Post-Training Quantization (PTQ) is essential for deploying Large Language Models (LLMs) on memory-constrained devices, yet it renders models static and difficult to fine-tune. Standard fine-tuning paradigms, including Reinforcement Learning (RL), fundamentally rely on backpropagation and continuous weights to compute gradients. Thus they cannot be used on quantized models, where the parameter space is discrete and non-differentiable. While Evolution Strategies (ES) offer a backpropagation-free alternative, optimization of the quantized parameters can still fail due to vanishing or inaccurate gradient estimation. This paper introduces Quantized Evolution Strategies (QES), an optimization paradigm that performs full-parameter fine-tuning directly in the quantized space. QES is based on two innovations: (1) it integrates accumulated error feedback to preserve high-precision weight updating signals, and (2) it utilizes a stateless seed replay to reduce memory usage to low-precision inference levels. QES significantly outperforms the state-of-the-art zeroth-order fine-tuning methods on a variety of tasks, making direct fine-tuning for quantized models possible. It therefore opens up the possibility for scaling up LLMs entirely in the quantized space. The source code is available at https://github.com/dibbla/Quantized-Evolution-Strategies .
LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-Tuning
Southwestern University of Finance and Economics（西南财经大学）；Artificial Intelligence and Digital Finance Key Laboratory of Sichuan Province（四川省人工智能与数字金融重点实验室）；The Hong Kong University of Science and Technology (Guangzhou)（香港科学与艺术大学（广州））；Sun Yat-sen University（中山大学）；Nanjing University（南京大学）
Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models
The State Key Laboratory of Blockchain and Data Security, Zhejiang University（区块链与数据安全国家重点实验室，浙江大学）；Sun Yat-sen University（中山大学）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新技术区（滨江）区块链与数据安全研究院）
Accuracy is Not Enough: A Divergence-Based Approach to Evaluate Fidelity Loss in Quantized LLMs
Fraunhofer IAIS（弗劳恩霍夫智能分析与信息处理研究所）；University of Bonn（波恩大学）；Lamarr Institute for Machine Learning and Artificial Intelligence（拉马尔机器学习与人工智能研究所）；University of Manitoba（曼尼托巴大学）；University of Central Florida（中佛罗里达大学）；Virginia Tech（弗吉尼亚理工大学）
Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency
SINTEF（辛泰夫（挪威研究机构））；Singapore Management University（新加坡管理大学）；Oslo Metropolitan University（奥斯陆城市大学）；Kristiania University of Applied Sciences（克里斯蒂安尼亚应用科技大学）
本研究在Raspberry Pi 4上评估了28个量化LLM在能效、推理性能和准确率上的权衡，通过硬件级能耗分析与多数据集基准测试，为资源受限环境下的可持续LLM部署提供了可操作的见解。
Achieving binary weight and activation for LLMs using Post-Training Quantization
MAIS, Institute of Automation, Chinese Academy of Sciences（自动化研究所，中国科学院）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Central Media Technology Institute, Huawei Technologies Ltd.（华为技术有限公司媒体技术研究所）
Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity
Princeton University（普林斯顿大学）；Stevens Institute of Technology（史蒂文斯理工学院）；University of Pennsylvania（宾夕法尼亚大学）；Rice University（莱斯大学）；Carnegie Mellon University（卡内基梅隆大学）；Cornell University（康奈尔大学）
L-TUNING: Synchronized Label Tuning for Prompt and Prefix in LLMs
Stevens Institute of Technology（史蒂文斯理工学院）；Hajee Mohammad Danesh Science & Technology University（哈吉·穆罕默德·达内什科学技术大学）；Noakhali Science & Technology University（诺阿卡利科学技术大学）；Amazon（亚马逊）
LFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMs
Kim Jaechul Graduate School of AI, KAIST, Daejeon, South Korea（韩国科学技术院人工智能研究生院）；LG AI Research, Seoul, South Korea（LG人工智能研究）；Hanyang University, Seoul, South Korea（翰阳大学）
One QuantLLM for ALL: Fine-tuning Quantized LLMs Once for Efficient Deployments
South China University of Technology（华南理工大学）；The Hong Kong University of Science and Technology（香港科技大学）；Salesforce AI Research（Salesforce AI研究院）；Tsinghua University（清华大学）
A Survey of Quantized Graph Representation Learning: Connecting Graph Structures with Large Language Models
National University of Singapore（新加坡国立大学）；Xi’an Jiaotong University（西安交通大学）；University of Southern Queensland（南方昆士兰大学）；Nanyang Technological University（南洋理工大学）
Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks
Meta；University of Pisa（比萨大学）；University of Modena and Reggio Emilia（摩德纳与雷焦艾米利亚大学）；Brown University（布朗大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
