English
Related papers

Related papers: MAR-GRPO: Stabilized GRPO for AR-diffusion Hybrid …

200 papers

Multi-agent LLM systems enable advanced reasoning and tool use via role specialization, yet reliable reinforcement learning (RL) post-training for such systems remains difficult. In this work, we theoretically pinpoint a key reason for…

Machine Learning · Computer Science 2026-02-10 Lang Feng , Longtao Zheng , Shuo He , Fuxiang Zhang , Bo An

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

Reinforcement learning (RL) has emerged as a crucial approach for enhancing the capabilities of large language models. However, in Mixture-of-Experts (MoE) models, the routing mechanism often introduces instability, even leading to…

Computation and Language · Computer Science 2025-10-22 Wenhan Ma , Hailin Zhang , Liang Zhao , Yifan Song , Yudong Wang , Zhifang Sui , Fuli Luo

Reinforcement learning (RL), earlier proven to be effective in large language and multi-modal models, has been successfully extended to enhance 2D image generation recently. However, applying RL to 3D generation remains largely unexplored…

Computer Vision and Pattern Recognition · Computer Science 2025-12-12 Yiwen Tang , Zoey Guo , Kaixin Zhu , Ray Zhang , Qizhi Chen , Dongzhi Jiang , Junli Liu , Bohan Zeng , Haoming Song , Delin Qu , Tianyi Bai , Dan Xu , Wentao Zhang , Bin Zhao

Training large language models (LLMs) as interactive agents presents unique challenges including long-horizon decision making and interacting with stochastic environment feedback. While reinforcement learning (RL) has enabled progress in…

Recent advances in reinforcement learning (RL) have substantially improved the training of large-scale language models, leading to significant gains in generation quality and reasoning ability. However, most existing research focuses on…

Machine Learning · Computer Science 2026-01-13 Di Zhang , Xun Wu , Shaohan Huang , Lingjie Jiang , Yaru Hao , Li Dong , Zewen Chi , Zhifang Sui , Furu Wei

Reinforcement Learning (RL) in Traffic Signal Control (TSC) faces significant hurdles in real-world deployment due to limited generalization to dynamic traffic flow variations. Existing approaches often overfit static patterns and use…

Artificial Intelligence · Computer Science 2026-03-13 Sheng-You Huang , Hsiao-Chuan Chang , Yen-Chi Chen , Ting-Han Wei , I-Hau Yeh , Sheng-Yao Kuan , Chien-Yao Wang , Hsuan-Han Lee , I-Chen Wu

Aligning denoising generative models with human preferences or verifiable rewards remains a key challenge. While policy-gradient online reinforcement learning (RL) offers a principled post-training framework, its direct application is…

Machine Learning · Computer Science 2026-04-28 Bingda Tang , Yuhui Zhang , Xiaohan Wang , Jiayuan Mao , Ludwig Schmidt , Serena Yeung-Levy

As single-center computing approaches power constraints, decentralized training becomes essential. However, traditional Reinforcement Learning (RL) methods, crucial for enhancing large model post-training, cannot adapt to decentralized…

Uniform Discrete Diffusion Model (UDM) has recently emerged as a promising paradigm for discrete generative modeling; however, its integration with reinforcement learning remains largely unexplored. We observe that naively applying GRPO to…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Jiaqi Wang , Haoge Deng , Ting Pan , Yang Liu , Chengyuan Wang , Fan Zhang , Yonggang Qi , Xinlong Wang

Autoregressive (AR) models remain the standard for natural language generation but still suffer from high latency due to strictly sequential decoding. Recent diffusion-inspired approaches, such as LlaDA and Dream, mitigate this by…

Computation and Language · Computer Science 2025-10-16 Qinglin Zhu , Yizhen Yao , Runcong Zhao , Yanzheng Xiang , Amrutha Saseendran , Chen Jin , Philip Teare , Bin Liang , Yulan He , Lin Gui

High-level autonomous driving requires motion planners capable of modeling multimodal future uncertainties while remaining robust in closed-loop interactions. Although diffusion-based planners are effective at modeling complex trajectory…

Computer Vision and Pattern Recognition · Computer Science 2026-04-17 Hao Gao , Shaoyu Chen , Yifan Zhu , Yuehao Song , Wenyu Liu , Qian Zhang , Xinggang Wang

Recent advancements in multi-modal large language models have propelled the development of joint probabilistic models capable of both image understanding and generation. However, we have identified that recent methods suffer from loss of…

Computer Vision and Pattern Recognition · Computer Science 2025-06-05 Jian Yang , Dacheng Yin , Yizhou Zhou , Fengyun Rao , Wei Zhai , Yang Cao , Zheng-Jun Zha

Recent advancements underscore the significant role of Reinforcement Learning (RL) in enhancing the Chain-of-Thought (CoT) reasoning capabilities of large language models (LLMs). Two prominent RL algorithms, Direct Preference Optimization…

Computer Vision and Pattern Recognition · Computer Science 2025-06-11 Chengzhuo Tong , Ziyu Guo , Renrui Zhang , Wenyu Shan , Xinyu Wei , Zhenghao Xing , Hongsheng Li , Pheng-Ann Heng

The teleoperated driving (TD) scenario comes with stringent Quality of Service (QoS) communication constraints, especially in terms of end-to-end (E2E) latency and reliability. In this context, Predictive Quality of Service (PQoS), possibly…

Networking and Internet Architecture · Computer Science 2025-05-07 Giacomo Avanzi , Marco Giordani , Michele Zorzi

Differentiable reinforcement learning (RL) frameworks like DiffRO offer a powerful approach for controllable text-to-speech (TTS), but are vulnerable to reward hacking, particularly for nuanced tasks like emotion control. The policy model…

Sound · Computer Science 2026-02-17 Cong Wang , Changfeng Gao , Yang Xiang , Zhihao Du , Keyu An , Han Zhao , Qian Chen , Xiangang Li , Yingming Gao , Ya Li

Mixture-of-Experts (MoE) has emerged as an effective approach to reduce the computational overhead of Transformer architectures by sparsely activating a subset of parameters for each token while preserving high model capacity. This paradigm…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Dohwan Ko , Jinyoung Park , Seoung Choi , Sanghyeok Lee , Seohyun Lee , Hyunwoo J. Kim

Recent advancements adopt online reinforcement learning (RL) from LLMs to text-to-image rectified flow diffusion models for reward alignment. The use of group-level rewards successfully aligns the model with the targeted reward. However, it…

Machine Learning · Computer Science 2026-01-06 Yiyang Wang , Xi Chen , Xiaogang Xu , Yu Liu , Hengshuang Zhao

This paper studies full-body 3D human motion recovery from head-mounted device signals. Existing diffusion-based methods often rely on global distribution matching, leading to local joint reconstruction errors. We propose MotionGRPO, a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Nanjie Yao , Junlong Ren , Wenhao Shen , Hao Wang

Model-based offline reinforcement Learning (RL) is a promising approach that leverages existing data effectively in many real-world applications, especially those involving high-dimensional inputs like images and videos. To alleviate the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-17 Shenghua Wan , Ziyuan Chen , Le Gan , Shuai Feng , De-Chuan Zhan