1
MorphoQuant: Modality-Aware Quantization for Omni-modal Large Language Models
针对全模态大语言模型4比特量化时模态分布异质难题，MorphoQuant提出模态感知量化框架，有效压缩模型同时保持性能。
arXiv:2606.04349v1 Announce Type: cross Abstract: Conventional Post-Training Quantization (PTQ) methods struggle with 4-bit Omni-modal Large Language …