QVLA: Not All Channels Are Equal in Vision-Language-Action Model's Quantization
QVLA:视觉-语言-动作模型量化中并非所有通道都平等
机构 * AutoLab, School of Artificial Intelligence, Shanghai Jiao Tong University(自动化实验室,人工智能学院,上海交通大学) ; Anyverse Dynamics ; State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences(多模态人工智能系统国家重点实验室,自动化研究所,中国科学院) ; School of Artificial Intelligence, University of Chinese Academy of Sciences(人工智能学院,中国科学院大学) ; Terminal Technology Department, Alipay, Ant Group(终端技术部,蚂蚁集团)
AI总结 QVLA提出了一种动作导向的量化框架,通过按通道分配比特数来优化视觉-语言-动作模型的压缩,实现了更高的性能和效率。
Comments ICLR2026