English
Related papers

Related papers: IRPO: Boosting Image Restoration via Post-training…

200 papers

Large language models (LLMs) trained via pretraining and supervised fine-tuning (SFT) can still produce harmful and misaligned outputs, or struggle in domains like math and coding. Reinforcement learning (RL)-based post-training methods,…

Computation and Language · Computer Science 2026-05-19 Zhichao Wang , Kiran Ramnath , Bin Bi , Shiva Kumar Pentyala , Sougata Chaudhuri , Shubham Mehrotra , Zixu , Zhu , Xiang-Bo Mao , Sitaram Asur , Na , Cheng

The Group Relative Policy Optimization (GRPO), a reinforcement learning method used to fine-tune large language models (LLMs), has proved its effectiveness in practical applications such as DeepSeek-R1. It raises a question whether GRPO can…

Machine Learning · Computer Science 2025-11-20 Yanchen Xu , Ziheng Jiao , Hongyuan Zhang , Xuelong Li

Subject-driven image generation models face a fundamental trade-off between identity preservation (fidelity) and prompt adherence (editability). While online reinforcement learning (RL), specifically GPRO, offers a promising solution, we…

Machine Learning · Computer Science 2026-04-23 Ziwei Huang , Ying Shu , Hao Fang , Quanyu Long , Wenya Wang , Qiushi Guo , Tiezheng Ge , Leilei Gan

Post-training has become essential for adapting large language models (LLMs) to complex downstream behaviors, including instruction following, preference alignment, and multi-step reasoning. Reinforcement learning with verifiable rewards…

Machine Learning · Computer Science 2026-05-20 Chengqian Zhang , Wei Zhu , Kyumin Lee

Image restoration, which aims to retrieve and enhance degraded images, is fundamental across a wide range of applications. While conventional deep learning approaches have notably improved the image quality across various tasks, they still…

Computer Vision and Pattern Recognition · Computer Science 2023-12-11 Zilong Li , Yiming Lei , Chenglong Ma , Junping Zhang , Hongming Shan

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

Group Relative Policy Optimization (GRPO) has recently shown strong performance in post-training large language models and vision-language models. It raises a question of whether the GRPO also significantly promotes the test-time adaptation…

Computer Vision and Pattern Recognition · Computer Science 2026-05-06 Yujun Li , Hongyuan Zhang , Yuan Yuan

Deep image restoration models aim to learn a mapping from degraded image space to natural image space. However, they face several critical challenges: removing degradation, generating realistic details, and ensuring pixel-level consistency.…

Computer Vision and Pattern Recognition · Computer Science 2025-07-31 Xinqi Lin , Fanghua Yu , Jinfan Hu , Zhiyuan You , Wu Shi , Jimmy S. Ren , Jinjin Gu , Chao Dong

Unified vision-language models have made significant progress in multimodal understanding and generation, yet they largely fall short in producing multimodal interleaved outputs, which is a crucial capability for tasks like visual…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Ming Nie , Chunwei Wang , Jianhua Han , Hang Xu , Li Zhang

As language models become increasingly capable, users expect them to provide not only accurate responses but also behaviors aligned with diverse human preferences across a variety of scenarios. To achieve this, Reinforcement learning (RL)…

Group-relative policy optimization methods train language models by generating multiple rollouts per prompt and normalizing rewards with a shared mean reward baseline. In resource-constrained settings where the rollout budget is small,…

Machine Learning · Computer Science 2026-02-02 Youngeun Kim

When applying reinforcement learning--typically through GRPO--to large vision-language model reasoning struggles to effectively scale reasoning length or generates verbose outputs across all tasks with only marginal gains in accuracy. To…

Computation and Language · Computer Science 2025-10-24 Wenyi Xiao , Leilei Gan

Reinforcement learning methods such as GRPO have seen great popularity in LLM post-training. In GRPO, models produce completions to a set of prompts, which are rewarded, and the policy is updated towards the relatively high reward…

Machine Learning · Computer Science 2026-05-22 Nikolay Blagoev , Oğuzhan Ersoy , Wendelin Boehmer , Lydia Yiyu Chen

Reinforcement learning from verifiable rewards (RLVR), especially with Group Relative Policy Optimization (GRPO), has shown strong potential for improving the reasoning capabilities of large vision-language models (LVLMs). However, in…

Artificial Intelligence · Computer Science 2026-05-11 Bingqing Jiang , Difan Zou

Visual reasoning may require models to interpret images and videos and respond to implicit text queries across diverse output formats, from pixel-level segmentation masks to natural language descriptions. Existing approaches rely on…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Yiqing Shen , Mathias Unberath

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

Recent advancements in post-training methodologies for large language models (LLMs) have highlighted reinforcement learning (RL) as a critical component for enhancing reasoning. However, the substantial computational costs associated with…

Computation and Language · Computer Science 2025-07-29 Songjun Tu , Jiahao Lin , Xiangyu Tian , Qichao Zhang , Linjing Li , Yuqian Fu , Nan Xu , Wei He , Xiangyuan Lan , Dongmei Jiang , Dongbin Zhao

While machine learning approaches to image restoration offer great promise, current methods risk training models fixated on performing well only for image corruption of a particular level of difficulty---such as a certain level of noise or…

Computer Vision and Pattern Recognition · Computer Science 2017-08-03 Ruohan Gao , Kristen Grauman

GRPO has emerged as a prominent reinforcement learning algorithm for post-training LLMs. Unlike critic-based methods, GRPO computes advantages by estimating the \emph{value baselines} from group-level statistics, eliminating the need for a…

The advantage function is a central concept in RL that helps reduce variance in policy gradient estimates. For language modeling, Group Relative Policy Optimization (GRPO) was proposed to use the within-group sample mean as a baseline for…

Machine Learning · Computer Science 2026-04-23 Hu Wang , Congbo Ma , Ian Reid , Mohammad Yaqub