Breaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Models
Published in Advances in Neural Information Processing Systems (NeurIPS), 2026
Recommended citation: Yi Zhong, Haotong Qin, Xindong Zhang, Lei Zhang, Guolei Sun (2026). Breaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Models. Advances in Neural Information Processing Systems (NeurIPS). https://arxiv.org/pdf/2605.19929
A low-bit post-training quantization framework that decouples modality-specific outliers and calibrates cross-modal differences in vision-language models.