Cover Image

The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mao, Weijia, Chen, Hao, Yang, Zhenheng, Shou, Mike Zheng
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning
by: Mao, Weijia, et al.
Published: (2025)

UniMoD: Efficient Unified Multimodal Transformers with Mixture-of-Depths
by: Mao, Weijia, et al.
Published: (2025)

DoraCycle: Domain-Oriented Adaptation of Unified Generative Model in Multimodal Cycles
by: Zhao, Rui, et al.
Published: (2025)

Show-o2: Improved Native Unified Multimodal Models
by: Xie, Jinheng, et al.
Published: (2025)

IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generation
by: Song, Yiren, et al.
Published: (2024)

Long-Context Autoregressive Video Modeling with Next-Frame Prediction
by: Gu, Yuchao, et al.
Published: (2025)

Mitty: Diffusion-based Human-to-Robot Video Generation
by: Song, Yiren, et al.
Published: (2025)

Edit Transfer: Learning Image Editing via Vision In-Context Relations
by: Chen, Lan, et al.
Published: (2025)

Reward Incremental Learning in Text-to-Image Generation
by: Wang, Maorong, et al.
Published: (2024)

Automated Movie Generation via Multi-Agent CoT Planning
by: Wu, Weijia, et al.
Published: (2025)

Understanding Reward Hacking in Text-to-Image Reinforcement Learning
by: Hong, Yunqi, et al.
Published: (2026)

Parrot: Pareto-optimal Multi-Reward Reinforcement Learning Framework for Text-to-Image Generation
by: Lee, Seung Hyun, et al.
Published: (2024)

Show-o: One Single Transformer to Unify Multimodal Understanding and Generation
by: Xie, Jinheng, et al.
Published: (2024)

DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models
by: Wu, Weijia, et al.
Published: (2023)

Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation
by: Zhao, Xiangyu, et al.
Published: (2026)

Explainable AI-Generated Image Detection RewardBench
by: Yang, Michael, et al.
Published: (2025)

Multi-human Interactive Talking Dataset
by: Zhu, Zeyu, et al.
Published: (2025)

UniGen-1.5: Enhancing Image Generation and Editing through Reward Unification in Reinforcement Learning
by: Tian, Rui, et al.
Published: (2025)

Unpaired Image Deraining Using Reward-Guided Self-Reinforcement Strategy
by: Chen, Yinghao, et al.
Published: (2026)

PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling
by: Ping, Bowen, et al.
Published: (2025)

Tuning-Free Image Editing with Fidelity and Editability via Unified Latent Diffusion Model
by: Mao, Qi, et al.
Published: (2025)

Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling
by: Zhang, Guiyu, et al.
Published: (2024)

Paragraph-to-Image Generation with Information-Enriched Diffusion Model
by: Wu, Weijia, et al.
Published: (2023)

Reward-Instruct: A Reward-Centric Approach to Fast Photo-Realistic Image Generation
by: Luo, Yihong, et al.
Published: (2025)

RewardFlow: Generate Images by Optimizing What You Reward
by: Susladkar, Onkar, et al.
Published: (2026)

MotionRL: Align Text-to-Motion Generation to Human Preferences with Multi-Reward Reinforcement Learning
by: Liu, Xiaoyang, et al.
Published: (2024)

RubricRL: Simple Generalizable Rewards for Text-to-Image Generation
by: Feng, Xuelu, et al.
Published: (2025)

Identity-Preserving Image-to-Video Generation via Reward-Guided Optimization
by: Shen, Liao, et al.
Published: (2025)

Enhancing Spatial Understanding in Image Generation via Reward Modeling
by: Tang, Zhenyu, et al.
Published: (2026)

VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation
by: Xu, Jiazheng, et al.
Published: (2024)

RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards
by: Ye, Junyan, et al.
Published: (2025)

Reinforcement Learning for Large Model: A Survey
by: Wu, Weijia, et al.
Published: (2025)

SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generation
by: Zhou, Sashuai, et al.
Published: (2026)

CCCaption: Dual-Reward Reinforcement Learning for Complete and Correct Image Captioning
by: Tang, Zhijiang, et al.
Published: (2026)

R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning
by: Zhang, Yi-Fan, et al.
Published: (2025)

Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
by: Wang, Yibin, et al.
Published: (2025)

A Dense Reward View on Aligning Text-to-Image Diffusion with Preference
by: Yang, Shentao, et al.
Published: (2024)

Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceivers
by: Shi, Yiqing, et al.
Published: (2025)

Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling
by: Bai, Xuehai, et al.
Published: (2026)

Reinforcement Learning with Inverse Rewards for World Model Post-training
by: Ye, Yang, et al.
Published: (2025)