中文
相关论文

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

200 篇论文

As Large Language Models (LLMs) become increasingly computationally complex, developing efficient deployment strategies, such as quantization, becomes crucial. State-of-the-art Post-training Quantization (PTQ) techniques often rely on…

机器学习 · 计算机科学 2025-01-17 Alireza Ghaffari , Sharareh Younesian , Boxing Chen , Vahid Partovi Nia , Masoud Asgharian

Post-training quantization (PTQ) has recently emerged as an effective tool for reducing the computational complexity and memory usage of a neural network by representing its weights and activations with lower precision. While this paradigm…

机器学习 · 计算机科学 2025-10-06 Logan Frank , Paul Ardis

Post-training quantization (PTQ) reduces excessive hardware cost by quantizing full-precision models into lower bit representations on a tiny calibration set, without retraining. Despite the remarkable progress made through recent efforts,…

机器学习 · 计算机科学 2024-12-16 Junrui Xiao , Zhikai Li , Lianwei Yang , Yiduo Mei , Qingyi Gu

A natural and intuitive idea in model quantization is to approximate each component's quantized output to match its original. Motivated by this idea, most layer-wise post-training quantization (PTQ) methods focus on weight approximation at…

机器学习 · 计算机科学 2026-01-28 Li Lin , Xiaojun Wan

Post-training quantization (PTQ) enables efficient deployment of large language models by mapping pretrained weights to low-bit formats without retraining, typically using a small calibration set to minimize a layer-wise calibration…

机器学习 · 计算机科学 2026-05-12 Seohyeon Cha , Huancheng Chen , Dongjun Kim , Haoran Zhang , Kevin Chan , Gustavo de Veciana , Haris Vikalo

Large Language Models (LLMs) are powerful tools for modern applications, but their computational demands limit accessibility. Quantization offers efficiency gains, yet its impact on safety and trustworthiness remains poorly understood. To…

密码学与安全 · 计算机科学 2025-07-01 Artyom Kharinaev , Viktor Moskvoretskii , Egor Shvetsov , Kseniia Studenikina , Bykov Mikhail , Evgeny Burnaev

Post-Training Quantization (PTQ) compresses large language models to low bit-widths using a small calibration set, and its quality depends strongly on which samples are chosen. We identify a failure mode in which calibration samples fail to…

机器学习 · 计算机科学 2026-04-28 Ibne Farabi Shihab , Sanjeda Akter , Anuj Sharma

Public large language models (LLMs) are typically safety-aligned during pretraining, yet task-specific fine-tuning required for deployment often erodes this alignment and introduces safety risks. Existing defenses either embed safety…

机器学习 · 计算机科学 2026-01-14 Qitao Tan , Xiaoying Song , Ningxi Cheng , Ninghao Liu , Xiaoming Zhai , Lingzi Hong , Yanzhi Wang , Zhen Xiang , Geng Yuan

Large language models (LLMs) have shown remarkable performance in various domains, but they are constrained by massive computational and storage costs. Quantization, an effective technique for compressing models to fit resource-limited…

计算与语言 · 计算机科学 2026-04-14 Han Liu , Haotian Gao , Xiaotong Zhang , Changya Li , Feng Zhang , Wei Wang , Fenglong Ma , Hong Yu

Large Language Models (LLMs) deliver strong performance across a wide range of NLP tasks, but their massive sizes hinder deployment on resource-constrained devices. To reduce their computational and memory burden, various compression…

机器学习 · 计算机科学 2026-05-18 Dung Anh Hoang , Cuong Pham , Cuong Nguyen , Trung le , Jianfei Cai , Thanh-Toan Do

Post-training quantization (PTQ) reduces a model's memory footprint by mapping full precision weights into low bit weights without costly retraining, but can degrade its downstream performance especially in low 2- to 3-bit settings. We…

机器学习 · 计算机科学 2025-07-18 Hanqi Xiao , Yi-Lin Sung , Elias Stengel-Eskin , Mohit Bansal

Post-training quantization (PTQ) is an effective approach for deploying large language models (LLMs) under memory and latency constraints. Most existing PTQ methods determine quantization parameters by minimizing a layer-wise reconstruction…

人工智能 · 计算机科学 2026-05-11 Yanlong Zhao , Xiaoyuan Cheng , Huihang Liu , Baihua He , Xinyu Zhang , Harrison Bo Hua Zhu , Wenlong Chen , Li Zeng , Zhuo Sun

Large-scale pre-trained Vision-Language Models (VLMs) have gained prominence in various visual and multimodal tasks, yet the deployment of VLMs on downstream application platforms remains challenging due to their prohibitive requirements of…

计算机视觉与模式识别 · 计算机科学 2024-09-27 Huixin Sun , Runqi Wang , Yanjing Li , Xianbin Cao , Xiaolong Jiang , Yao Hu , Baochang Zhang

Current mainstream post-training quantization methods for large language models typically apply a uniform quantization strategy across all network layers, overlooking the substantial differences in algorithmic suitability among layers. To…

机器学习 · 计算机科学 2026-01-09 Jinhao Zhang , Yunquan Zhang , Daning Chen , JunSun , Zicheng Yan

Post-Training Quantization (PTQ) has received significant attention because it requires only a small set of calibration data to quantize a full-precision model, which is more practical in real-world applications in which full access to a…

计算机视觉与模式识别 · 计算机科学 2024-07-30 Cuong Pham , Hoang Anh Dung , Cuong C. Nguyen , Trung Le , Dinh Phung , Gustavo Carneiro , Thanh-Toan Do

Low-bit post-training quantization (PTQ) is a practical route to deploy reasoning-capable LLMs under tight memory and latency budgets, yet it can markedly impair mathematical reasoning (drops up to 69.81% in our harder settings). We address…

机器学习 · 计算机科学 2026-01-21 Zhen Li , Yupeng Su , Songmiao Wang , Runming Yang , Congkai Xie , Aofan Liu , Ming Li , Jiannong Cao , Yuan Xie , Ngai Wong , Hongxia Yang

Large Language Models (LLMs) are widely used across many domains, but their scale makes deployment challenging. Post-Training Quantization (PTQ) reduces memory footprint without retraining by leveraging a small calibration set. Recent…

机器学习 · 计算机科学 2026-04-16 Jaemin Kim , Sungkyun Kim , Junyeol Lee , Jiwon Seo

Diffusion models have shown remarkable performance in image synthesis by progressively estimating a smooth transition from a Gaussian distribution of noise to a real image. Unfortunately, their practical deployment is limited by slow…

机器学习 · 计算机科学 2026-03-03 Dung Anh Hoang , Cuong Pham anh Trung Le , Jianfei Cai , Thanh-Toan Do

Post-training quantization (PTQ) has emerged as a promising technique for mitigating memory consumption and computational costs in large language models (LLMs). However, a systematic examination of various quantization schemes, model…

机器学习 · 计算机科学 2023-05-29 Zhewei Yao , Xiaoxia Wu , Cheng Li , Stephen Youn , Yuxiong He

Uncertainty quantification (UQ) is essential for safe deployment of generative AI models such as large language models (LLMs), especially in high stakes applications. Conformal prediction (CP) offers a principled uncertainty quantification…

机器学习 · 计算机科学 2025-06-09 Sima Noorani , Shayan Kiyani , George Pappas , Hamed Hassani
‹ 上一页 1 2 3 10 下一页 ›