Papers
arxiv:2503.19948

Test-Time Reasoning Through Visual Human Preferences with VLMs and Soft Rewards

Published on Mar 25
Authors:
,

Abstract

Visual Language Models trained with reinforcement learning can effectively capture human visual preferences, offering accurate and interpretable image ranking.

AI-generated summary

Can Visual Language Models (VLMs) effectively capture human visual preferences? This work addresses this question by training VLMs to think about preferences at test time, employing reinforcement learning methods inspired by DeepSeek R1 and OpenAI O1. Using datasets such as ImageReward and Human Preference Score v2 (HPSv2), our models achieve accuracies of 64.9% on the ImageReward test set (trained on ImageReward official split) and 65.4% on HPSv2 (trained on approximately 25% of its data). These results match traditional encoder-based models while providing transparent reasoning and enhanced generalization. This approach allows to use not only rich VLM world knowledge, but also its potential to think, yielding interpretable outcomes that help decision-making processes. By demonstrating that human visual preferences reasonable by current VLMs, we introduce efficient soft-reward strategies for image ranking, outperforming simplistic selection or scoring methods. This reasoning capability enables VLMs to rank arbitrary images-regardless of aspect ratio or complexity-thereby potentially amplifying the effectiveness of visual Preference Optimization. By reducing the need for extensive markup while improving reward generalization and explainability, our findings can be a strong mile-stone that will enhance text-to-vision models even further.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2503.19948 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2503.19948 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2503.19948 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.