English
Related papers

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

200 papers

Recent large reasoning models (LRMs) driven by reinforcement learning algorithms (e.g., GRPO) have achieved remarkable performance on challenging reasoning tasks. However, these models suffer from overthinking, generating unnecessarily long…

Artificial Intelligence · Computer Science 2026-03-03 Gang Li , Yan Chen , Ming Lin , Tianbao Yang

Image restoration is the task of recovering a clean image from a degraded version. In most cases, the degradation is spatially varying, and it requires the restoration network to both localize and restore the affected regions. In this…

Image and Video Processing · Electrical Eng. & Systems 2022-01-04 Maitreya Suin , Kuldeep Purohit , A. N. Rajagopalan

The ability to train high-performing reward models with few-shot data is critical for enhancing the efficiency and scalability of Reinforcement Learning from Human Feedback (RLHF). We propose a data augmentation and expansion framework that…

Machine Learning · Computer Science 2025-06-11 Yiyang Zhao , Huiyu Bai , Xuejiao Zhao

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

Visual-Language-Action (VLA) models have demonstrated strong cross-scenario generalization capabilities in various robotic tasks through large-scale pre-training and task-specific fine-tuning. However, their training paradigm mainly relies…

Robotics · Computer Science 2025-09-30 Zengjue Chen , Runliang Niu , He Kong , Qi Wang , Qianli Xing , Zipei Fan

The effectiveness of Direct Preference Optimization (DPO) depends on preference data that reflect the quality differences that matter in multimodal tasks. Existing pipelines often rely on off-policy perturbations or coarse outcome-based…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Ya-Qi Yu , Fangyu Hong , Xiangyang Qu , Hao Wang , Gaojie Wu , Qiaoyu Luo , Nuo Xu , Huixin Wang , Wuheng Xu , Yongxin Liao , Zihao Chen , Haonan Li , Ziming Li , Dezhi Peng , Minghui Liao , Jihao Wu , Haoyu Ren , Dandan Tu

Medical Image Grounding (MIG), which involves localizing specific regions in medical images based on textual descriptions, requires models to not only perceive regions but also deduce spatial relationships of these regions. Existing…

Machine Learning · Computer Science 2025-07-08 Huihui Xu , Yuanpeng Nie , Hualiang Wang , Ying Chen , Wei Li , Junzhi Ning , Lihao Liu , Hongqiu Wang , Lei Zhu , Jiyao Liu , Xiaomeng Li , Junjun He

We investigate a narrow but common failure mode of GRPO-style reinforcement learning in the context of sparse verifiable rewards: early updates contain more responses with negative advantages than those with positive advantages, while…

Machine Learning · Computer Science 2026-05-29 Mohamed Sana , Nicola Piovesan , Antonio De Domenico , Fadhel Ayed , Haozhe Zhang

Language model (LM) post-training relies on two stages of human supervision: task demonstrations for supervised finetuning (SFT), followed by preference comparisons for reinforcement learning from human feedback (RLHF). As LMs become more…

Machine Learning · Computer Science 2025-01-15 Yaowen Ye , Cassidy Laidlaw , Jacob Steinhardt

Reinforcement learning with verifiable rewards (RLVR) has become an effective paradigm for improving reasoning language models on tasks such as mathematics, coding, and scientific question answering. However, widely used group-relative…

Computation and Language · Computer Science 2026-05-29 Redacted by arXiv

Generative diffusion models are becoming one of the most popular prior in image restoration (IR) tasks due to their remarkable ability to generate realistic natural images. Despite achieving satisfactory results, IR methods based on…

Computer Vision and Pattern Recognition · Computer Science 2025-01-27 Di You , Pier Luigi Dragotti

Recently, Group Relative Policy Optimization (GRPO) has shown promising potential for aligning text-to-image (T2I) models, yet existing GRPO-based methods suffer from two critical limitations. (1) \textit{Shared credit assignment}:…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Qiang Lyu , Zicong Chen , Chongxiao Wang , Haolin Shi , Shibo Gao , Ran Piao , Youwei Zeng , Jianlou Si , Fei Ding , Jing Li , Chun Pong Lau , Weiqiang Wang

Large language models increasingly rely on long chains of thought to improve accuracy, yet such gains come with substantial inference-time costs. We revisit token-efficient post-training and argue that existing sequence-level reward-shaping…

Computation and Language · Computer Science 2026-02-24 Yinhan He , Yaochen Zhu , Mingjia Shi , Wendy Zheng , Lin Su , Xiaoqing Wang , Qi Guo , Jundong Li

Group Relative Policy Optimization (GRPO) has become a standard approach for training mathematical reasoning models; however, its reliance on multiple completions per prompt makes training computationally expensive. Although recent work has…

Machine Learning · Computer Science 2026-01-15 Kangda Wei , Ruihong Huang

To cope with uncertain changes of the external world, intelligent systems must continually learn from complex, evolving environments and respond in real time. This ability, collectively known as general continual learning (GCL),…

Artificial Intelligence · Computer Science 2026-05-12 Guanglong Sun , Hongwei Yan , Liyuan Wang , Zhiqi Kang , Shuang Cui , Hang Su , Jun Zhu , Yi Zhong

Image quality assessment (IQA) focuses on the perceptual visual quality of images, playing a crucial role in downstream tasks such as image reconstruction, compression, and generation. The rapid advancement of multi-modal large language…

Computer Vision and Pattern Recognition · Computer Science 2025-05-26 Weiqi Li , Xuanyu Zhang , Shijie Zhao , Yabin Zhang , Junlin Li , Li Zhang , Jian Zhang

Image captioning tasks usually use two-stage training to complete model optimization. The first stage uses cross-entropy as the loss function for optimization, and the second stage uses self-critical sequence training (SCST) for…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Xu Liang

Traditional on-policy Reinforcement Learning with Verifiable Rewards (RLVR) frameworks suffer from experience waste and reward homogeneity, which directly hinders learning efficiency on difficult samples during large language models…

Artificial Intelligence · Computer Science 2026-03-17 Xu Wan , Yansheng Wang , Wenqi Huang , Mingyang Sun

Video generation models trained on heterogeneous data with likelihood-surrogate objectives can produce visually plausible rollouts that violate physical constraints in embodied manipulation. Although reinforcement-learning post-training…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Zhenyang Ni , Yijiang Li , Ruochen Jiao , Simon Sinong Zhan , Sipeng Chen , Zhenfei Yin , Minshuo Chen , Philip Torr , Zhaoran Wang , Qi Zhu

Large-scale alignment pipelines typically pair a policy model with a separately trained reward model whose parameters remain frozen during reinforcement learning (RL). This separation creates a complex, resource-intensive pipeline and…

Computer Vision and Pattern Recognition · Computer Science 2025-07-24 Songshuo Lu , Hua Wang , Zhi Chen , Yaohua Tang