CoLT: Multimodal Latent Chain of Thought Reasoning

机器之心 · wechat · 2026-07-15

This article introduces CoLT (Chain of Latent Thoughts), a multimodal latent space reasoning method. It aims to enable MLLMs to reason using a few continuous latent vectors instead of verbose text CoT, without requiring extra image annotations.

Core Approach

Key Results

Ablation and Interpretability

Original post →

More from Research

Research channel →