中文
相关论文

相关论文: B-GRTO: Bootstrapped Group Relative Tool Optimizat…

200 篇论文

Referring image segmentation (RIS) aims to segment objects in an image conditioning on free-from text descriptions. Despite the overwhelming progress, it still remains challenging for current approaches to perform well on cases with various…

计算机视觉与模式识别 · 计算机科学 2023-12-04 Yajie Liu , Pu Ge , Haoxiang Ma , Shichao Fan , Qingjie Liu , Di Huang , Yunhong Wang

Speculative decoding accelerates large language model (LLM) inference by letting a lightweight draft model propose multiple tokens that the target model verifies in parallel. Yet existing training objectives optimize only a single greedy…

计算与语言 · 计算机科学 2026-03-03 Shijing Hu , Jingyang Li , Zhihui Lu , Pan Zhou

Referring Video Object Segmentation (RVOS) aims to segment the object referred to by the query sentence throughout the entire video. Most existing methods require end-to-end training with dense mask annotations, which could be…

计算机视觉与模式识别 · 计算机科学 2024-06-25 Ci-Siang Lin , I-Jieh Liu , Min-Hung Chen , Chien-Yi Wang , Sifei Liu , Yu-Chiang Frank Wang

Group Relative Policy Optimization (GRPO) has been shown to be an effective algorithm when an accurate reward model is available. However, such a highly reliable reward model is not available in many real-world tasks. In this paper, we…

机器学习 · 计算机科学 2026-01-12 Yuki Ichihara , Yuu Jinnai , Tetsuro Morimura , Mitsuki Sakamoto , Ryota Mitsuhashi , Eiji Uchibe

Group Relative Policy Optimization (GRPO) enhances policy learning by computing gradients from relative comparisons among candidate outputs that share a common input prefix. Despite its effectiveness, GRPO introduces substantial…

机器学习 · 计算机科学 2025-06-09 Zikang Liu , Tongtian Yue , Yepeng Tang , Longteng Guo , Junxian Cai , Qingbin Liu , Xi Chen , Jing Liu

Fine-grained visual categorization is to recognize hundreds of subcategories belonging to the same basic-level category, which is a highly challenging task due to the quite subtle and local visual distinctions among similar subcategories.…

计算机视觉与模式识别 · 计算机科学 2019-02-21 Xiangteng He , Yuxin Peng

Traditional methods for reasoning segmentation rely on supervised fine-tuning with categorical labels and simple descriptions, limiting its out-of-domain generalization and lacking explicit reasoning processes. To address these limitations,…

计算机视觉与模式识别 · 计算机科学 2025-07-01 Yuqi Liu , Bohao Peng , Zhisheng Zhong , Zihao Yue , Fanbin Lu , Bei Yu , Jiaya Jia

Referring image segmentation aims to segment the objects referred by a natural language expression. Previous methods usually focus on designing an implicit and recurrent feature interaction mechanism to fuse the visual-linguistic features…

计算机视觉与模式识别 · 计算机科学 2021-03-31 Ya Jing , Tao Kong , Wei Wang , Liang Wang , Lei Li , Tieniu Tan

Radiology report generation requires advanced medical image analysis, effective temporal reasoning, and accurate text generation. Although recent innovations, particularly multimodal large language models, have shown improved performance,…

计算与语言 · 计算机科学 2025-11-11 Kai Zhang , Christopher Malon , Lichao Sun , Martin Renqiang Min

Alignment methodologies have emerged as a critical pathway for enhancing language model alignment capabilities. While SFT (supervised fine-tuning) accelerates convergence through direct token-level loss intervention, its efficacy is…

Reinforcement learning, particularly Group Relative Policy Optimization (GRPO), has emerged as an effective framework for post-training visual generative models with human preference signals. However, its effectiveness is fundamentally…

计算机视觉与模式识别 · 计算机科学 2026-04-28 Rui Li , Ke Hao , Yuanzhi Liang , Haibin Huang , Chi Zhang , Yun Gu , XueLong Li

Recent advances in pixel-level tasks (e.g. segmentation) illustrate the benefit of of long-range interactions between aggregated region-based representations that can enhance local features. However, such aggregated representations, often…

计算机视觉与模式识别 · 计算机科学 2024-04-19 Mir Rayat Imtiaz Hossain , Leonid Sigal , James J. Little

Group Relative Policy Optimization (GRPO) has emerged as an effective method for training reasoning models. While it computes advantages based on group mean, GRPO treats each output as an independent sample during the optimization and…

人工智能 · 计算机科学 2026-03-16 Yu Li , Tian Lan , Zhengling Qi

Reinforcement learning (RL) has proven effective in strengthening the reasoning capabilities of large language models (LLMs). A widely adopted method, Group Relative Policy Optimization (GRPO), has shown strong empirical results in training…

机器学习 · 计算机科学 2026-03-11 Peter Chen , Xiaopeng Li , Ziniu Li , Xi Chen , Tianyi Lin

Multimodal referring segmentation aims to segment target objects in visual scenes, such as images, videos, and 3D scenes, based on referring expressions in text or audio format. This task plays a crucial role in practical applications…

计算机视觉与模式识别 · 计算机科学 2025-08-06 Henghui Ding , Song Tang , Shuting He , Chang Liu , Zuxuan Wu , Yu-Gang Jiang

Reinforcement learning (RL) has become a key driver of language model reasoning. Among RL algorithms, Group Relative Policy Optimization (GRPO) is the de facto standard, avoiding the need for a critic by using per-prompt baselines and…

机器学习 · 计算机科学 2026-02-02 Cheng Ge , Caitlyn Heqi Yin , Hao Liang , Jiawei Zhang

Referring image segmentation is an advanced semantic segmentation task where target is not a predefined class but is described in natural language. Most of existing methods for this task rely heavily on convolutional neural networks, which…

计算机视觉与模式识别 · 计算机科学 2022-04-01 Namyup Kim , Dongwon Kim , Cuiling Lan , Wenjun Zeng , Suha Kwak

Hybrid Group Relative Policy Optimization (Hybrid GRPO) is a reinforcement learning framework that extends Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO) by incorporating empirical multi-sample action…

机器学习 · 计算机科学 2025-02-05 Soham Sane

Geospatial pixel reasoning aims to generate segmentation masks in remote sensing imagery directly from natural-language instructions. Most existing approaches follow a paradigm that fine-tunes multimodal large language models under…

计算机视觉与模式识别 · 计算机科学 2025-10-29 Chengjie Jiang , Yunqi Zhou , Jiafeng Yan , Jing Li , Jiayang Li , Yue Zhou , Hongjie He , Jonathan Li

Group Relative Policy Optimization (GRPO) has proven to be an effective tool for post-training language models (LMs). However, AI systems are increasingly expressed as modular programs that mix together multiple LM calls with distinct…