突破2-bit量化瓶颈，统一标量与向量量化方法，实现大模型低成本部署与推理加速。
arXiv:2606.10520v1 Announce Type: new Abstract: Post-training quantization at the 2-bit level enables low-cost deployment and inference acceleration f…
LLM极低比特量化新突破，线性约束向量量化实现2比特数据高效训练，已被ICML 2026收录。
arXiv:2606.10531v1 Announce Type: cross Abstract: Quantization-aware training (QAT) is essential for extremely low-bit large language models (LLMs). C…
提出一种无需训练的向量量化新方法，利用高斯VAE实现高效表示学习，为量化领域开辟新路径。
arXiv:2512.06609v3 Announce Type: replace Abstract: Vector-quantized variational autoencoders (VQ-VAEs) are discrete autoencoders that compress images…
利用高效向量量化架构大幅加速LLM解码，已获顶级会议ISCA 2026接收，为推理提速带来新思路。
arXiv:2605.24144v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved impressive performance across diverse domains but remain …