Decoding the Pulse of Reasoning VLMs in Multi-Image Understanding Tasks
解码多图像理解任务中推理视觉语言模型的脉冲
专题命中 测试时计算 :reasoning(title,abstract);CoT(abstract,abstract_cn);chain-of-thought(abstract);分类 cs.AI
AI总结 本文提出PulseFocus方法,通过规划和聚焦块结构及软注意力门控,提升多图像推理任务性能,实现在BLINK和MuirBench上分别提升3.7%和1.07%。
Comments This article is withdrawn because the experimental results and analysis require substantial revision. The current version should not be cited as a reliable representation of the work