Beyond Visual CoT: Internalized Visual Thinking for Proactive Video Reasoning

Apple Machine LearningAugust 24, 2026en

Apple Machine Learning

AI Global Wire

Multimodal large language models increasingly use visual chain-of-thought (Visual CoT) to reason about spatial, temporal, and embodied environments. By generating intermediate reasoning images, Visual CoT provides an intuitive mechanism for visual foresight but introduces substantial inference overhead, which is particularly problematic for proactive video reasoning. We ask whether models can learn to think visually during training while reasoning directly at inference. We introduce Internalized Visual Thinking (IVT), a post-training framework that jointly optimizes textual prediction and…

This is a short summary published by AI Global Wire. The full article is owned and hosted by Apple Machine Learning — open it there to read it in full.

• Verktyg
• Bild