works on
benchmark evaluation 1intermediate visual states 1large language models 1multimodal models 1visual reasoning 1

From the 1 of 3 linked papers with an AI index.

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

Latent Thought Flow: Efficient Latent Reasoning in Large Language Models

Xiandong Zou, Jing Huang, Jianshu Li +1

Large Language Models (LLMs) increasingly rely on intermediate reasoning, yet explicit Chain-of-Thought (CoT) suffers from a linguistic space bottleneck: each thought must be decod…