Page 3 - Lorn

ACL2026AlgoARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs

用增广残差通道提升 LLM 的 NVFP4 量化。

ICML2026AlgoVEQ: Modality-Adaptive Quantization for MoE Vision-Language Models

面向 MoE 视觉语言模型的模态自适应量化。

NeurIPS2026AlgoBreaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Models

缓解低比特量化下视觉语言模型的模态异质性问题。

ICML2026AlgoReSpinQuant: Efficient Layer-Wise LLM Quantization via Subspace Residual Rotation Approximation

通过子空间残差旋转近似的逐层大模型量化。

ICLR2026AlgoSERQ: Saliency-Aware Low-Rank Error Reconstruction For LLM Quantization

用显著性感知的低秩误差重建，把 LLM 的 PTQ 稳定地做到 W4A4。