MetaphorStar: 基于端到端视觉强化学习的图像隐喻理解与推理
MetaphorStar: Image Metaphor Understanding and Reasoning with End-to-End Visual Reinforcement Learning
AI总结：
MetaphorStar通过端到端视觉强化学习框架提升图像隐喻理解与推理能力，显著优于现有模型。
摘要：
图像中的隐喻理解仍然是当今人工智能系统面临的关键挑战。尽管多模态大语言模型（MLLMs）在基本的视觉问答（VQA）任务上表现出色，但它们始终难以把握嵌入在视觉内容中的细微文化、情感和情境含义。这种困难源于任务对复杂多跳推理、文化背景和心灵理论（ToM）能力的需求，而当前模型缺乏这些能力。为填补这一空白，我们提出了MetaphorStar，这是首个针对图像隐喻任务的端到端视觉强化学习（RL）框架。我们的框架包括三个核心组件：细粒度数据集TFQ-Data、视觉RL方法TFQ-GRPO以及结构化的基准TFQ-Bench。我们的完全开源的MetaphorStar家族，通过在TFQ-Data上使用TFQ-GRPO进行训练，显著提高了在图像隐喻基准上的性能，平均提升了82.6%。与20多个主流MLLMs相比，MetaphorStar-32B在多项选择问题和开放式问题上实现了最先进的（SOTA），显著优于顶级闭源模型Gemini-3.0-pro在判断题上的表现。关键地，我们的实验表明，学习图像隐喻任务能提升一般理解能力，尤其是复杂的视觉推理能力。我们进一步对模型参数扩展、训练数据扩展以及不同模型架构和训练策略的影响进行了系统分析，证明了我们方法的广泛适用性。我们已开源所有模型权重、数据集和方法代码，网址为https://metaphorstar.github.io。
英文摘要：
Metaphorical comprehension in images remains a critical challenge for Nowadays AI systems. While Multimodal Large Language Models (MLLMs) excel at basic Visual Question Answering (VQA), they consistently struggle to grasp the nuanced cultural, emotional, and contextual implications embedded in visual content. This difficulty stems from the task's demand for sophisticated multi-hop reasoning, cultural context, and Theory of Mind (ToM) capabilities, which current models lack. To fill this gap, we propose MetaphorStar, the first end-to-end visual reinforcement learning (RL) framework for image implication tasks. Our framework includes three core components: the fine-grained dataset TFQ-Data, the visual RL method TFQ-GRPO, and the well-structured benchmark TFQ-Bench. Our fully open-source MetaphorStar family, trained using TFQ-GRPO on TFQ-Data, significantly improves performance by an average of 82.6% on the image implication benchmarks. Compared with 20+ mainstream MLLMs, MetaphorStar-32B achieves state-of-the-art (SOTA) on Multiple-Choice Question and Open-Style Question, significantly outperforms the top closed-source model Gemini-3.0-pro on True-False Question. Crucially, our experiments reveal that learning image implication tasks improves the general understanding ability, especially the complex visual reasoning ability. We further provide a systematic analysis of model parameter scaling, training data scaling, and the impact of different model architectures and training strategies, demonstrating the broad applicability of our method. We open-sourced all model weights, datasets, and method code at https://metaphorstar.github.io.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
