English
Related papers

Related papers: Blockwise Advantage Estimation for Multi-Objective…

200 papers

Direct Preference Optimization is an offline post-SFT method for aligning language models from preference pairs, with strong results in instruction following and summarization. However, DPO's sequence-level implicit reward can be brittle…

Computation and Language · Computer Science 2026-03-03 Samah Fodeh , Linhai Ma , Ganesh Puthiaraju , Srivani Talakokkul , Afshan Khan , Ashley Hagaman , Sarah R. Lowe , Aimee Kendall Roundtree

Generative recommendation treats next-item prediction as autoregressive item-identifier generation. Specifically, items are encoded as semantic identifiers (SIDs), which are short coarse-to-fine token sequences whose early tokens capture…

Artificial Intelligence · Computer Science 2026-05-19 Zaiyi Zheng , Guanghui Min , Yaochen Zhu , Liang Wu , Liangjie Hong , Chen Chen , Jundong Li

Large language model (LLM)-based agents are increasingly trained with reinforcement learning (RL) to enhance their ability to interact with external environments through tool use, particularly in search-based settings that require…

Computation and Language · Computer Science 2026-03-25 Guoqing Wang , Sunhao Dai , Guangze Ye , Zeyu Gan , Wei Yao , Yong Deng , Xiaofeng Wu , Zhenzhe Ying

Reinforcement learning (RL), particularly GRPO, improves image generation quality significantly by comparing the relative performance of images generated within the same group. However, in the later stages of training, the model tends to…

Computer Vision and Pattern Recognition · Computer Science 2025-12-29 Henglin Liu , Huijuan Huang , Jing Wang , Chang Liu , Xiu Li , Xiangyang Ji

Existing policy-gradient methods for auto-regressive language models typically select subsequent tokens one at a time as actions in the policy. While effective for many generation tasks, such an approach may not fully capture the structure…

Computation and Language · Computer Science 2026-02-17 Mufan Xu , Kehai Chen , Xuefeng Bai , Zhengyu Niu , Muyun Yang , Tiejun Zhao , Min Zhang

Group Relative Policy Optimization (GRPO) is a standard algorithm for reinforcement learning from verifiable rewards, but its group-mean-centered advantage can fail under binary rewards. The failure mode is gradient starvation: when every…

Machine Learning · Computer Science 2026-05-11 Wenhua Nie , Jianan Wu , Junlin Liu , Ziwei Li , Zheng Lin , Zhang Zijian , Yilong Fan , Haoran Zheng , Jyh-Shing Roger Jang

Reinforcement learning has become a cornerstone for enhancing the reasoning capabilities of Large Language Models, where group-based approaches such as GRPO have emerged as efficient paradigms that optimize policies by leveraging…

Recent progress in aligning image and video generative models with Group Relative Policy Optimization (GRPO) has improved human preference alignment, but existing variants remain inefficient due to sequential rollouts and large numbers of…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Yuming Li , Yikai Wang , Yuying Zhu , Zhongyu Zhao , Ming Lu , Qi She , Shanghang Zhang

Group Relative Policy Optimization (GRPO) is highly effective for post-training autoregressive (AR) language models, yet its direct application to diffusion large language models (dLLMs) often triggers reward collapse. We identify two…

Machine Learning · Computer Science 2026-03-10 Jianyuan Zhong , Kaibo Wang , Ding Ding , Zijin Feng , Haoli Bai , Yang Xiang , Jiacheng Sun , Qiang Xu

Recent advancements in reinforcement learning from human feedback have shown that utilizing fine-grained token-level reward models can substantially enhance the performance of Proximal Policy Optimization (PPO) in aligning large language…

Machine Learning · Computer Science 2025-06-18 Mingkang Zhu , Xi Chen , Zhongdao Wang , Bei Yu , Hengshuang Zhao , Jiaya Jia

Reinforcement learning from human feedback (RLHF) or verifiable rewards (RLVR), the standard paradigm for aligning LLMs or building recent SOTA reasoning models, is highly sensitive to noise from inconsistent or erroneous rewards. Yet, the…

Machine Learning · Computer Science 2026-05-20 Omar El Mansouri , Fathinah Asma Izzati , Mohamed El Amine Seddik , Salem Lahlou

Recent progress in large language models (LLMs) has boosted mathematical reasoning, yet geometry remains challenging where auxiliary construction is often essential. Prior methods either underperform or depend on very large models (e.g.,…

Computation and Language · Computer Science 2026-04-21 Yikun Wang , Yibin Wang , Dianyi Wang , Zimian Peng , Qipeng Guo , Dacheng Tao , Jiaqi Wang

Reinforcement learning is emerging as a primary driver for improving language model reasoning capabilities. A fundamental question is whether current reinforcement learning algorithms -- such as Group Relative Policy Optimization (GRPO),…

Machine Learning · Computer Science 2025-06-23 Andre He , Daniel Fried , Sean Welleck

The recent success and openness of DeepSeek-R1 have brought widespread attention to Group Relative Policy Optimization (GRPO) as a reinforcement learning method for large reasoning models (LRMs). In this work, we analyze the GRPO objective…

Machine Learning · Computer Science 2026-01-07 Gang Li , Ming Lin , Tomer Galanti , Zhengzhong Tu , Tianbao Yang

A key challenge in applying reinforcement learning (RL) to diffusion large language models (dLLMs) lies in the intractability of their likelihood functions, which are essential for the RL objective, necessitating corresponding approximation…

Machine Learning · Computer Science 2025-10-15 Nianyi Lin , Jiajie Zhang , Lei Hou , Juanzi Li

Group Relative Policy Optimization (GRPO) has emerged as the de facto Reinforcement Learning (RL) objective driving recent advancements in Multimodal Large Language Models. However, extending this success to open-source multimodal…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Wenbo Hu , Xin Chen , Yan Gao-Tian , Yihe Deng , Nanyun Peng , Kai-Wei Chang

Diffusion large language models (dLLMs), which offer a promising alternative to traditional autoregressive LLMs, have recently shown strong results in pretraining. However, due to their lack of tractable sequence-level likelihoods, they…

Machine Learning · Computer Science 2026-02-03 Anthony Zhan

Multi-turn human-AI collaboration is fundamental to deploying interactive services such as adaptive tutoring, conversational recommendation, and professional consultation. However, optimizing these interactions via reinforcement learning is…

Machine Learning · Computer Science 2026-03-26 Haoyu Wang , Yuxin Chen , Liang Luo , Buyun Zhang , Ellie Dingqiao Wen , Pan Li

Group Relative Policy Optimization (GRPO) enhances policy learning by computing gradients from relative comparisons among candidate outputs that share a common input prefix. Despite its effectiveness, GRPO introduces substantial…

Machine Learning · Computer Science 2025-06-09 Zikang Liu , Tongtian Yue , Yepeng Tang , Longteng Guo , Junxian Cai , Qingbin Liu , Xi Chen , Jing Liu

Group-Relative Policy Optimization (GRPO) is a key technique for training large reasoning models, yet it suffers from a critical vulnerability: the \emph{Think-Answer Mismatch}, where noisy reward signals corrupt the learning process. This…

Machine Learning · Computer Science 2025-08-11 Si Shen , Peijun Shen , Wenhua Zhao , Danhao Zhu
‹ Prev 1 8 9 10 Next ›