Papers2

All Beginner Intermediate Advanced

All Sources arXiv

#residual stream

Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process

Beginner

Zhenyu Zhang, Shujian Zhang et al.Dec 30arXiv

This paper shows a new way (called RISE) to find and control how AI models think without needing any human-made labels.

#RISE#sparse auto-encoder#reasoning vectors

Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies

Beginner

Yuqiao Tan, Minzheng Wang et al.Dec 22arXiv

Large language models (LLMs) don’t act as a single brain; inside, each layer and module quietly makes its own mini-decisions called internal policies.

#Bottom-up Policy Optimization#internal layer policy#internal modular policy