Marvin Li

Marvin Li

AI Researcher (Harvard '25)

Posts by Collection

publications

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

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

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

Published in International Conference on Machine Learning, 2024 — 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

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

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

Published in Harvard College thesis, 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

Firm Foundations for Membership Inference Attacks Against Large Language Models

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

talks

teaching