VisRef: 通过思考进行视觉再聚焦以提高多模态大推理模型的测试时间扩展
VisRef: Visual Refocusing while Thinking Improves Test-Time Scaling in Multi-Modal Large Reasoning Models
AI总结：
VisRef通过视觉再聚焦提升多模态大推理模型测试时间扩展性能，有效解决视觉依赖任务中推理性能下降问题。
摘要：
在大推理模型方面取得的进步表明，通过扩展推理过程来增加测试时间的计算能力，在复杂推理任务中表现出强大的性能。然而，最近的研究发现，在依赖视觉的任务中，推理时间扩展的文本推理会降低性能，因为模型逐渐失去对视觉标记的关注，并越来越多地依赖于文本先验。为了解决这个问题，先前的工作使用基于强化学习（RL）的微调来路由视觉标记，或者在推理过程中使用再聚焦机制。虽然有效，但这些方法计算成本高，需要大规模数据生成和策略优化。为了利用测试时间计算的优势而无需额外的RL微调，我们提出了VisRef，一种基于视觉的测试时间扩展框架。我们的核心思想是通过重新注入与推理上下文语义相关且多样且能代表图像全局的视觉标记集，主动引导推理过程，从而实现更扎实的多模态推理。在三个视觉推理基准上，使用最先进的多模态大推理模型进行实验表明，在固定测试时间计算预算下，VisRef在现有测试时间扩展方法上表现优异，最高可提升6.4%。
英文摘要：
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%.
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。
