3 papers
cs.CL2025
Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning
Miles Turpin, Andy Arditi, Marvin Li +2
Language models trained with reinforcement learning (RL) can engage in reward hacking--the exploitation of unintended strategies for high reward--without revealing this behavior in…
cs.LG2025
Blink of an eye: a simple theory for feature localization in generative models
Marvin Li, Aayush Karan, Sitan Chen
Large language models can exhibit unexpected behavior in the blink of an eye. In a recent computer use demo, a language model switched from coding to Googling pictures of Yellowsto…
cs.LG2024
Critical windows: non-asymptotic theory for feature emergence in diffusion models
Marvin Li, Sitan Chen
We develop theory to understand an intriguing property of diffusion models for image generation that we term critical windows. Empirically, it has been observed that there are narr…