Papers2

#transferability

Sparse Reward Subsystem in Large Language Models

Guowei Xu, Mert Yuksekgonul et al.Feb 1arXiv

The paper discovers a tiny, special group of neurons inside large language models (LLMs) that act like a reward system in the human brain.

#value neurons#dopamine neurons#reward prediction error

Few Tokens Matter: Entropy Guided Attacks on Vision-Language Models

Intermediate

Mengqi He, Xinyu Tian et al.Dec 26arXiv

The paper shows that when vision-language models write captions, only a small set of uncertain words (about 20%) act like forks that steer the whole sentence.

#vision-language models#autoregressive generation#entropy