让AI推理时重新关注图像，提升多模态模型的准确率
VisRef: Visual Refocusing while Thinking Improves Test-Time Scaling in Multi-Modal Large Reasoning Models
- 推理时主动重注入语义相关的视觉特征
- 在固定计算预算下准确率最高提升6.4%
- 无需强化学习微调，适合部署在大模型上
大型推理模型通过延长推理时间来提升复杂任务表现，但在视觉依赖任务中，持续扩展文本推理会导致模型逐渐忽略视觉信息，过度依赖文本先验。现有方法采用强化学习微调或注意力重聚焦机制，但需大规模数据生成与策略优化，计算成本高。为此，本文提出VisRef，一种无需额外强化学习微调的视觉引导测试时扩展框架。核心思想是在推理过程中，重新注入一组语义相关、多样且全局代表图像的视觉特征子集，以增强多模态推理的视觉根基。在三个视觉推理基准上，使用先进多模态大模型进行实验，结果表明：在固定测试时计算预算下，VisRef相比现有方法性能最高提升6.4%。
原文摘要 · Abstract (English)
Advances in large reasoning models have shown strong performance on complex reasoning tasks by scaling test-time compute through extended reasoning. However, recent studies observe that in vision-dependent tasks, extended textual reasoning at inference time can degrade performance as models progressively lose attention to visual tokens and increasingly rely on textual priors alone. To address this, prior works use reinforcement learning (RL)-based fine-tuning to route visual tokens or employ refocusing mechanisms during reasoning. While effective, these methods are computationally expensive, requiring large-scale data generation and policy optimization. To leverage the benefits of test-time compute without additional RL fine-tuning, we propose VisRef, a visually grounded test-time scaling framework. Our key idea is to actively guide the reasoning process by re-injecting a coreset of visual tokens that are semantically relevant to the reasoning context while remaining diverse and globally representative of the image, enabling more grounded multi-modal reasoning. Experiments on three visual reasoning benchmarks with state-of-the-art multi-modal large reasoning models demonstrate that, under fixed test-time compute budgets, VisRef consistently outperforms existing test-time scaling approaches by up to 6.4%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。