MM-R1: Unleashing the Power of Unified Multimodal Large Language Models for Personalized Image Generation
This addresses the problem of scalable personalized image generation for users by reducing the need for data-intensive fine-tuning, though it appears incremental as it builds on existing MLLM architectures.
The paper tackles the challenge of aligning unified Multimodal Large Language Models (MLLMs) with personalized image generation by introducing MM-R1, a framework that uses cross-modal Chain-of-Thought reasoning and Grouped Reward Proximal Policy Optimization to enable zero-shot generation of images with high subject fidelity and strong text alignment.
Multimodal Large Language Models (MLLMs) with unified architectures excel across a wide range of vision-language tasks, yet aligning them with personalized image generation remains a significant challenge. Existing methods for MLLMs are frequently subject-specific, demanding a data-intensive fine-tuning process for every new subject, which limits their scalability. In this paper, we introduce MM-R1, a framework that integrates a cross-modal Chain-of-Thought (X-CoT) reasoning strategy to unlock the inherent potential of unified MLLMs for personalized image generation. Specifically, we structure personalization as an integrated visual reasoning and generation process: (1) grounding subject concepts by interpreting and understanding user-provided images and contextual cues, and (2) generating personalized images conditioned on both the extracted subject representations and user prompts. To further enhance the reasoning capability, we adopt Grouped Reward Proximal Policy Optimization (GRPO) to explicitly align the generation. Experiments demonstrate that MM-R1 unleashes the personalization capability of unified MLLMs to generate images with high subject fidelity and strong text alignment in a zero-shot manner.