English
Related papers

Related papers: UDM-GRPO: Stable and Efficient Group Relative Poli…

200 papers

Diffusion policies, widely adopted in decision-making scenarios such as robotics, gaming and autonomous driving, are capable of learning diverse skills from demonstration data due to their high representation power. However, the sub-optimal…

Machine Learning · Computer Science 2025-09-30 Ningyuan Yang , Jiaxuan Gao , Feng Gao , Yi Wu , Chao Yu

Differentially private diffusion models (DPDMs) harness the remarkable generative capabilities of diffusion models while enforcing differential privacy (DP) for sensitive data. However, existing DPDM training approaches often suffer from…

Cryptography and Security · Computer Science 2025-02-19 Tanqiu Jiang , Changjiang Li , Fenglong Ma , Ting Wang

Diffusion Models have emerged as a leading class of generative models, yet their iterative sampling process remains computationally expensive. Timestep distillation is a promising technique to accelerate generation, but it often requires…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Guanjie Chen , Shirui Huang , Kai Liu , Jianchen Zhu , Xiaoye Qu , Peng Chen , Yu Cheng , Yifu Sun

We introduce FedDM, a novel training framework designed for the federated training of diffusion models. Our theoretical analysis establishes the convergence of diffusion models when trained in a federated setting, presenting the specific…

Machine Learning · Computer Science 2024-07-23 Jayneel Vora , Nader Bouacida , Aditya Krishnan , Prasant Mohapatra

Post-training LLMs with Reinforcement Learning, specifically Group Relative Policy Optimization (GRPO), has emerged as a paradigm for enhancing mathematical reasoning. However, standard GRPO relies on scalar correctness rewards that are…

Computation and Language · Computer Science 2026-03-03 Xiwen Chen , Wenhui Zhu , Peijie Qiu , Xuanzhao Dong , Hao Wang , Haiyu Wu , Huayu Li , Aristeidis Sotiras , Yalin Wang , Abolfazl Razi

Diffusion models have garnered widespread attention in Reinforcement Learning (RL) for their powerful expressiveness and multimodality. It has been verified that utilizing diffusion policies can significantly improve the performance of RL…

Machine Learning · Computer Science 2024-12-17 Shutong Ding , Ke Hu , Zhenhao Zhang , Kan Ren , Weinan Zhang , Jingyi Yu , Jingya Wang , Ye Shi

Reinforcement learning (RL) has been successfully applied to autoregressive (AR) and diffusion models. However, extending RL to hybrid AR-diffusion frameworks remains challenging due to interleaved inference and noisy log-probability…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Xiaoxiao Ma , Jiachen Lei , Tianfei Ren , Jie Huang , Siming Fu , Aiming Hao , Jiahong Wu , Xiangxiang Chu , Feng Zhao

Conventional diffusion models typically relies on a fixed forward process, which implicitly defines complex marginal distributions over latent variables. This can often complicate the reverse process' task in learning generative…

Machine Learning · Statistics 2025-06-10 Grigory Bartosh , Dmitry Vetrov , Christian A. Naesseth

Masked diffusion models (MDMs) have recently emerged as a novel framework for language modeling. MDMs generate sentences by iteratively denoising masked sequences, filling in [MASK] tokens step by step. Although MDMs support any-order…

Machine Learning · Computer Science 2026-02-27 Chunsan Hong , Seonho An , Min-Soo Kim , Jong Chul Ye

By formulating data samples' formation as a Markov denoising process, diffusion models achieve state-of-the-art performances in a collection of tasks. Recently, many variants of diffusion models have been proposed to enable controlled…

Machine Learning · Computer Science 2023-04-17 Hengtong Zhang , Tingyang Xu

Online reinforcement learning (RL) has been central to post-training language models, but its extension to diffusion models remains challenging due to intractable likelihoods. Recent works discretize the reverse sampling process to enable…

Machine Learning · Computer Science 2026-02-17 Kaiwen Zheng , Huayu Chen , Haotian Ye , Haoxiang Wang , Qinsheng Zhang , Kai Jiang , Hang Su , Stefano Ermon , Jun Zhu , Ming-Yu Liu

Designing and deriving effective model-based reinforcement learning (MBRL) algorithms with a performance improvement guarantee is challenging, mainly attributed to the high coupling between model learning and policy optimization. Many prior…

Machine Learning · Computer Science 2023-10-25 Hai Zhang , Hang Yu , Junqiao Zhao , Di Zhang , Chang Huang , Hongtu Zhou , Xiao Zhang , Chen Ye

A commonly used family of RL algorithms for diffusion policies conducts softmax reweighting over samples from the behavior policy, which often induces an overgreedy policy and fails to utilize feedback from negative samples. In this work,…

Machine Learning · Computer Science 2026-05-26 Haitong Ma , Chenxiao Gao , Tianyi Chen , Na Li , Bo Dai

Improving the reasoning capabilities of diffusion-based large language models (dLLMs) through reinforcement learning (RL) remains an open problem. The intractability of dLLMs likelihood function necessitates approximating the current, old,…

Machine Learning · Computer Science 2026-02-17 Xiaohang Tang , Rares Dolga , Sangwoong Yoon , Ilija Bogunovic

Direct preference optimization (DPO) methods have shown strong potential in aligning text-to-image diffusion models with human preferences by training on paired comparisons. These methods improve training stability by avoiding the REINFORCE…

Computer Vision and Pattern Recognition · Computer Science 2025-10-22 Yi-Lun Wu , Bo-Kai Ruan , Chiang Tseng , Hong-Han Shuai

Score-based generative models (SGMs) have revolutionized the field of generative modeling, achieving unprecedented success in generating realistic and diverse content. Despite empirical advances, the theoretical basis for why optimizing the…

Machine Learning · Computer Science 2024-08-30 Gen Li , Yuling Yan

Generalizing locomotion policies across diverse legged robots with varying morphologies is a key challenge due to differences in observation/action dimensions and system dynamics. In this work, we propose Multi-Loco, a novel unified…

Robotics · Computer Science 2025-06-16 Shunpeng Yang , Zhen Fu , Zhefeng Cao , Guo Junde , Patrick Wensing , Wei Zhang , Hua Chen

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

Diffusion models have garnered significant attention since they can effectively learn complex multivariate Gaussian distributions, resulting in diverse, high-quality outcomes. They introduce Gaussian noise into training data and reconstruct…

Computer Vision and Pattern Recognition · Computer Science 2023-12-27 Vidya Prasad , Chen Zhu-Tian , Anna Vilanova , Hanspeter Pfister , Nicola Pezzotti , Hendrik Strobelt

Recent advances in generative AI have revolutionized visual content creation, yet aligning model outputs with human preferences remains a critical challenge. While Reinforcement Learning (RL) has emerged as a promising approach for…

Computer Vision and Pattern Recognition · Computer Science 2025-08-29 Zeyue Xue , Jie Wu , Yu Gao , Fangyuan Kong , Lingting Zhu , Mengzhao Chen , Zhiheng Liu , Wei Liu , Qiushan Guo , Weilin Huang , Ping Luo