English
Related papers

Related papers: Unifying Group-Relative and Self-Distillation Poli…

200 papers

Reinforcement Learning with Verifiable Rewards (RLVR) has catalyzed a leap in Large Language Model (LLM) reasoning, yet its optimization dynamics remain fragile. Standard algorithms like GRPO enforce stability via "hard clipping", which…

Machine Learning · Computer Science 2026-04-21 Xiaoliang Fu , Jiaye Lin , Yangyi Fang , Chaowen Hu , Cong Qin , Zekai Shao , Binbin Zheng , Lu Pan , Ke Zeng

Fine-tuning pre-trained generative models with Reinforcement Learning (RL) has emerged as an effective approach for aligning outputs more closely with nuanced human preferences. In this paper, we investigate the application of Group…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Matteo Gallici , Haitz Sáez de Ocáriz Borde

Reinforcement Learning with Human Feedback (RLHF) has been the dominant approach for improving the reasoning capabilities of Large Language Models (LLMs). Recently, Reinforcement Learning with Verifiable Rewards (RLVR) has simplified this…

Computation and Language · Computer Science 2025-10-10 Yining Wang , Jinman Zhao , Chuangxin Zhao , Shuhao Guan , Gerald Penn , Shinan Liu

Group Relative Policy Optimization (GRPO) has shown promise in aligning image and video generative models with human preferences. However, applying it to modern flow matching models is challenging because of its deterministic sampling…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Dailan He , Guanlin Feng , Xingtong Ge , Yazhe Niu , Yi Zhang , Bingqi Ma , Guanglu Song , Yu Liu , Hongsheng Li

Reinforcement learning (RL) plays an increasingly important role in enhancing the reasoning capabilities of large language models (LLMs), yet stable and performant policy optimization remains challenging. Token-level importance ratios often…

Machine Learning · Computer Science 2025-12-02 Chang Gao , Chujie Zheng , Xiong-Hui Chen , Kai Dang , Shixuan Liu , Bowen Yu , An Yang , Shuai Bai , Jingren Zhou , Junyang Lin

In the post-training of large language models (LLMs), Reinforcement Learning from Human Feedback (RLHF) is an effective approach to achieve generation aligned with human preferences. Direct Preference Optimization (DPO) allows for policy…

Machine Learning · Computer Science 2025-06-16 Motoki Omura , Yasuhiro Fujita , Toshiki Kataoka

Standard reinforcement learning from human feedback (RLHF) trains a reward model on pairwise preference data and then uses it for policy optimization. However, while reward models are optimized to capture relative preferences, existing…

Machine Learning · Computer Science 2026-02-05 Kyuseong Choi , Dwaipayan Saha , Woojeong Kim , Anish Agarwal , Raaz Dwivedi

Direct Preference Optimization (DPO) has emerged as a prominent algorithm for the direct and robust alignment of Large Language Models (LLMs) with human preferences, offering a more straightforward alternative to the complex Reinforcement…

Computation and Language · Computer Science 2024-12-10 Junru Lu , Jiazheng Li , Siyu An , Meng Zhao , Yulan He , Di Yin , Xing Sun

Search-augmented reasoning agents interleave internal reasoning with calls to an external retriever, and their performance relies on the quality of each issued query. However, under outcome-reward reinforcement learning, every search…

Artificial Intelligence · Computer Science 2026-05-19 Yufei Ma , Zihan Liang , Ben Chen , Zhipeng Qian , Huangyu Dai , Lingtao Mao , Xuxin Zhang , Chenyi Lei , Wenwu Ou

LLM-based search agents are increasingly trained on entity-centric synthetic data to solve complex, knowledge-intensive tasks. However, prevailing training methods like Group Relative Policy Optimization (GRPO) discard this rich entity…

Computation and Language · Computer Science 2026-02-25 Yida Zhao , Kuan Li , Xixi Wu , Liwen Zhang , Dingchu Zhang , Baixuan Li , Maojia Song , Zhuo Chen , Chenxi Wang , Xinyu Wang , Kewei Tu , Pengjun Xie , Jingren Zhou , Yong Jiang

Test-time scaling has proven effective in further enhancing the performance of pretrained Large Language Models (LLMs). However, mainstream post-training methods (i.e., reinforcement learning (RL) with chain-of-thought (CoT) reasoning)…

Machine Learning · Computer Science 2025-08-19 Yuyang Xu , Yi Cheng , Haochao Ying , Zhuoyun Du , Renjun Hu , Xing Shi , Wei Lin , Jian Wu

Group Relative Policy Optimization (GRPO) has proven highly effective in enhancing the alignment capabilities of Large Language Models (LLMs). However, current adaptations of GRPO for the flow matching-based image generation neglect a…

Machine Learning · Computer Science 2025-12-16 Yawen Shao , Jie Xiao , Kai Zhu , Yu Liu , Wei Zhai , Yang Cao , Zheng-Jun Zha

Recent advancements have established Reinforcement Learning (RL) as a pivotal paradigm for aligning generative models with human intent. However, group-based optimization frameworks (e.g., GRPO) face a critical limitation: the rapid decay…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Sujie Hu , Chubin Chen , Jiashu Zhu , Jiahong Wu , Xiangxiang Chu , Xiu Li

In this paper, we introduce \emph{refined Direct Preference Optimization} (rDPO), a method for improving the behavioral alignment of Large Language Models (LLMs) without the need for human-annotated data. The method involves creating…

Computation and Language · Computer Science 2024-02-14 Víctor Gallego

Direct Preference Optimization (DPO) and its variants have become the de facto standards for aligning large language models (LLMs) with human preferences or specific goals. However, DPO requires high-quality preference data and suffers from…

Machine Learning · Computer Science 2024-11-12 Zhuotong Chen , Fang Liu , Jennifer Zhu , Wanyu Du , Yanjun Qi

Aligning text-to-image (T2I) diffusion models with Direct Preference Optimization (DPO) has shown notable improvements in generation quality. However, applying DPO to T2I faces two challenges: the sensitivity of DPO to preference pairs and…

Computer Vision and Pattern Recognition · Computer Science 2025-05-19 Renjie Chen , Wenfeng Lin , Yichen Zhang , Jiangchuan Wei , Boyuan Liu , Chao Feng , Jiao Ran , Mingyu Guo

Reinforcement Learning with Verifiable Rewards (RLVR) is commonly based on group sampling to estimate advantages and stabilize policy updates. In practice, computational limits often rule out very large groups, so training proceeds with…

We present Anchored Direct Preference Optimization (ADPO), a policy alignment method derived from first principles of KL-regularized reinforcement learning. Unlike standard approaches that treat the reference policy merely as a regularizer,…

Machine Learning · Computer Science 2026-01-13 Wang Zixian

Critic-free methods like GRPO reduce memory demands by estimating advantages from multiple rollouts but tend to converge slowly, as critical learning signals are diluted by an abundance of uninformative samples and tokens. To tackle this…

Machine Learning · Computer Science 2025-09-29 Chao Wang , Tao Yang , Hongtao Tian , Yunsheng Shi , Qiyao Ma , Xiaotao Liu , Ting Yao , Wenbo Ding

Improving and understanding the training dynamics and reasoning of Large Language Models (LLMs) has become essential for their deployment in AI-based security tools, such as software vulnerability detection. In this work, we present an…

Cryptography and Security · Computer Science 2025-07-08 Marco Simoni , Aleksandar Fontana , Giulio Rossolini , Andrea Saracino
‹ Prev 1 8 9 10 Next ›