English
Related papers

Related papers: Step-level Denoising-time Diffusion Alignment with…

200 papers

In traditional reinforcement learning (RL), the learner aims to solve a single objective optimization problem: find the policy that maximizes expected reward. However, in many real-world settings, it is important to optimize over multiple…

Machine Learning · Computer Science 2025-02-18 Eric Eaton , Marcel Hussing , Michael Kearns , Aaron Roth , Sikata Bela Sengupta , Jessica Sorrell

We introduce a reinforcement learning (RL) based adaptive optimization algorithm for aerodynamic shape optimization focused on dimensionality reduction. The form in which RL is applied here is that of a surrogate-based, actor-critic policy…

Meta-reinforcement learning (meta-RL) aims to learn from multiple training tasks the ability to adapt efficiently to unseen test tasks. Despite the success, existing meta-RL algorithms are known to be sensitive to the task distribution…

Machine Learning · Computer Science 2021-03-02 Zichuan Lin , Garrett Thomas , Guangwen Yang , Tengyu Ma

Diffusion distillation is central to accelerating image and video generation, yet existing methods are fundamentally limited by the denoising process, where step reduction has largely saturated. Partial timestep low-resolution generation…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Feiyang Chen , Hongpeng Pan , Haonan Xu , Xinyu Duan , Yang Yang , Zhefeng Wang

We present a novel perspective on goal-conditioned reinforcement learning by framing it within the context of denoising diffusion models. Analogous to the diffusion process, where Gaussian noise is used to create random trajectories that…

Machine Learning · Computer Science 2024-10-29 Vineet Jain , Siamak Ravanbakhsh

Sequential decision-making is desired to align with human intents and exhibit versatility across various tasks. Previous methods formulate it as a conditional generation process, utilizing return-conditioned diffusion models to directly…

Machine Learning · Computer Science 2024-10-11 Xudong Yu , Chenjia Bai , Haoran He , Changhong Wang , Xuelong Li

With the rapid advancement of remote sensing technology, super-resolution image reconstruction is of great research and practical significance. Existing deep learning methods have made progress but still face limitations in handling complex…

Computer Vision and Pattern Recognition · Computer Science 2025-07-24 Shijie Lyu

Masked diffusion language models enable parallel token generation and offer improved decoding efficiency over autoregressive models. However, their performance degrades significantly when generating multiple tokens simultaneously, due to a…

Computation and Language · Computer Science 2026-05-12 Houxing Ren , Mingjie Zhan , Zimu Lu , Ke Wang , Yunqiao Yang , Haotian Hou , Junting Pan , Hongsheng Li

Diffusion models excel in generative tasks, but aligning them with specific objectives while maintaining their versatility remains challenging. Existing fine-tuning methods often suffer from reward over-optimization, while approximate…

Machine Learning · Computer Science 2025-04-18 Sunwoo Kim , Minkyu Kim , Dongmin Park

Diffusion Models (DMs), as a leading class of generative models, offer key advantages for reinforcement learning (RL), including multi-modal expressiveness, stable training, and trajectory-level planning. This survey delivers a…

Machine Learning · Computer Science 2025-10-15 Changfu Xu , Jianxiong Guo , Yuzhu Liang , Haiyang Huang , Haodong Zou , Xi Zheng , Shui Yu , Xiaowen Chu , Jiannong Cao , Tian Wang

Direct Preference Optimization (DPO) has emerged as a predominant alignment method for diffusion models, facilitating off-policy training without explicit reward modeling. However, its reliance on large-scale, high-quality human preference…

Computer Vision and Pattern Recognition · Computer Science 2026-02-09 Khiem Pham , Quang Nguyen , Tung Nguyen , Jingsen Zhu , Michele Santacatterina , Dimitris Metaxas , Ramin Zabih

Reinforcement learning from human feedback (RLHF) has evolved to be one of the main methods for fine-tuning large language models (LLMs). However, existing RLHF methods are non-robust, and their performance deteriorates if the downstream…

Machine Learning · Computer Science 2025-03-04 Debmalya Mandal , Paulius Sasnauskas , Goran Radanovic

This paper investigates the application of Diffusion Policy in non-stationary, vision-based RL settings, specifically targeting environments where task dynamics and objectives evolve over time. Our work is grounded in practical challenges…

Artificial Intelligence · Computer Science 2025-04-02 Gunbir Singh Baveja

Image-based motion prediction is one of the essential techniques for robot manipulation. Among the various prediction models, we focus on diffusion models because they have achieved state-of-the-art performance in various applications. In…

Computer Vision and Pattern Recognition · Computer Science 2023-06-19 Takeru Oba , Norimichi Ukita

We propose Flow-GRPO, the first method to integrate online policy gradient reinforcement learning (RL) into flow matching models. Our approach uses two key strategies: (1) an ODE-to-SDE conversion that transforms a deterministic Ordinary…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Jie Liu , Gongye Liu , Jiajun Liang , Yangguang Li , Jiaheng Liu , Xintao Wang , Pengfei Wan , Di Zhang , Wanli Ouyang

Recently, there has been an increased interest in the practical problem of learning multiple dense scene understanding tasks from partially annotated data, where each training sample is only labeled for a subset of the tasks. The missing of…

Computer Vision and Pattern Recognition · Computer Science 2024-03-25 Hanrong Ye , Dan Xu

Reinforcement learning (RL) allows an agent interacting sequentially with an environment to maximize its long-term expected return. In the distributional RL (DistrRL) paradigm, the agent goes beyond the limit of the expected value, to…

Machine Learning · Computer Science 2023-05-01 Mastane Achab , Reda Alami , Yasser Abdelaziz Dahou Djilali , Kirill Fedyanin , Eric Moulines

Fine-tuning Diffusion Models remains an underexplored frontier in generative artificial intelligence (GenAI), especially when compared with the remarkable progress made in fine-tuning Large Language Models (LLMs). While cutting-edge…

Machine Learning · Computer Science 2024-02-16 Huizhuo Yuan , Zixiang Chen , Kaixuan Ji , Quanquan Gu

Imitation learning is an efficient method for teaching robots a variety of tasks. Diffusion Policy, which uses a conditional denoising diffusion process to generate actions, has demonstrated superior performance, particularly in learning…

Robotics · Computer Science 2025-08-14 Zhuoqun Chen , Xiu Yuan , Tongzhou Mu , Hao Su

Reward-based fine-tuning steers a pretrained diffusion or flow-based generative model toward higher-reward samples while remaining close to the pretrained model. Although existing methods are derived from different perspectives, we show…

Machine Learning · Computer Science 2026-05-08 Jeongjae Lee , Jinho Chang , Jeongsol Kim , Jong Chul Ye