Mingyu Jin

Local Branch Routing enables language models to leverage contextual evidence for decision-making without the computational burden of full solution searches, leading to substantial improvements in reasoning accuracy.

Runtime safety detection in coding agents can be achieved through a novel intervention in hidden representations, drastically reducing harmful actions during multi-turn interactions.

LLMs respond to increasingly difficult out-of-distribution inputs by activating sparser representations in their last hidden states, revealing a quantifiable relationship between task difficulty and neural activity.