I’m a first-year CS PhD at Stanford. Previously, I worked as an algorithm developer at Hudson River Trading’s HRT AI Labs (HAIL), training foundation models for automated trading. I graduated summa cum laude from Harvard in 2025 with a B.A. in CS and Math.

Selected Publications

* denotes equal contribution

Blink of an Eye: A Simple Theory for Feature Localization in Generative Models
Marvin Li, Aayush Karan, Sitan Chen.
ICML, 2025 (Oral, top 1% of submissions)
arXiv / code
A unifying theory showing why and when features suddenly “lock in” during generation in both diffusion and autoregressive models.

Critical Windows: Non-Asymptotic Theory for Feature Emergence in Diffusion Models
Marvin Li, Sitan Chen.
ICML, 2024
arXiv / code
Introduces tight, distribution-agnostic bounds pinpointing when image features appear along the diffusion trajectory.

MoPe: Model Perturbation-Based Privacy Attacks on Language Models
Marvin Li*, Jason Wang*, Jeffrey Wang*, Seth Neel.
EMNLP Main Conference, 2023
arXiv
Shows that second-order gradient information lets an attacker detect training-set membership far more reliably than loss-only baselines.