Marvin Li

Marvin Li

AI Researcher (Harvard '25)

Publications

You can also find my articles on my Google Scholar profile.

Conference Papers

Blink of an Eye: A Simple Theory for Feature Localization in Generative Models

Published in International Conference on Machine Learning (Oral, top 1%), 2025 — Paper

Critical Windows: Non-Asymptotic Theory for Feature Emergence in Diffusion Models

Published in International Conference on Machine Learning, 2024 — Paper

MOPE: Model Perturbation-based Privacy Attacks on Language Models

Published in EMNLP 2023 Main Conference – Large Language Models and the Future of NLP track, 2023 — Paper

Thesis

In the Blink of an Eye: A Unified Theory for Feature Emergence in Generative Models

Published in Harvard College thesis, 2025 — Paper

Journal Articles

Machine Learning Classification Algorithms for Predicting Karenia brevis Blooms on the West Florida Shelf

Published in Journal of Marine Science and Engineering, 9(9):999, 2021 — Paper

Workshop Papers

Firm Foundations for Membership Inference Attacks Against Large Language Models

Published in ICML 2025 Workshop on Data in Generative Models, 2025 — Paper

Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning

Published in ICML 2025 Workshop on Reliable and Responsible Foundation Models, 2025 — Paper

Bias Begets Bias: The Impact of Biased Embeddings on Diffusion Models

Published in ICML 2024 Workshop on Trustworthy Multi-modal Foundation Models and AI Agents, 2024 — Paper