# Video Finetuning Improves Reasoning Between Frames

Source: [Video Finetuning Improves Reasoning Between Frames](<https://www.sota2.com/research/paper/691bfe0f6750be83fe5cec3d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-11-19T05:04:29.660Z

Authors: Ruiqi Yang, Tian Yun, Zihan Wang, Ellie Pavlick

Published: 2025-11-17T01:51:57.000Z

## Abstract

Multimodal large language models (LLMs) have made rapid progress in visual understanding, yet their extension from images to videos often reduces to a naive concatenation of frame tokens. In this work, we investigate what video finetuning brings to multimodal LLMs. We propose Visual Chain-of-Thought (vCoT), an explicit reasoning process that generates transitional event descriptions between consecutive frames. Using vCoT, we systematically compare image-only LVLMs with their video-finetuned counterparts, both with and without access to these transitional cues. Our experiments show that vCoT significantly improves the performance of image-only models on long-form video question answering, while yielding only marginal gains for video-finetuned models. This suggests that the latter already capture frame-to-frame transitions implicitly. Moreover, we find that video models transfer this temporal reasoning ability to purely static settings, outperforming image models' baselines on relational visual reasoning tasks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2511.12868>)

[PDF](<https://arxiv.org/pdf/2511.12868.pdf>)
