Celine Lee
Principal Investigator
Celine Lee is a PhD candidate at Cornell Tech in New York City, where she researches neurosymbolic approaches to language reasoning, especially in coding tasks. She explores questions in structured language, particularly problems in programming language semantics and reasoning.
Her recent publications include "Critical Thinking: Which Kinds of Complexity Govern Optimal Reasoning Length?" (ACL Findings), "Commit0: Library Generation from Scratch" (ICLR 2025), "Sampling Language from Latent System-2 Reasoning" (NeurIPS 2024), "Guess & Sketch: Language Model Guided Transpilation" (ICLR 2024), and "The Counterfeit Conundrum: Can Code Language Models Grasp the Nuances of Their Incorrect Generations?" (ACL 2024).
Celine has held various research and development roles at IBM TJ Watson, Intel, and VMware. She joined the Cognitive Computation Group as an undergraduate/master's student researcher in 2019 and graduated from Penn in 2020.
Her excitement for teaching shows through her TA positions at the University of Pennsylvania and Cornell, as a head instructor with Break Through Tech AI, and through external mentorship programs.
Begin Your Journey
The application takes 10 minutes and is reviewed on a rolling basis. We look for strong technical signal—projects, coursework, or competition results—and a genuine curiosity to do real research.
If admitted, you will join a structured pipeline with direct mentorship to take your work from ideation to top conference submission at venues like NeurIPS, ACL, and EMNLP.
