Video-R4: Reinforcing Text-Rich Video Reasoning with Visual Rumination

TL;DR

Video-R4 introduces an iterative visual rumination approach for text-rich video reasoning, enabling models to re-inspect and focus on critical regions, significantly improving accuracy on various video QA tasks.

Contribution

The paper presents a novel multi-stage training framework for a large language model that performs iterative visual rumination, enhancing pixel-grounded multimodal reasoning capabilities.

Findings

Achieves state-of-the-art results on M4-ViteVQA.

Generalizes well to document, slides, and generic video QA.

Demonstrates the effectiveness of iterative rumination for fine-grained reasoning.

Abstract

Understanding text-rich videos requires reading small, transient textual cues that often demand repeated inspection. Yet most video QA models rely on single-pass perception over fixed frames, leading to hallucinations and failures on fine-grained evidence. Inspired by how humans pause, zoom, and re-read critical regions, we introduce Video-R4 (Reinforcing Text-Rich Video Reasoning with Visual Rumination), a video reasoning LMM that performs visual rumination: iteratively selecting frames, zooming into informative regions, re-encoding retrieved pixels, and updating its reasoning state. We construct two datasets with executable rumination trajectories: Video-R4-CoT-17k for supervised practice and Video-R4-RL-30k for reinforcement learning. We propose a multi-stage rumination learning framework that progressively finetunes a 7B LMM to learn atomic and mixing visual operations via SFT and GRPO-based RL. Video-R4-7B achieves state-of-the-art results on M4-ViteVQA and further generalizes to multi-page document QA, slides QA, and generic video QA, demonstrating that iterative rumination is an effective paradigm for pixel-grounded multimodal reasoning. Project Page: https://yunlong10.github.io/Video-R4/