English
Related papers

Related papers: Fast and Stable Diffusion Planning through Variati…

200 papers

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

Acquiring high-quality data for training discriminative models is a crucial yet challenging aspect of building effective predictive systems. In this paper, we present Diffusion Inversion, a simple yet effective method that leverages the…

Computer Vision and Pattern Recognition · Computer Science 2023-05-25 Yongchao Zhou , Hshmat Sahak , Jimmy Ba

Diffusion Language Models (dLLMs) have emerged as promising alternatives to Auto-Regressive (AR) models. While recent efforts have validated their pre-training potential and accelerated inference speeds, the post-training landscape for…

Machine Learning · Computer Science 2026-01-07 Ying Zhu , Jiaxin Wan , Xiaoran Liu , Siyang He , Qiqi Wang , Xu Guo , Tianyi Liang , Zengfeng Huang , Ziwei He , Xipeng Qiu

Modern reinforcement learning (RL) algorithms have found success by using powerful probabilistic models, such as transformers, energy-based models, and diffusion/flow-based models. To this end, RL researchers often choose to pay the price…

Machine Learning · Computer Science 2025-06-05 Raj Ghugare , Benjamin Eysenbach

Diffusion Policy is a powerful technique tool for learning end-to-end visuomotor robot control. It is expected that Diffusion Policy possesses scalability, a key attribute for deep neural networks, typically suggesting that increasing model…

We propose DiFFPO, Diffusion Fast and Furious Policy Optimization, a unified framework for training masked diffusion large language models (dLLMs) to reason not only better (furious), but also faster via reinforcement learning (RL). We…

Machine Learning · Computer Science 2026-01-13 Hanyang Zhao , Dawen Liang , Wenpin Tang , David Yao , Nathan Kallus

Among the reasons hindering reinforcement learning (RL) applications to real-world problems, two factors are critical: limited data and the mismatch between the testing environment (real environment in which the policy is deployed) and the…

Machine Learning · Computer Science 2023-01-30 Xiaoteng Ma , Zhipeng Liang , Jose Blanchet , Mingwen Liu , Li Xia , Jiheng Zhang , Qianchuan Zhao , Zhengyuan Zhou

Training neural samplers directly from unnormalized densities without access to target distribution samples presents a significant challenge. A critical desideratum in these settings is achieving comprehensive mode coverage, ensuring the…

Machine Learning · Computer Science 2025-05-27 Chenguang Wang , Xiaoyu Zhang , Kaiyuan Cui , Weichen Zhao , Yongtao Guan , Tianshu Yu

One of the key challenges that Reinforcement Learning (RL) faces is its limited capability to adapt to a change of data distribution caused by uncertainties. This challenge arises especially in RL systems using deep neural networks as…

Machine Learning · Computer Science 2025-06-17 Amornyos Horprasert , Esa Apriaskar , Xingyu Liu , Lanlan Su , Lyudmila S. Mihaylova

Video Diffusion Models (VDMs) can generate high-quality videos, but often struggle with producing temporally coherent motion. Optical flow supervision is a promising approach to address this, with prior works commonly employing…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Kuanting Wu , Kei Ota , Asako Kanezaki

We investigate reinforcement learning (RL) in the presence of distributional mismatch between training and deployment, where policies trained in simulators often underperform in practice due to mismatches between training and deployment…

Machine Learning · Computer Science 2025-11-12 Debamita Ghosh , George K. Atia , Yue Wang

It has been recognized that the data generated by the denoising diffusion probabilistic model (DDPM) improves adversarial training. After two years of rapid development in diffusion models, a question naturally arises: can better diffusion…

Computer Vision and Pattern Recognition · Computer Science 2023-06-02 Zekai Wang , Tianyu Pang , Chao Du , Min Lin , Weiwei Liu , Shuicheng Yan

Masked diffusion models (MDMs) are a promising alternative to autoregressive models (ARMs), but they suffer from inherently much higher training variance. High variance leads to noisier gradient estimates and unstable optimization, so even…

Machine Learning · Computer Science 2026-05-22 Mengni Jia , Mengyu Zhou , Yihao Liu , Xiaoxi Jiang , Guanjun Jiang

We study value adaptation in offline-to-online reinforcement learning under general function approximation. Starting from an imperfect offline pretrained $Q$-function, the learner aims to adapt it to the target environment using only a…

Machine Learning · Computer Science 2026-04-16 Shangzhe Li , Weitong Zhang

Large-scale diffusion models like Stable Diffusion are powerful and find various real-world applications while customizing such models by fine-tuning is both memory and time inefficient. Motivated by the recent progress in natural language…

Computer Vision and Pattern Recognition · Computer Science 2023-04-13 Chendong Xiang , Fan Bao , Chongxuan Li , Hang Su , Jun Zhu

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

Reinforcement learning has been widely applied to diffusion and flow models for visual tasks such as text-to-image generation. However, these tasks remain challenging because diffusion models have intractable likelihoods, which creates a…

Machine Learning · Computer Science 2026-05-20 Jaemoo Choi , Yuchen Zhu , Wei Guo , Petr Molodyk , Bo Yuan , Jinbin Bai , Yi Xin , Molei Tao , Yongxin Chen

In offline reinforcement learning (RL), the performance of the learned policy highly depends on the quality of offline datasets. However, in many cases, the offline dataset contains very limited optimal trajectories, which poses a challenge…

Machine Learning · Computer Science 2024-02-23 Guanghe Li , Yixiang Shan , Zhengbang Zhu , Ting Long , Weinan Zhang

Diffusion-based models have achieved notable empirical successes in reinforcement learning (RL) due to their expressiveness in modeling complex distributions. Despite existing methods being promising, the key challenge of extending existing…

Machine Learning · Computer Science 2024-11-04 Dmitry Shribak , Chen-Xiao Gao , Yitong Li , Chenjun Xiao , Bo Dai

Diffusion models have shown an impressive ability to model complex data distributions, with several key advantages over GANs, such as stable training, better coverage of the training distribution's modes, and the ability to solve inverse…

Computer Vision and Pattern Recognition · Computer Science 2024-06-12 Yinbo Chen , Oliver Wang , Richard Zhang , Eli Shechtman , Xiaolong Wang , Michael Gharbi