English
Related papers

Related papers: S2D: Selective Spectral Decay for Quantization-Fri…

200 papers

Post-Training Quantization (PTQ) enhances the efficiency of Large Language Models (LLMs) by enabling faster operation and compatibility with more accessible hardware through reduced memory usage, at the cost of small performance drops. We…

Machine Learning · Computer Science 2024-06-06 Davide Paglieri , Saurabh Dash , Tim Rocktäschel , Jack Parker-Holder

We investigate the functional role of emergent outliers in large language models, specifically attention sinks (a few tokens that consistently receive large attention logits) and residual sinks (a few fixed dimensions with persistently…

With the growing size of large language models, the role of quantization becomes increasingly significant. However, outliers present in weights or activations notably influence the performance of quantized models. Recently,…

Computation and Language · Computer Science 2024-02-20 Baohao Liao , Christof Monz

Quantization for deep neural networks (DNNs) is the process of mapping the parameter values of DNNs from original data types to other data types of lower precision to reduce model sizes and make inference faster. Quantization often maps…

Machine Learning · Computer Science 2025-02-07 Jaewoo Song , Fangzhen Lin

Regularization techniques such as L2 regularization (Weight Decay) and Dropout are fundamental to training deep neural networks, yet their underlying physical mechanisms regarding feature frequency selection remain poorly understood. In…

Machine Learning · Computer Science 2025-12-30 Jiahao Lu

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…

Machine Learning · Computer Science 2026-04-28 Ibne Farabi Shihab , Sanjeda Akter , Anuj Sharma

Adversarial training has emerged as a highly effective way to improve the robustness of deep neural networks (DNNs). It is typically conceptualized as a min-max optimization problem over model weights and adversarial perturbations, where…

Machine Learning · Computer Science 2026-03-03 Gaojie Jin , Xinping Yi , Wei Huang , Sven Schewe , Xiaowei Huang

Efficient deployment of 1-bit Large Language Models (LLMs) is hindered by activation outliers, which complicate quantization to low bit-widths. We introduce BitNet v2, a novel framework enabling native 4-bit activation quantization for…

Computation and Language · Computer Science 2025-06-16 Hongyu Wang , Shuming Ma , Furu Wei

We propose an empirical approach centered on the spectral dynamics of weights -- the behavior of singular values and vectors during optimization -- to unify and clarify several phenomena in deep learning. We identify a consistent bias in…

Transformer architecture has become the fundamental element of the widespread natural language processing~(NLP) models. With the trends of large NLP models, the increasing memory and computation costs hinder their efficient deployment on…

Machine Learning · Computer Science 2023-02-22 Xiuying Wei , Yunchen Zhang , Xiangguo Zhang , Ruihao Gong , Shanghang Zhang , Qi Zhang , Fengwei Yu , Xianglong Liu

Deep neural networks with adaptive configurations have gained increasing attention due to the instant and flexible deployment of these models on platforms with different resource budgets. In this paper, we investigate a novel option to…

Computer Vision and Pattern Recognition · Computer Science 2020-03-17 Qing Jin , Linjie Yang , Zhenyu Liao

As Large Language Models (LLMs) continue to scale in parameter count, deploying them on commodity hardware has become increasingly challenging. Post-Training Quantization (PTQ) addresses this by reducing the precision of model weights,…

Machine Learning · Computer Science 2025-12-03 Shashank Landge , Abhishek Patil , Tejas kamble , Bhushan Buddhivant , Priyanka Joshi

Regularization techniques help prevent overfitting and therefore improve the ability of convolutional neural networks (CNNs) to generalize. One reason for overfitting is the complex co-adaptations among different parts of the network, which…

Computer Vision and Pattern Recognition · Computer Science 2024-09-30 Rinor Cakaj , Jens Mehnert , Bin Yang

Weight-only post-training quantization (PTQ) is crucial for efficient Large Language Model (LLM) deployment but suffers from accuracy degradation caused by weight and activation outliers. Existing mitigation strategies often face critical…

Machine Learning · Computer Science 2026-02-10 Xi Chen , Ming Li , Junxi Li , Changsheng Li , Peisong Wang , Lizhong Ding , Ye Yuan , Guoren Wang

Speculative decoding is a powerful technique for reducing the latency of Large Language Models (LLMs), offering a fault-tolerant framework that enables the use of highly compressed draft models. In this work, we introduce Self-Distilled…

Computation and Language · Computer Science 2025-06-03 Mike Lasby , Nish Sinnadurai , Valavan Manohararajah , Sean Lie , Yani Ioannou , Vithursan Thangarasa

Quantized deep neural networks (QDNNs) are necessary for low-power, high throughput, and embedded applications. Previous studies mostly focused on developing optimization methods for the quantization of given models. However, quantization…

Machine Learning · Computer Science 2020-06-02 Yoonho Boo , Sungho Shin , Wonyong Sung

Large language models have demonstrated promising capabilities upon scaling up parameters. However, serving large language models incurs substantial computation and memory movement costs due to their large scale. Quantization methods have…

Machine Learning · Computer Science 2024-11-12 Ke Yi , Zengke Liu , Jianwei Zhang , Chengyuan Li , Tong Zhang , Junyang Lin , Jingren Zhou

Differentially-Private SGD (DP-SGD) and its adaptive variant DP-Adam are powerful techniques to protect user privacy when using sensitive data to train neural networks. During training, converting model weights and activations into…

Machine Learning · Computer Science 2026-04-17 Yubo Gao , Renbo Tu , Gennady Pekhimenko , Nandita Vijaykumar

Large language models (LLMs) excel at natural language tasks but face deployment challenges due to their growing size outpacing GPU memory advancements. Model quantization mitigates this issue by lowering weight and activation precision,…

Computation and Language · Computer Science 2025-12-17 Shizhuo Mao , Song Chen , Yi Kang

The emergence of accurate open large language models (LLMs) has sparked a push for advanced quantization techniques to enable efficient deployment on end-user devices. In this paper, we revisit the challenge of extreme LLM compression --…

Machine Learning · Computer Science 2026-04-09 Zhixiong Zhao , Fangxin Liu , Junjie Wang , Chenyang Guan , Zongwu Wang , Li Jiang , Haibing Guan