Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring
链式推理压缩不应盲目:通过双路径锚定实现高效的多模态推理的V-Skip
机构 * School of Software Engineering, Xi’an Jiaotong University(西安交通大学软件工程学院) ; Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所) ; Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) ; Harbin Institute of Technology, Shenzhen(深圳哈尔滨工业大学) ; University of Science and Technology Beijing(北京科技大学)
AI总结 V-Skip通过双路径锚定机制解决多模态推理中令牌剪枝的盲目性问题,实现高效的推理速度提升与精度保持。