a fourth-year PhD student at Berkeley AI Research, advised by Anca Dragan and Dan Klein. My research is supported by the Apple Scholars in AI Fellowship.

I’m interested in building agents that can collaborate and interact with humans, and use language as a medium to do so. Currently, I’m excited about dialogue and language + RL.

Previously, I worked on research and product at Lilt, working on human-in-the-loop machine translation / Copilot for expert translators. I graduated with a double-major in computer science and philosophy from MIT, where I did research on human-inspired AI with the Computational Cognitive Science Group, advised by Kelsey Allen and Josh Tenenbaum, and machine learning security as a founding member of labsix. I also spent a great summer with the Natural Language Understanding group at Google Research NY, advised by David Weiss.

Publications

Learning to Model the World with Language

Jessy Lin, Yuqing Du, Olivia Watkins, Danijar Hafner, Pieter Abbeel, Dan Klein, Anca Dragan

ICML 2024. (oral, top 1.5%)

We introduce Dynalang, an agent that leverages diverse types of language to solve tasks by using language to predict the future in a multimodal world model.

Decision-Oriented Dialogue for Human-AI Collaboration

Jessy Lin*, Nicholas Tomlin*, Jacob Andreas, Jason Eisner

TACL/ACL 2024, LLM Agents @ ICLR 2024.

We introduce a new task and suite of environments to evaluate how agents like LLMs can assist humans with everyday decision-making.

InCoder: A Generative Model for Code Infilling and Synthesis

Daniel Fried*, Armen Aghajanyan*, Jessy Lin, Sida Wang, Eric Wallace, Freda Shi, Ruiqi Zhong, Wen-tau Yih, Luke Zettlemoyer, Mike Lewis

ICLR 2023. (spotlight, top 6%)

We open-source a new large language model for code that can both generate and fill-in-the-blank to do tasks like docstring generation, code rewriting, type hint inference, and more.

[Paper] [Twitter] [Demo] [Site] [Code]

Automatic Correction of Human Translations

Jessy Lin, Geza Kovacs, Aditya Shastry, Joern Wuebker, John DeNero

NAACL 2022. Best Task Paper, Best Resource Paper, Best Theme Paper Honorable Mention.

We introduce the task of translation error correction and show how models can augment professional translators in-the-loop.

Uni[MASK]: Unified Inference in Sequential Decision Problems

Micah Carroll, Orr Paradise, Jessy Lin, Raluca Georgescu, Mingfei Sun, David Bignell, Stephanie Milani, Katja Hofmann, Matthew Hausknecht, Anca Dragan, Sam Devlin

NeurIPS 2022. (oral, top 1.8%)

We show how a single model trained with a BERT-like masked prediction objective can unify inference in sequential decisionmaking settings (e.g. for RL): behavior cloning, future prediction, and more.

Inferring Rewards from Language in Context

Jessy Lin, Daniel Fried, Dan Klein, Anca Dragan

ACL 2022.

We infer human preferences (reward functions) from language.

Black-box Adversarial Attacks with Limited Queries and Information

Andrew Ilyas*, Logan Engstrom*, Anish Athalye*, Jessy Lin*

ICML 2018.

We generate adversarial examples for real-world ML systems like the Google Cloud Vision API using only access to predicted labels.

[Paper] [Blog] [Code]