Celine Lee

PhD student @ Cornell University, advised by Sasha Rush. I work on language modeling, with a special focus on code reasoning and generation.

Currently (Spring 2025): Adjunct Instructor @ Mohamed Bin Zayed University of Artificial Intelligence in Abu Dhabi, UAE.

Previously: BSE & MSE @ University of Pennsylvania, 2020, where I worked with Dan Roth and Justin Gottschlich.

My CV and my Google Scholar.

I am co-organizing the VerifAI: AI Verification in the Wild workshop @ ICLR 2025. Submit, review, and attend!

Publications & Patents

Sampling Language from Latent System-2 Reasoning (Celine Lee, Arafat Sultan, Tahira Naseem, Alexander M. Rush, Ramon Fernandez Astudillo). (NeurIPS 2024 - System 2 Reasoning at Scale). Workshop version.

The Counterfeit Conundrum: Can Code Language Models Grasp the Nuances of Their Incorrect Generations? (Alex Gu, Celine Lee*, Wen-Ding Li*, Naman Jain*, Theo X. Olausson*, Koushik Sen, Armando Solar-Lezama). (ACL 2024 - Findings). Website. arXiv.

Guess & Sketch: Language Model Guided Transpilation. (Celine Lee, Abdulrahman Mahmoud, Michal Kurek, Simone Campanoni, David Brooks, Stephen Chong, Gu-Yeon Wei, Alexander Rush). (ICLR 2024). arXiv, poster pdf, and blog post.

Mixture of Soft Prompts for Controllable Data Generation. (Derek Chen, Celine Lee, Yunan Lu, Domenic Rosati, Zhou Yu). (EMNLP 2023 - Findings) arXiv.

Batched Vectorized Earley Parsing. (Celine Lee, Alexander M. Rush). Presented at the 2023 Mid-Atlantic Student Colloquium on Speech, Language and Learning (MASC-SLL 2023). Blog post. Poster.

A Survey on Semantic Parsing for Machine Programming. (Celine Lee, Justin Gottschlich, Dan Roth). Presented at the 2021 KDD Workshop on Programming Language Processing (KDD 2021 - PLP). arXiv, Workshop version.

METHODS AND APPARATUS TO IMPROVE DATA QUALITY FOR ARTIFICIAL INTELLIGENCE (USPTO App. No. 17/540050)

METHODS AND APPARATUS TO TRAIN MODELS FOR PROGRAM SYNTHESIS (USPTO App. No. 17/551170)

METHODS AND APPARATUS TO DETERMINE REFINED CONTEXT FOR SOFTWARE BUG DETECTION AND CORRECTION (USPTO App. No. 17/554918)

METHODS, APPARATUS, AND ARTICLES OF MANUFACTURE TO GENERATE COMMAND LISTS TO BE OFFLOADED TO ACCELERATOR CIRCUITRY (USPTO App. No. 17/559556)

Media

• June 2024 - I was interviewed by Jennifer Sheffield for the Cognitive Computation Group Blog. Interview link.
• October 2021 - I was interviewed by Dr. Justin Gottschlich on the Machine Programming & Technology channel. Video

Software

• Semantic Role Labeling (English) (Spanish)

Essays & Zines

The Fussy Suitor (September 2024) Published in Yale Paprika! Vol.11 Iss.1

The Say Yes Mindset (August 2024) Medium blog post

Irrealis and World Models (July 2024) Medium blog post

The Graph-Optimized Party (June 2024) Medium blog post

Neurosymbolic Assembly Transpilation (May 2024) Medium blog post

Memorme: a philosophy on writing and memory (May 2024) Medium blog post

Bird Saturday (March 2024) pdf

Playlists (on Nostalgia) (December 2023) pdf in REMINIS-ZINE

So You Want To Stick Googly Eyes On There (November 2023) pdf

Donut Wheel (October 2023) pdf

Trinkets (September 2023) pdf

Please Be Seated (July 2023) pdf

Dear Kohlrabi (April 2023) Published in Yale Paprika! Vol.8 Iss.6

Fast Earley Parsing (May 2024) Medium blog post

Sidewalk Politics (October 2022) Published in Yale Paprika! Vol.8 Iss.2

Smelly Colors (September 2022) Medium blog post

The Vowel Trapezoid (December 2021) Medium blog post

My first study of "grounding" natural language in code on StackOverflow (December 2021) Medium blog post

Misc.

Hobbies include: volleyball, writing, some arts and crafts.

Slides from past presentations here.

A running list of what-to-do ideas when you need some inspiration. Use them if that's fun for you

I like soup a lot.