English
Related papers

Related papers: Self-Reflective Reinforcement Learning for Diffusi…

200 papers

Diffusion models typically employ static or heuristic classifier-free guidance (CFG) schedules, which often fail to adapt across timesteps and noise conditions. In this work, we introduce a quantum reinforcement learning (QRL) controller…

Quantum Physics · Physics 2025-09-18 Chi-Sheng Chen , En-Jui Kuo

Recent research has shown that fine-tuning diffusion models (DMs) with arbitrary rewards, including non-differentiable ones, is feasible with reinforcement learning (RL) techniques, enabling flexible model alignment. However, applying…

Machine Learning · Computer Science 2025-03-12 Zhiwei Jia , Yuesong Nan , Huixi Zhao , Gengdai Liu

We introduce iterative reasoning through energy diffusion (IRED), a novel framework for learning to reason for a variety of tasks by formulating reasoning and decision-making problems with energy-based optimization. IRED learns energy…

Machine Learning · Computer Science 2024-06-18 Yilun Du , Jiayuan Mao , Joshua B. Tenenbaum

Diffusion models have shown promising results on single-image super-resolution and other image- to-image translation tasks. Despite this success, they have not outperformed state-of-the-art GAN models on the more challenging blind…

Computer Vision and Pattern Recognition · Computer Science 2023-02-16 Hshmat Sahak , Daniel Watson , Chitwan Saharia , David Fleet

Recent advances in one-step text-to-image generation have enabled real-time synthesis with remarkable efficiency and quality. Previous reinforcement learning methods for one-step generators combine image-space reward optimization with…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Junyi Wu , Weijian Luo , Haoyang Zheng , Ruizhe Zhang , Guang Lin

Diffusion models have been successfully applied in areas such as image, video, and audio generation. Recent works show their promise for sequential decision-making and dexterous manipulation, leveraging their ability to model complex action…

Robotics · Computer Science 2026-03-17 Maria Makarova , Qian Liu , Dzmitry Tsetserukou

While diffusion models demonstrate strong generative capabilities in image restoration (IR) tasks, their complex architectures and iterative processes limit their practical application compared to mainstream reconstruction-based general…

Computer Vision and Pattern Recognition · Computer Science 2025-06-30 Xin Lu , Xueyang Fu , Jie Xiao , Zihao Fan , Yurui Zhu , Zheng-Jun Zha

We investigate a novel approach for image restoration by reinforcement learning. Unlike existing studies that mostly train a single large network for a specialized task, we prepare a toolbox consisting of small-scale convolutional networks…

Computer Vision and Pattern Recognition · Computer Science 2018-04-11 Ke Yu , Chao Dong , Liang Lin , Chen Change Loy

As a key component to intuitive cognition and reasoning solutions in human intelligence, causal knowledge provides great potential for reinforcement learning (RL) agents' interpretability towards decision-making by helping reduce the…

Machine Learning · Computer Science 2025-04-25 Ruichu Cai , Siyang Huang , Jie Qiao , Wei Chen , Yan Zeng , Keli Zhang , Fuchun Sun , Yang Yu , Zhifeng Hao

Retrieval-Augmented Generation (RAG) integrates external knowledge with Large Language Models (LLMs) to enhance factual correctness and mitigate hallucination. However, dense retrievers often become the bottleneck of RAG systems due to…

Computation and Language · Computer Science 2025-10-27 Yuan Li , Qi Luo , Xiaonan Li , Bufan Li , Qinyuan Cheng , Bo Wang , Yining Zheng , Yuxin Wang , Zhangyue Yin , Xipeng Qiu

Reinforcement learning-based retrieval-augmented generation (RAG) methods enhance the reasoning abilities of large language models (LLMs). However, most rely only on final-answer rewards, overlooking intermediate reasoning quality. This…

Computation and Language · Computer Science 2025-08-07 Jie He , Victor Gutiérrez-Basulto , Jeff Z. Pan

Learning from human feedback has been shown to improve text-to-image models. These techniques first learn a reward function that captures what humans care about in the task and then improve the models based on the learned reward function.…

In-context reinforcement learning (ICRL) refers to the ability of RL agents to adapt to new tasks at inference time without parameter updates by conditioning on additional context. Recent empirical studies further demonstrate that…

Machine Learning · Computer Science 2026-05-11 Zixuan Xie , Xinyu Liu , Rohan Chandra , Shangtong Zhang

Recent advancements in diffusion models have significantly improved performance in super-resolution (SR) tasks. However, previous research often overlooks the fundamental differences between SR and general image generation. General image…

Image and Video Processing · Electrical Eng. & Systems 2024-10-31 Hanlin Wu , Jiangwei Mo , Xiaohui Sun , Jie Ma

Image restoration is a long-standing problem in low-level computer vision with many interesting applications. We describe a flexible learning framework based on the concept of nonlinear reaction diffusion models for various image…

Computer Vision and Pattern Recognition · Computer Science 2016-08-23 Yunjin Chen , Thomas Pock

Generative models have made significant progress in synthesizing visual content, including images, videos, and 3D/4D structures. However, they are typically trained with surrogate objectives such as likelihood or reconstruction loss, which…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Yuanzhi Liang , Yijie Fang , Ke Hao , Rui Li , Ziqi Ni , Ruijie Su , Chi Zhang

Denosing diffusion model, as a generative model, has received a lot of attention in the field of image generation recently, thanks to its powerful generation capability. However, diffusion models have not yet received sufficient research in…

Computer Vision and Pattern Recognition · Computer Science 2023-04-12 ZiHan Cao , ShiQi Cao , Xiao Wu , JunMing Hou , Ran Ran , Liang-Jian Deng

Reinforcement Learning (RL) bears the promise of being a game-changer in many applications. However, since most of the literature in the field is currently focused on opaque models, the use of RL in high-stakes scenarios, where…

Machine Learning · Computer Science 2025-01-22 Leonardo Lucio Custode , Giovanni Iacca

Denoising diffusion models (DDMs) have recently attracted increasing attention by showing impressive synthesis quality. DDMs are built on a diffusion process that pushes data to the noise distribution and the models learn to denoise. In…

Machine Learning · Computer Science 2023-05-16 Jaemoo Choi , Yesom Park , Myungjoo Kang

Recent advances of Reinforcement Learning (RL) have highlighted its potential in complex reasoning tasks, yet effective training often relies on external supervision, which limits the broader applicability. In this work, we propose a novel…

Artificial Intelligence · Computer Science 2025-06-11 Kongcheng Zhang , Qi Yao , Shunyu Liu , Yingjie Wang , Baisheng Lai , Jieping Ye , Mingli Song , Dacheng Tao