English
Related papers

Related papers: Leveraging Automated Mixed-Low-Precision Quantizat…

200 papers

Neural network quantization procedure is the necessary step for porting of neural networks to mobile devices. Quantization allows accelerating the inference, reducing memory consumption and model size. It can be performed without…

Machine Learning · Computer Science 2019-06-27 Alexander Goncharenko , Andrey Denisov , Sergey Alyamkin , Evgeny Terentev

Deep learning-based image compression (LIC) has achieved state-of-the-art rate-distortion (RD) performance, yet deploying these models on resource-constrained FPGAs remains a major challenge. This work presents a complete, multi-stage…

Computer Vision and Pattern Recognition · Computer Science 2025-11-24 Jiaxun Fang , Li Chen

Mixed-precision Deep Neural Networks achieve the energy efficiency and throughput needed for hardware deployment, particularly when the resources are limited, without sacrificing accuracy. However, the optimal per-layer bit precision that…

Machine Learning · Computer Science 2022-08-15 Mariam Rakka , Mohammed E. Fouda , Pramod Khargonekar , Fadi Kurdahi

Deep neural network (DNN)-based policy models like vision-language-action (VLA) models are transformative in automating complex decision-making across applications by interpreting multi-modal data. However, scaling these models greatly…

Robotics · Computer Science 2024-12-03 Seongmin Park , Hyungmin Kim , Wonseok Jeon , Juyoung Yang , Byeongwook Jeon , Yoonseon Oh , Jungwook Choi

One of the primary challenges in optimizing large language models (LLMs) for long-context inference lies in the high memory consumption of the Key-Value (KV) cache. Existing approaches, such as quantization, have demonstrated promising…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Wei Tao , Haocheng Lu , Xiaoyang Qu , Bin Zhang , Kai Lu , Jiguang Wan , Jianzong Wang

IoT devices based on microcontroller units (MCU) provide ultra-low power consumption and ubiquitous computation for near-sensor deep learning models (DNN). However, the memory of MCU is usually 2-3 orders of magnitude smaller than mobile…

Hardware Architecture · Computer Science 2024-06-12 Size Zheng , Renze Chen , Meng Li , Zihao Ye , Luis Ceze , Yun Liang

Mixture-of-Experts Large Language Models (MoE-LLMs) achieve strong performance but incur substantial memory overhead due to massive expert parameters. Mixed-precision quantization mitigates this cost by allocating expert-wise bit-widths…

Machine Learning · Computer Science 2026-05-25 Jianing Deng , Song Wang , Dongwei Wang , Zijie Liu , Tianlong Chen , Huanrui Yang , Jingtong Hu

Running Deep Neural Network (DNN) models on devices with limited computational capability is a challenge due to large compute and memory requirements. Quantized Neural Networks (QNNs) have emerged as a potential solution to this problem,…

Computer Vision and Pattern Recognition · Computer Science 2018-05-31 Yaman Umuroglu , Magnus Jahre

Deep convolutional neural network (DCNN) has achieved remarkable performance on object detection and speech recognition in recent years. However, the excellent performance of a DCNN incurs high computational complexity and large memory…

Computer Vision and Pattern Recognition · Computer Science 2016-08-09 Fangxuan Sun , Jun Lin , Zhongfeng Wang

Due to the promising advantages in space compression and inference acceleration, quantized representation learning for recommender systems has become an emerging research direction recently. As the target is to embed latent features in the…

Information Retrieval · Computer Science 2021-12-06 Yankai Chen , Yifei Zhang , Yingxue Zhang , Huifeng Guo , Jingjie Li , Ruiming Tang , Xiuqiang He , Irwin King

Deploying deep neural networks on resource-constrained 6G edge devices demands aggressive compression with minimal accuracy loss. Quantization-Aware Training (QAT) has emerged as a leading compression approach; however, existing…

This study addresses the deployment challenges of integer-only quantized Transformers on resource-constrained embedded FPGAs (Xilinx Spartan-7 XC7S15). We enhanced the flexibility of our VHDL template by introducing a selectable resource…

Machine Learning · Computer Science 2026-04-22 Tianheng Ling , Chao Qian , Gregor Schiele

As deep learning (DL) is being rapidly pushed to edge computing, researchers invented various ways to make inference computation more efficient on mobile/IoT devices, such as network pruning, parameter compression, and etc. Quantization, as…

Computer Vision and Pattern Recognition · Computer Science 2019-03-13 Tao Sheng , Chen Feng , Shaojie Zhuo , Xiaopeng Zhang , Liang Shen , Mickey Aleksic

Quantization is essential for efficient large language model (LLM) inference, yet the dequantization step-converting low-bit weights back to high-precision for matrix multiplication has become a critical bottleneck on modern AI…

Machine Learning · Statistics 2026-05-15 Lingchao Zheng , Yuwei Fan , Jun Li , Chengqiu Hu , Qichen Liao , Junyi Fan , Rui Shi , Fangzheng Miao

Recognition of overlapped speech has been a highly challenging task to date. State-of-the-art multi-channel speech separation system are becoming increasingly complex and expensive for practical applications. To this end, low-bit neural…

Sound · Computer Science 2021-11-30 Junhao Xu , Jianwei Yu , Xunying Liu , Helen Meng

Efficient deep neural network (DNN) inference on mobile or embedded devices typically involves quantization of the network parameters and activations. In particular, mixed precision networks achieve better performance than networks with…

Quantization of weights and activations in Deep Neural Networks (DNNs) is a powerful technique for network compression, and has enjoyed significant attention and success. However, much of the inference-time benefit of quantization is…

Performance · Computer Science 2019-12-13 Andrew Anderson , David Gregg

Conventional multiply-accumulate (MAC) operations have long dominated computation time for deep neural networks (DNNs), espcially convolutional neural networks (CNNs). Recently, product quantization (PQ) has been applied to these workloads,…

Hardware Architecture · Computer Science 2024-04-01 Ahmed F. AbouElhamayed , Angela Cui , Javier Fernandez-Marques , Nicholas D. Lane , Mohamed S. Abdelfattah

Model quantization is widely applied for compressing and accelerating deep neural networks (DNNs). However, conventional Quantization-Aware Training (QAT) focuses on training DNNs with uniform bit-width. The bit-width settings vary across…

Computer Vision and Pattern Recognition · Computer Science 2025-02-04 Haiduo Huang , Zhenhua Liu , Tian Xia , Wenzhe zhao , Pengju Ren

In the era of large language models (LLMs), weight-activation quantization helps fit models on edge device by reducing memory and compute bit-widths. However, three challenges persist for energy constrained hardware: (1) even after…

Machine Learning · Computer Science 2025-10-23 Chenyu Wang , Zhanglu Yan , Zhi Zhou , Xu Chen , Weng-Fai Wong