Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Pan, Kaihang, Wu, Yang, Bu, Wendong, Shen, Kai, Li, Juncheng, Wang, Yingting, Li, Yunfei, Tang, Siliang, Xiao, Jun, Wu, Fei, Zhao, Hang, Zhuang, Yueting
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2506.01480
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909862032572416
author Pan, Kaihang
Wu, Yang
Bu, Wendong
Shen, Kai
Li, Juncheng
Wang, Yingting
Li, Yunfei
Tang, Siliang
Xiao, Jun
Wu, Fei
Zhao, Hang
Zhuang, Yueting
author_facet Pan, Kaihang
Wu, Yang
Bu, Wendong
Shen, Kai
Li, Juncheng
Wang, Yingting
Li, Yunfei
Tang, Siliang
Xiao, Jun
Wu, Fei
Zhao, Hang
Zhuang, Yueting
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_01480
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning
Pan, Kaihang
Wu, Yang
Bu, Wendong
Shen, Kai
Li, Juncheng
Wang, Yingting
Li, Yunfei
Tang, Siliang
Xiao, Jun
Wu, Fei
Zhao, Hang
Zhuang, Yueting
Computer Vision and Pattern Recognition
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.
title Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.01480