中文
相关论文

相关论文: Safety-Preserving PTQ via Contrastive Alignment Lo…

200 篇论文

The ever-growing computational complexity of Large Language Models (LLMs) necessitates efficient deployment strategies. The current state-of-the-art approaches for Post-training Quantization (PTQ) often require calibration to achieve the…

计算与语言 · 计算机科学 2024-05-24 Alireza Ghaffari , Sharareh Younesian , Vahid Partovi Nia , Boxing Chen , Masoud Asgharian

Improving the efficiency of inference in Large Language Models (LLMs) is a critical area of research. Post-training Quantization (PTQ) is a popular technique, but it often faces challenges at low-bit levels, particularly in downstream…

计算机视觉与模式识别 · 计算机科学 2025-04-15 Wenjin Ke , Zhe Li , Dong Li , Lu Tian , Emad Barsoum

Recently, significant progress has been made in developing reasoning-capable Large Language Models (LLMs) through long Chain-of-Thought (CoT) techniques. However, this long-CoT reasoning process imposes substantial memory overhead due to…

计算与语言 · 计算机科学 2025-05-27 Tengxuan Liu , Shiyao Li , Jiayi Yang , Tianchen Zhao , Feng Zhou , Xiaohui Song , Guohao Dai , Shengen Yan , Huazhong Yang , Yu Wang

Post-training quantization has emerged as the most widely used strategy for deploying large language models at low precision. Still, current methods show perplexity degradation at bit-widths less than or equal to 4, partly because…

机器学习 · 计算机科学 2026-01-30 Lorenz K. Müller , Philippe Bich , Jiawei Zhuang , Ahmet Çelik , Luca Benfenati , Lukas Cavigelli

The quantization of large language models (LLMs) has been a prominent research area aimed at enabling their lightweight deployment in practice. Existing research about LLM's quantization has mainly explored the interplay between weights and…

计算与语言 · 计算机科学 2025-05-16 Yifei Gao , Jie Ou , Lei Wang , Jun Cheng , Mengchu Zhou

Post-training quantization (PTQ) has played a key role in compressing large language models (LLMs) with ultra-low costs. However, existing PTQ methods only focus on handling the outliers within one layer or one block, which ignores the…

机器学习 · 计算机科学 2025-02-26 Xin Ding , Xiaoyu Liu , Zhijun Tu , Yun Zhang , Wei Li , Jie Hu , Hanting Chen , Yehui Tang , Zhiwei Xiong , Baoqun Yin , Yunhe Wang

Multimodal Large Language Models (MLLM) are increasingly deployed in domains where both reliability and efficiency are critical. However, current models remain overconfident, producing highly certain but incorrect answers. At the same time,…

计算机视觉与模式识别 · 计算机科学 2026-02-17 Paul Jonas Kurz , Tobias Jan Wieczorek , Mohamed A. Abdelsalam , Rahaf Aljundi , Marcus Rohrbach

Large language models (LLMs) excel in various tasks but face deployment challenges due to hardware constraints. We propose density-aware post-training weight-only quantization (DAQ), which has two stages: 1) density-centric alignment, which…

机器学习 · 计算机科学 2024-10-18 Yingsong Luo , Ling Chen

Diffusion models have achieved great success in image generation tasks. However, the lengthy denoising process and complex neural networks hinder their low-latency applications in real-world scenarios. Quantization can effectively reduce…

计算机视觉与模式识别 · 计算机科学 2025-06-24 Xuewen Liu , Zhikai Li , Junrui Xiao , Mengjuan Chen , Jianquan Li , Qingyi Gu

As machine learning (ML) models are increasingly deployed in high-stakes domains, trustworthy uncertainty quantification (UQ) is critical for ensuring the safety and reliability of these models. Traditional UQ methods rely on specifying a…

机器学习 · 统计学 2025-05-14 Abhineet Agarwal , Michael Xiao , Rebecca Barter , Omer Ronen , Boyu Fan , Bin Yu

The increasing size and complexity of large language models (LLMs) have raised significant challenges in deployment efficiency, particularly under resource constraints. Post-training quantization (PTQ) has emerged as a practical solution by…

计算与语言 · 计算机科学 2026-04-07 Han Liu , Haotian Gao , Changya Li , Feng Zhang , Xiaotong Zhang , Wei Wang , Hong Yu

Post-training quantization of Large Language Models (LLMs) has proven effective in reducing the memory and computational requirements for inference. In this study, we focus on a straightforward question: When aiming for a target accuracy or…

计算与语言 · 计算机科学 2025-08-08 Zeyu Cao , Boyang Gu , Cheng Zhang , Pedro Gimenes , Jianqiao Lu , Jianyi Cheng , Xitong Gao , Yiren Zhao

Diffusion large language models (dLLMs), which offer bidirectional context and flexible masked-denoising generation, are emerging as a compelling alternative to autoregressive (AR) LLMs. However, like AR LLMs, their model sizes continue to…

机器学习 · 计算机科学 2025-10-07 Tianao Zhang , Zhiteng Li , Xianglong Yan , Haotong Qin , Yong Guo , Yulun Zhang

Variational quantum algorithms (VQAs) are leading strategies for using near-term quantum devices, with a well-studied bottleneck being their trainability. Standard expectation-value objectives with expressive circuits frequently encounter…

量子物理 · 物理学 2026-05-05 Yixian Qiu , Josep Lumbreras , Xiufan Li , Patrick Rebentrost

Post-Training Quantization (PTQ) is an effective technique for compressing Large Language Models (LLMs). While many studies focus on quantizing both weights and activations, it is still a challenge to maintain the accuracy of LLM after…

机器学习 · 计算机科学 2024-10-11 Wenyuan Liu , Xindian Ma , Peng Zhang , Yan Wang

Segment Anything Model (SAM) exhibits remarkable zero-shot segmentation capability; however, its prohibitive computational costs make edge deployment challenging. Although post-training quantization (PTQ) offers a promising compression…

计算机视觉与模式识别 · 计算机科学 2025-11-18 Jing Zhang , Zhikai Li , Chengzhi Hu , Xuewen Liu , Qingyi Gu

Quantization Aware Training (QAT) is a neural network quantization technique that compresses model size and improves operational efficiency while effectively maintaining model performance. The paradigm of QAT is to introduce fake…

计算机视觉与模式识别 · 计算机科学 2025-04-25 Wenqiang Zhou , Zhendong Yu , Xinyu Liu , Jiaming Yang , Rong Xiao , Tao Wang , Chenwei Tang , Jiancheng Lv

Post-training quantization (PTQ) of large language models (LLMs) to extremely low bit-widths remains challenging due to the fundamental trade-off between computational efficiency and representational capacity. While existing ultra-low-bit…

机器学习 · 计算机科学 2026-01-05 He Xiao , Runming Yang , Qingyao Yang , Wendong Xu , Zhen Li , Yupeng Su , Zhengwu Liu , Hongxia Yang , Ngai Wong

Post-training quantization (PTQ) has stood out as a cost-effective and promising model compression paradigm in recent years, as it avoids computationally intensive model retraining. Nevertheless, current PTQ methods for Vision Transformers…

计算机视觉与模式识别 · 计算机科学 2025-06-16 Zhuguanyu Wu , Shihe Wang , Jiayi Zhang , Jiaxin Chen , Yunhong Wang

Quantization is an effective technique to reduce the deployment cost of large language models (LLMs), and post-training quantization (PTQ) has been widely studied due to its efficiency. However, existing PTQ methods are limited by their…