用Kronecker分解海森矩阵，高效提升LLM量化精度，突破后训练量化瓶颈。
arXiv:2607.07964v1 Announce Type: new Abstract: Post-training quantization (PTQ) is a widely adopted technique for compressing large language models (…
提出TWLA方法，通过后训练量化实现大模型的三值权重和低位激活，已被ICML 2026接收，性能与效率兼顾。
arXiv:2606.13054v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit exceptional general language processing capabilities, but their…
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…
提出基于块尺度初始化的NVFP4后训练量化方法，有效提升大语言模型低比特精度。
arXiv:2606.07618v1 Announce Type: new Abstract: NVFP4 is a recently introduced hardware-supported FP4 format that improves the fidelity of 4-bit quant…
针对扩散大语言模型量化中的“稳定性滞后”问题，提出前沿感知重加权校准方法，有效抑制量化误差导致的早期决策翻转。
arXiv:2606.06547v1 Announce Type: cross Abstract: Diffusion Large Language Models (dLLMs) refine tokens iteratively but commit them irreversibly, lead…
提出AAAC方法，通过激活感知自适应码本，在保持4比特精度的同时进一步降低LLM权重量化误差
arXiv:2605.08692v2 Announce Type: replace Abstract: Post-training weight-only quantization to 4 bits is widely used to reduce the memory and compute c…
提出状态-时间一致后训练量化方案，突破扩散大语言模型部署瓶颈，降低模型推理成本。
arXiv:2606.04945v1 Announce Type: new Abstract: Diffusion large language models (DLLMs) have recently emerged as a promising alternative to autoregres…
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 …
新方法ProjQ让大模型压缩更聪明：后训练量化与低秩适配协同去噪，缓解顺序部署的精度损失。
arXiv:2606.00494v1 Announce Type: new Abstract: Post-Training Quantization (PTQ) and Low-Rank Adaptation (LoRA) constitute the standard pipeline for e…
作者亲自实验Hyrox比赛前最低训练量，用双人赛证明“偷懒”也能完赛的实用指南。
I've never felt stronger, or more scared.
循环语言模型量化面临三大挑战，首次系统性研究揭秘其脆弱性根源
arXiv:2605.16343v1 Announce Type: new Abstract: Looped language models (LoopLMs) improve parameter efficiency by recursively reusing Transformer block…
1-bit量化大模型新思路，输出对齐策略再审视，助力低资源设备高效推理
arXiv:2512.21651v3 Announce Type: replace Abstract: Large Language Models (LLMs) deliver strong performance across a wide range of NLP tasks, but thei…