Omni-R1: Towards the Unified Generative Paradigm for Multimodal Reasoning
This addresses the problem of limited generalizability in multimodal reasoning for AI researchers and practitioners, offering a novel approach but with incremental improvements over existing methods.
The paper tackles the limitation of multimodal large language models (MLLMs) that rely on single task-specific reasoning patterns by proposing a unified generative paradigm for multimodal reasoning, which generates intermediate images during reasoning to unify diverse skills; results show that Omni-R1 achieves this across various tasks, and Omni-R1-Zero matches or surpasses it without multimodal annotations.
Multimodal Large Language Models (MLLMs) are making significant progress in multimodal reasoning. Early approaches focus on pure text-based reasoning. More recent studies have incorporated multimodal information into the reasoning steps; however, they often follow a single task-specific reasoning pattern, which limits their generalizability across various multimodal tasks. In fact, there are numerous multimodal tasks requiring diverse reasoning skills, such as zooming in on a specific region or marking an object within an image. To address this, we propose unified generative multimodal reasoning, which unifies diverse multimodal reasoning skills by generating intermediate images during the reasoning process. We instantiate this paradigm with Omni-R1, a two-stage SFT+RL framework featuring perception alignment loss and perception reward, thereby enabling functional image generation. Additionally, we introduce Omni-R1-Zero, which eliminates the need for multimodal annotations by bootstrapping step-wise visualizations from text-only reasoning data. Empirical results show that Omni-R1 achieves unified generative reasoning across a wide range of multimodal tasks, and Omni-R1-Zero can match or even surpass Omni-R1 on average, suggesting a promising direction for generative multimodal reasoning.