Beyond Visual CoT: Internalized Visual Thinking for Proactive Video Reasoning
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…
content type paperpublished August 2026
Beyond Visual CoT: Internalized Visual Thinking for Proactive Video Reasoning
AuthorsXiaoyu Zhu, Xinke Deng, Suresh Taddewadikar, Arnab Kumar Mondal, Zhongyu Jiang, Ian Fasel, Joerg Liebelt
View publication
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 next-embedding prediction over unlabeled videos. Given a partially observed video, IVT predicts latent representations of future frames together with the target textual answer, encouraging the model to capture motion, object transitions, interactions, and latent intent. At inference, IVT generates the answer directly without synthesizing or re-encoding future frames. We conduct controlled studies across target representations, decoder designs, prediction horizons, data mixtures, training curricula, and predictive objectives. IVT improves over text-only post-training across all six evaluation settings while retaining the same efficient inference pathway. Compared with Visual CoT, IVT achieves comparable or better performance and reduces end-to-end latency by more than 5×. Our findings suggest that explicit pixel-space generation at inference time, as used in Visual CoT, may not be necessary for proactive video reasoning. Predictive world modeling can be internalized during training to produce multimodal reasoners that are both more accurate and substantially more efficient.
The Potential of CoT for Reasoning: A Closer Look at Trace Dynamics
February 24, 2026research area Methods and Algorithms, research area Speech and Natural Language Processingconference ICLR
Chain-of-thought (CoT) prompting is a de-facto standard technique to elicit reasoning-like responses from large language models (LLMs), allowing them to spell out individual steps before giving a final answer. While the resemblance to human-like reasoning is undeniable, the driving forces underpinning the success of CoT reasoning still remain largely unclear. In this work, we perform an in-depth analysis of CoT traces originating from…
Read more
Improve Vision Language Model Chain-of-thought Reasoning
June 5, 2025research area Computer Vision, research area Speech and Natural Language Processingconference ACL
Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness. However, current training recipes often relying on datasets dominated by short annotations with minimal rationales. In this work, we show that training VLM on short answers leads to poor generalization on reasoning tasks that require more detailed explanations. To address this limitation, we propose a two-stage…
Read more