English
Related papers

Related papers: PCPO: Proportionate Credit Policy Optimization for…

200 papers

Despite rapid advances in text-to-image generation, faithfully realizing user intent remains challenging, often requiring manual multi-turn trial and error. To automate this process, existing systems rely on either simple prompt rewriting…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Jinming Liu , Ruoyu Feng , Yuqi Wang , Wenjun Zeng , Xin Jin

Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning abilities of Large Language Models (LLMs) by using rule-based binary feedback. However, current RLVR methods typically assign the same reward to every token.…

Machine Learning · Computer Science 2025-10-21 Guofu Xie , Yunsheng Shi , Hongtao Tian , Ting Yao , Xiao Zhang

Direct Preference Optimization (DPO) has been proposed as an effective and efficient alternative to reinforcement learning from human feedback (RLHF). In this paper, we propose a novel and enhanced version of DPO based on curriculum…

Computer Vision and Pattern Recognition · Computer Science 2025-05-12 Florinel-Alin Croitoru , Vlad Hondru , Radu Tudor Ionescu , Nicu Sebe , Mubarak Shah

Optical computing holds promise for high-speed, energy-efficient information processing, with diffractive optical networks emerging as a flexible platform for implementing task-specific transformations. A challenge, however, is the…

Machine Learning · Computer Science 2026-01-05 Yuhang Li , Shiqi Chen , Tingyu Gong , Aydogan Ozcan

In sequence generation task, many works use policy gradient for model optimization to tackle the intractable backpropagation issue when maximizing the non-differentiable evaluation metrics or fooling the discriminator in adversarial…

Computation and Language · Computer Science 2018-08-27 Yi-Lin Tuan , Jinzhi Zhang , Yujia Li , Hung-yi Lee

Training stability remains a critical bottleneck for Group Relative Policy Optimization (GRPO), often manifesting as a trade-off between reasoning plasticity and general capability retention. We identify a root cause as the geometric…

Machine Learning · Computer Science 2026-02-09 Wenwen Qiang , Ziyin Gu , Jiahuan Zhou , Jie Hu , Jingyao Wang , Changwen Zheng , Hui Xiong

Reinforcement learning (RL) has become a powerful tool for post-training visual generative models, with Group Relative Policy Optimization (GRPO) increasingly used to align generators with human preferences. However, existing GRPO pipelines…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Ziqi Ni , Yuanzhi Liang , Rui Li , Yi Zhou , Haibin Huang , Chi Zhang , Xuelong Li

Latent diffusion models are the state-of-the-art for synthetic image generation. To align these models with human preferences, training the models using reinforcement learning on human feedback is crucial. Black et. al 2024 introduced…

Machine Learning · Computer Science 2024-04-09 Mo Kordzanganeh , Danial Keshvary , Nariman Arian

Group Relative Policy Optimization has emerged as essential for aligning video diffusion models with human preferences, but faces a critical computational bottleneck: training a 14B parametered model typically demands hundreds of GPU days…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Xiaoxuan He , Siming Fu , Zeyue Xue , Weijie Wang , Ruizhe He , Yuming Li , Dacheng Yin , Shuai Dong , Haoyang Huang , Hongfa Wang , Nan Duan , Bohan Zhuang

Safe Reinforcement Learning (RL) often faces significant issues such as constraint violations and instability, necessitating the use of constrained policy optimization, which seeks optimal policies while ensuring adherence to specific…

Machine Learning · Computer Science 2025-08-07 Ning Yang , Pengyu Wang , Guoqing Liu , Haifeng Zhang , Pin Lv , Jun Wang

To enhance controllability in text-to-image generation, ControlNet introduces image-based control signals, while ControlNet++ improves pixel-level cycle consistency between generated images and the input control signal. To avoid the…

Computer Vision and Pattern Recognition · Computer Science 2025-11-10 Zonglin Lyu , Ming Li , Xinxin Liu , Chen Chen

Large language models (LLMs) are increasingly applied to complex reasoning tasks that require executing several complex steps before receiving any reward. Properly assigning credit to these steps is essential for enhancing model…

Constrained reinforcement learning has achieved promising progress in safety-critical fields where both rewards and constraints are considered. However, constrained reinforcement learning methods face challenges in striking the right…

Machine Learning · Computer Science 2024-10-29 Jianmina Ma , Jingtian Ji , Yue Gao

Traditional policy gradient methods are fundamentally flawed. Natural gradients converge quicker and better, forming the foundation of contemporary Reinforcement Learning such as Trust Region Policy Optimization (TRPO) and Proximal Policy…

Machine Learning · Computer Science 2022-09-07 W. J. A. van Heeswijk

Reinforcement Learning, particularly through policy gradient methods, has played a central role in enabling reasoning capabilities of Large Language Models. However, the optimization stability of policy gradients in this setting remains…

Machine Learning · Computer Science 2026-03-03 Luckeciano C. Melo , Alessandro Abate , Yarin Gal

Reinforcement learning is crucial for aligning large language models to perform complex reasoning tasks. However, current algorithms such as Group Relative Policy Optimization suffer from coarse grained, sequence level credit assignment,…

Machine Learning · Computer Science 2026-05-11 Hongbo Jin , Rongpeng Zhu , Zhongjing Du , Xu Jiang , Jingqi Tian , Qiaoman Zhang , Jiayu Ding

Text-to-image generation has evolved beyond single monolithic models to complex multi-component pipelines. These combine fine-tuned generators, adapters, upscaling blocks and even editing steps, leading to significant improvements in image…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Uri Gadot , Rinon Gal , Yftah Ziser , Gal Chechik , Shie Mannor

We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent.…

Machine Learning · Computer Science 2017-08-29 John Schulman , Filip Wolski , Prafulla Dhariwal , Alec Radford , Oleg Klimov

Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles, but reinforcement learning for such systems is limited by credit assignment: shared terminal rewards obscure individual…

Artificial Intelligence · Computer Science 2026-05-27 Zhongyi Li , Wan Tian , Yikun Ban , Jinju Chen , Huiming Zhang , Yang Liu , Fuzhen Zhuang

While Reinforcement Learning from Verifiable Rewards (RLVR) has advanced reasoning in Large Vision-Language Models (LVLMs), prevailing frameworks suffer from a foundational methodological flaw: by distributing identical advantages across…

Artificial Intelligence · Computer Science 2026-04-09 Zekai Ye , Qiming Li , Xiaocheng Feng , Ruihan Chen , Ziming Li , Haoyu Ren , Kun Chen , Dandan Tu , Bing Qin