2 papers
cs.LG2026
REACT: Representational Early Analysis and Control of Chain-of-Thought Trajectories
Hanwen Zhang, Enyi Jiang, Ruike Zhu +2
Chain-of-thought (CoT) generation offers an opportunity to intervene before a reasoning model completes its answer. But does the point at which risk is easiest to detect also offer…
cs.AI2025
Beyond Parameters: Exploring Virtual Logic Depth for Scaling Laws
Ruike Zhu, Hanwen Zhang, Kevin Li +6
Scaling large language models typically involves three dimensions: depth, width, and parameter count. In this work, we explore a fourth dimension, \textbf{virtual logical depth} (V…