跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+0已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-22 08:44 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 13:24 — 2026-11-22 13:24(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-22 08:44最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 1 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 08:42(北京时间)
版本更新 · v3arXiv:2605.23500

GRTO: Bootstrapped Group Relative Tool Optimization for Referring Segmentation

Mario Markov, Stefan Maria Ailuro, Mohammad Mahdi, Luc Van Gool, Danda Pani Paudel

原文摘要

Referring segmentation requires reasoning to connect language with visual evidence and identify the intended target in challenging scenarios. This makes GRPO a natural choice for training VLMs together with a segmentation tool. However, existing approaches optimize only the VLM, assuming that the tool is perfect and leaving it untouched. This assumption is particularly limiting when the tool faces domain shift, as segmentation errors can undermine even correct reasoning. We therefore argue that the segmentation tool should be optimized together with the reasoning policy. However, this is challenging because policy optimization and differentiable tool learning rely on fundamentally different objectives. In this work, we introduce group relative tool optimization (GRTO), a mathematically grounded two-stage framework for jointly optimizing a policy and its differentiable tool. The key idea is to first align the tool with the policy expected after joint training, rather than the initial policy. The prealigned tool then leads to a more robust reward signal and superior policy convergence in subsequent policy training. In the first stage, GRTO bootstraps the tool toward the theoretically optimal policy, capturing readily attainable gains without costly on-policy rollouts. This alignment bootstraps the second stage, where GRTO extends GRPO to jointly refine the policy and tool. Across three challenging referring segmentation benchmarks, GRTO achieves substantial improvements over plain GRPO and alternative tool training procedures, matching or surpassing domain-specific state-of-the-art methods. This demonstrates the value of unifying reinforcement learning with differentiable auxiliary objectives for reasoning-intensive segmentation.

cs.CV · cs.LG