UniGen-1.5: Enhancing Image Generation and Editing through Reward Unification in Reinforcement Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918208298024960 |
|---|---|
| author | Tian, Rui Gao, Mingfei Gang, Haiming Lu, Jiasen Gan, Zhe Yang, Yinfei Wu, Zuxuan Dehghan, Afshin |
| author_facet | Tian, Rui Gao, Mingfei Gang, Haiming Lu, Jiasen Gan, Zhe Yang, Yinfei Wu, Zuxuan Dehghan, Afshin |
| contents | We present UniGen-1.5, a unified multimodal large language model (MLLM) for advanced image understanding, generation and editing. Building upon UniGen, we comprehensively enhance the model architecture and training pipeline to strengthen the image understanding and generation capabilities while unlocking strong image editing ability. Especially, we propose a unified Reinforcement Learning (RL) strategy that improves both image generation and image editing jointly via shared reward models. To further enhance image editing performance, we propose a light Edit Instruction Alignment stage that significantly improves the editing instruction comprehension that is essential for the success of the RL training. Experimental results show that UniGen-1.5 demonstrates competitive understanding and generation performance. Specifically, UniGen-1.5 achieves 0.89 and 4.31 overall scores on GenEval and ImgEdit that surpass the state-of-the-art models such as BAGEL and reaching performance comparable to proprietary models such as GPT-Image-1. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_14760 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | UniGen-1.5: Enhancing Image Generation and Editing through Reward Unification in Reinforcement Learning Tian, Rui Gao, Mingfei Gang, Haiming Lu, Jiasen Gan, Zhe Yang, Yinfei Wu, Zuxuan Dehghan, Afshin Computer Vision and Pattern Recognition We present UniGen-1.5, a unified multimodal large language model (MLLM) for advanced image understanding, generation and editing. Building upon UniGen, we comprehensively enhance the model architecture and training pipeline to strengthen the image understanding and generation capabilities while unlocking strong image editing ability. Especially, we propose a unified Reinforcement Learning (RL) strategy that improves both image generation and image editing jointly via shared reward models. To further enhance image editing performance, we propose a light Edit Instruction Alignment stage that significantly improves the editing instruction comprehension that is essential for the success of the RL training. Experimental results show that UniGen-1.5 demonstrates competitive understanding and generation performance. Specifically, UniGen-1.5 achieves 0.89 and 4.31 overall scores on GenEval and ImgEdit that surpass the state-of-the-art models such as BAGEL and reaching performance comparable to proprietary models such as GPT-Image-1. |
| title | UniGen-1.5: Enhancing Image Generation and Editing through Reward Unification in Reinforcement Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.14760 |