Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning
This work addresses the integration of reasoning mechanisms in MLLMs to unify image generation tasks, representing a novel method rather than an incremental improvement.
The paper tackles the problem of independent visual comprehension and generation in Multimodal Large Language Models (MLLMs) by proposing a collaborative co-evolution approach, resulting in a model that excels in text-to-image generation, image editing, and functions as a superior image semantic evaluator.
Recent endeavors in Multimodal Large Language Models (MLLMs) aim to unify visual comprehension and generation. However, these two capabilities remain largely independent, as if they are two separate functions encapsulated within the same model. Consequently, visual comprehension does not enhance visual generation, and the reasoning mechanisms of LLMs have not been fully integrated to revolutionize image generation. In this paper, we propose to enable the collaborative co-evolution of visual comprehension and generation, advancing image generation into an iterative introspective process. We introduce a two-stage training approach: supervised fine-tuning teaches the MLLM with the foundational ability to generate genuine CoT for visual generation, while reinforcement learning activates its full potential via an exploration-exploitation trade-off. Ultimately, we unlock the Aha moment in visual generation, advancing MLLMs from text-to-image tasks to unified image generation. Extensive experiments demonstrate that our model not only excels in text-to-image generation and image editing, but also functions as a superior image semantic evaluator with enhanced visual comprehension capabilities. Project Page: https://janus-pro-r1.github.io.