Page 5 - Lorn

AlgoVLMQ: Efficient Post-Training Quantization for Large Vision-Language Models via Hessian Augmentation

通过 Hessian 增广高效量化视觉语言模型。

CVPR2026AlgoFine-Grained Post-Training Quantization for Large Vision Language Models with Quantization-Aware Integrated Gradients

用量化感知的积分梯度做细粒度的视觉语言模型训练后量化。

CVPR2025AlgoMBQ: Modality-Balanced Quantization for Large Vision-Language Models

平衡视觉与文本模态敏感度的视觉语言模型量化。

CVPR2026AlgoMASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models

面向多模态大模型、模态感知的平滑量化。

ICLR2026AlgoTurboQuant: Online Vector Quantization with Near-optimal Distortion Rate

接近最优失真率的在线向量量化方法。