English
Related papers

Related papers: S-GRPO: Unified Post-Training for Large Vision-Lan…

200 papers

While reinforcement learning (RL) has been central to the recent success of large language models (LLMs), RL optimization is notoriously unstable, especially when compared to supervised fine-tuning (SFT). In this work, we investigate the…

Machine Learning · Computer Science 2026-03-03 Hongzhan Chen , Tao Yang , Yuhua Zhu , Shiping Gao , Xiaojun Quan , Ting Yao

Recently, vision-language model (VLM) agents have shown promising progress in open-world tasks, where successful task completion often requires multiple turns of visual perception and action execution. However, existing methods still rely…

Machine Learning · Computer Science 2026-05-22 Xiongbin Wu , Zhihao Luo , Shanzhe Lei , Lechao Zhang , Xuhong Wang , Jie Yang , Zhonglong Zheng , Yuanjie Zheng , Xin Tan , Wei Liu

Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capabilities of Large Language Models (LLMs) by leveraging direct outcome verification instead of learned reward models. Building on this paradigm, Group…

Machine Learning · Computer Science 2026-04-23 Jingyi Wang , Lei Zhu , Tengjin Weng , Song-Li Wu , Haochen Tan , Jierun Chen , Chaofan Tao , Haoli Bai , Lu Hou , Lifeng Shang , Xiao-Ping Zhang

Recent advances in Large Language Model (LLM) agents have demonstrated their promising general capabilities. However, their performance in specialized real-world domains often degrades due to challenges in effectively integrating external…

Computation and Language · Computer Science 2025-10-10 Yuzheng Cai , Siqi Cai , Yuchen Shi , Zihan Xu , Lichao Chen , Yulei Qin , Xiaoyu Tan , Gang Li , Zongyi Li , Haojia Lin , Yong Mao , Ke Li , Xing Sun

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

Most of the traditional Applicant Tracking Systems (ATS) depend on strict matching using keywords, where candidates that are highly qualified are many times disqualified because of minor semantic differences. In this article, the two-stage…

Machine Learning · Computer Science 2026-01-21 Shreyansh Jain , Madhav Singhvi , Shreya Rahul Jain , Pranav S , Dishaa Lokesh , Naren Chittibabu , Akash Anandhan

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for post-training reasoning models. However, group-based methods such as Group Relative Policy Optimization (GRPO) face a critical dilemma in…

Machine Learning · Computer Science 2026-04-07 Yuning Wu , Ke Wang , Devin Chen , Kai Wei

Post-training of large language models routinely interleaves supervised fine-tuning (SFT) with reinforcement learning (RL). These two methods have different objectives: SFT minimizes the cross-entropy loss between model outputs and expert…

Machine Learning · Computer Science 2026-05-07 Xueyan Niu , Bo Bai , Wei Han , Weixi Zhang

Supervised fine-tuning (SFT) of foundation models often leads to poor generalization, where prior capabilities deteriorate after tuning on new tasks or domains. Inspired by trust-region policy optimization (TRPO) and proximal policy…

Machine Learning · Computer Science 2026-04-14 Wenhong Zhu , Ruobing Xie , Rui Wang , Xingwu Sun , Di Wang , Pengfei Liu

Recent advances in large language models (LLMs) have broadened their applicability across diverse tasks, yet specialized domains still require targeted post training. Among existing methods, Group Relative Policy Optimization (GRPO) stands…

Machine Learning · Computer Science 2025-08-08 Ziyin Gu , Jingyao Wang , Ran Zuo , Chuxiong Sun , Zeen Song , Changwen Zheng , Wenwen Qiang

A significant portion of recent research on Large Language Model (LLM) alignment focuses on developing new policy optimization methods based on Group Relative Policy Optimization (GRPO). Two prominent directions have emerged: (i) a shift…

Machine Learning · Computer Science 2026-02-27 Svetlana Glazyrina , Maksim Kryzhanovskiy , Roman Ischenko

We introduce a novel method that averages the logits of a frozen reference policy (e.g., SFT) and a trainable policy, and incorporate the method into Group Relative Policy Optimization (GRPO). In contrast to Reinforcement Learning with…

Machine Learning · Computer Science 2026-05-21 Xingwei Gan , Ying Zhu

Supervised fine-tuning (SFT) is the predominant method for adapting large language models (LLMs), yet it often struggles with generalization compared to reinforcement learning (RL). In this work, we posit that this performance disparity…

Computation and Language · Computer Science 2026-02-03 Rui Ming , Haoyuan Wu , Shoubo Hu , Zhuolun He , Bei Yu

Group Relative Policy Optimization (GRPO) was introduced and used recently for promoting reasoning in LLMs under verifiable (binary) rewards. We show that the mean + variance calibration of these rewards induces a weighted contrastive loss…

Machine Learning · Computer Science 2025-10-22 Youssef Mroueh

Despite their sophisticated general-purpose capabilities, Large Language Models (LLMs) often fail to align with diverse individual preferences because standard post-training methods, like Reinforcement Learning with Human Feedback (RLHF),…

Post-training has demonstrated its importance in enhancing the reasoning capabilities of large language models (LLMs). The primary post-training methods can be categorized into supervised fine-tuning (SFT) and reinforcement fine-tuning…

Machine Learning · Computer Science 2025-10-21 Mingyang Liu , Gabriele Farina , Asuman Ozdaglar

This paper presents a learning-based guidance-and-control approach that couples a reasoning-enabled Large Language Model (LLM) with Group Relative Policy Optimization (GRPO). A two-stage procedure consisting of Supervised Fine-Tuning (SFT)…

Robotics · Computer Science 2026-01-09 Amit Jain , Richard Linares

Recent advances in multi-modal large language models (MLLMs) have significantly improved object-level grounding and region captioning. However, they remain limited in visual relation understanding, struggling even with binary relation…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Lin Li , Wei Chen , Jiahui Li , Kwang-Ting Cheng , Long Chen

Training robust and generalizable reward models for human visual preferences is essential for aligning text-to-image and text-to-video generative models with human intent. However, current reward models often fail to generalize, and…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Alexander Gambashidze , Li Pengyi , Matvey Skripkin , Andrey Galichin , Anton Gusarov , Konstantin Sobolev , Andrey Kuznetsov , Ivan Oseledets

Supervised fine-tuning (SFT) has emerged as a crucial method for aligning large language models (LLMs) with human-annotated demonstrations. However, SFT, being an off-policy approach similar to behavior cloning, often struggles with…

Computation and Language · Computer Science 2025-10-27 Qingru Zhang , Liang Qiu , Ilgee Hong , Zhenghao Xu , Tianyi Liu , Shiyang Li , Rongzhi Zhang , Zheng Li , Lihong Li , Bing Yin , Chao Zhang , Jianshu Chen , Haoming Jiang , Tuo Zhao