English
Related papers

Related papers: MIRA: Towards Mitigating Reward Hacking in Inferen…

200 papers

Generating high-quality and photorealistic 3D assets remains a longstanding challenge in 3D vision and computer graphics. Although state-of-the-art generative models, such as diffusion models, have made significant progress in 3D…

Graphics · Computer Science 2025-06-19 Qingming Liu , Zhen Liu , Dinghuai Zhang , Kui Jia

In recent years, large-scale pre-trained diffusion models have demonstrated their outstanding capabilities in image and video generation tasks. However, existing models tend to produce visual objects commonly found in the training dataset,…

Computer Vision and Pattern Recognition · Computer Science 2024-07-30 Changgu Chen , Libing Yang , Xiaoyan Yang , Lianggangxu Chen , Gaoqi He , CHangbo Wang , Yang Li

Reinforcement Learning (RL) has recently been incorporated into diffusion models, e.g., tasks such as text-to-image. However, directly applying existing RL methods to diffusion-based image restoration models is suboptimal, as the objective…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Xiaogang Xu , Ruihang Chu , Jian Wang , Kun Zhou , Wenjie Shu , Harry Yang , Ser-Nam Lim , Hao Chen , Liang Lin

Recent methods exploit the powerful text-to-image (T2I) diffusion models for real-world image super-resolution (Real-ISR) and achieve impressive results compared to previous models. However, we observe two kinds of inconsistencies in…

Computer Vision and Pattern Recognition · Computer Science 2025-04-28 Junhao Gu , Peng-Tao Jiang , Hao Zhang , Mi Zhou , Jinwei Chen , Wenming Yang , Bo Li

Inference-time alignment techniques offer a lightweight alternative or complement to costly reinforcement learning, while enabling continual adaptation as alignment objectives and reward targets evolve. Existing theoretical analyses justify…

Machine Learning · Computer Science 2026-05-14 Ye Wang , Jing Liu , Toshiaki Koike-Akino

Aligning diffusion models with user preferences has been a key challenge. Existing methods for aligning diffusion models either require retraining or are limited to differentiable reward functions. To address these limitations, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2025-02-28 Po-Hung Yeh , Kuang-Huei Lee , Jun-Cheng Chen

Recent advances align diffusion models with human preferences to increase aesthetic appeal and mitigate artifacts and biases. Such methods aim to maximize a conditional output distribution aligned with higher rewards whilst not drifting far…

Machine Learning · Computer Science 2026-02-23 Ratnavibusena Don Shahain Manujith , Teoh Tze Tzun , Kenji Kawaguchi , Yang Zhang

Diffusion and flow models achieve State-Of-The-Art (SOTA) generative performance, yet many practically important behaviors such as fine-grained prompt fidelity, compositional correctness, and text rendering are weakly specified by score or…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Yuanzhi Zhu , Xi Wang , Stéphane Lathuilière , Vicky Kalogeiton

Reinforcement learning (RL) has emerged as a powerful tool for aligning diffusion models with human preferences, typically by optimizing a single reward function under a KL regularization constraint. In practice, however, human preferences…

Machine Learning · Computer Science 2026-04-17 Qi Zhang , Dawei Wang , Shaofeng Zou

In this paper, we make the first attempt to align diffusion models for image inpainting with human aesthetic standards via a reinforcement learning framework, significantly improving the quality and visual appeal of inpainted images.…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Kendong Liu , Zhiyu Zhu , Chuanhao Li , Hui Liu , Huanqiang Zeng , Junhui Hou

Aligning text-to-image (T2I) diffusion models with preference optimization is valuable for human-annotated datasets, but the heavy cost of manual data collection limits scalability. Using reward models offers an alternative, however,…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Kyungmin Lee , Xiaohang Li , Qifei Wang , Junfeng He , Junjie Ke , Ming-Hsuan Yang , Irfan Essa , Jinwoo Shin , Feng Yang , Yinxiao Li

The default paradigm of post-training text-to-image generators includes post-hoc selection of generated images, and subsequent training with one reward model to align the generator to the reward, typically user preference. This discards…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Nicolas Dufour , Lucas Degeorge , Arijit Ghosh , Vicky Kalogeiton , David Picard

Fine-tuning diffusion models via online reinforcement learning (RL) has shown great potential for enhancing text-to-image alignment. However, since precisely specifying a ground-truth objective for visual tasks remains challenging, the…

Machine Learning · Computer Science 2026-01-01 Haoran He , Yuxiao Ye , Jie Liu , Jiajun Liang , Zhiyong Wang , Ziyang Yuan , Xintao Wang , Hangyu Mao , Pengfei Wan , Ling Pan

Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models with human preferences, inspiring the development of reward-centric diffusion reinforcement learning (RDRL) to achieve similar…

Machine Learning · Computer Science 2026-03-24 Kwanyoung Kim , Byeongsu Sim

Learning from feedback has been shown to enhance the alignment between text prompts and images in text-to-image diffusion models. However, due to the lack of focus in feedback content, especially regarding the object type and quantity,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Xuexiang Niu , Jinping Tang , Lei Wang , Ge Zhu

Aligning LLMs with user preferences is crucial for real-world use but often requires costly fine-tuning or expensive inference, forcing trade-offs between alignment quality and computational cost. Existing inference-time methods typically…

Machine Learning · Computer Science 2025-08-08 Mason Nakamura , Saaduddin Mahmud , Kyle H. Wray , Hamed Zamani , Shlomo Zilberstein

To fully leverage the capabilities of diffusion models, we are often interested in optimizing downstream reward functions during inference. While numerous algorithms for reward-guided generation have been recently proposed due to their…

Machine Learning · Computer Science 2025-04-18 Masatoshi Uehara , Xingyu Su , Yulai Zhao , Xiner Li , Aviv Regev , Shuiwang Ji , Sergey Levine , Tommaso Biancalani

Diffusion models are widely used for generative tasks across domains. Given a pre-trained diffusion model, it is often desirable to fine-tune it further either to correct for errors in learning or to align with downstream applications.…

Diffusion model alignment aims to bridge the gap between generated outputs and human preferences by enhancing both semantic consistency with textual prompts and overall visual quality. Existing alignment methods face a challenging…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Xin Xie , Jiaxian Guo , Dong Gong

Diffusion and flow-matching models scale because pretraining is supervised regression: a clean sample is noised analytically, and a model regresses against a closed-form target. RL post-training aligns the model with a reward. In image…

Machine Learning · Computer Science 2026-05-19 Andreas Bergmeister , Stefanie Jegelka , Nikolas Nüsken , Carles Domingo-Enrich , Jakiw Pidstrigach