---
title: "视觉提示工程：让视频模型更聪明的简单方法"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.25537v1"
permalink: "https://feed.astralor.com/items/itm_f5f6c609ed2ea06370af64ec"
published: "2026-07-28T10:18:58.000Z"
score: 81
channel: "tech"
tags: ["arXiv","基础模型","提示工程","视觉提示工程","视频模型"]
---

# 视觉提示工程：让视频模型更聪明的简单方法

## AI 点评

> 这篇论文让我眼前一亮：原来提示工程也可以对视频模型图像输入生效，而且效果这么显著。如果你是从事视频理解或视觉推理的研究者，或者正在优化多模态模型的实际应用，这篇文章值得一读——它可能会改变你处理输入数据的方式。

## 速览

这项研究提出视觉提示工程（VIPE），通过自动修改任务图像来提升视频模型的视觉推理能力。实验表明，将抽象草图转为逼真场景等操作能显著改善模型在物理推理等任务上的表现，效果甚至优于传统文本提示工程和测试时扩展。VIPE提供了一种计算高效的替代方案，类似于文本提示对语言模型的提升。

## 关键点

- 视觉提示工程（VIPE）通过图像编辑工具自动优化输入图像，提升视频模型推理性能。
- 在物理推理任务中，将抽象示意图转为逼真场景可带来显著收益。
- VIPE比传统文本提示和测试时扩展更有效，且计算成本更低。
- 该方法提供了统一框架，类似文本提示工程对语言模型的作用。

## 全文

In the age of foundation models, a model is only as good as its prompt. For this reason, prompt engineering has become an essential technique for improving language model performance. Since video models are currently becoming foundation models for visual tasks (e.g., visual reasoning), we here ask whether they similarly benefit from visual prompt engineering: automatically modifying the task image to improve model performance. For example, for a visual physics reasoning task ("Where does the ball land, after passing a set of obstacles?"), an abstract sketch-like scene can be turned into a photorealistic version with a simple call to an image editing model. We find that visual prompt engineering, or VIPE for short, improves video reasoning performance across tasks. In fact, for video models, visual prompt engineering can be even more effective than classic text-based prompt engineering or test-time scaling. Ultimately, just as text-based prompt engineering systematically improves language model performance, visual prompt engineering can serve as a simple, compute-efficient approach to elicit better visual reasoning performance from video models. Example videos on our project page at https://visual-prompt-engineering.github.io/.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_f5f6c609ed2ea06370af64ec