Related papers: Zero-Shot Quantization via Weight-Space Arithmetic
Deploying quantized deep neural network (DNN) models with resource adaptation capabilities on ubiquitous Internet of Things (IoT) devices to provide high-quality AI services can leverage the benefits of compression and meet multi-scenario…
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…
Quantization is an effective technique to reduce memory footprint, inference latency, and power consumption of deep learning models. However, existing quantization methods suffer from accuracy degradation compared to full-precision (FP)…
Neural network quantization is frequently used to optimize model size, latency and power consumption for on-device deployment of neural networks. In many cases, a target bit-width is set for an entire network, meaning every layer get…
This paper examines the use of Quantized Neural Networks (QNNs) for two resource-constrained scientific applications: automated calibration of semi-conductor quantum bits (qubits) and scientific particle detectors. We evaluate the…
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,…
We study the problem of training and certifying adversarially robust quantized neural networks (QNNs). Quantization is a technique for making neural networks more efficient by running them using low-bit integer arithmetic and is therefore…
Learning-based 3D reconstruction models, represented by Visual Geometry Grounded Transformers (VGGTs), have made remarkable progress with the use of large-scale transformers. Their prohibitive computational and memory costs severely hinder…
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…
Inference for state-of-the-art deep neural networks is computationally expensive, making them difficult to deploy on constrained hardware environments. An efficient way to reduce this complexity is to quantize the weight parameters and/or…
Post-training quantization (PTQ) has emerged as a promising technique to reduce the cost of large language models (LLMs). Specifically, PTQ can effectively mitigate memory consumption and reduce computational overhead in LLMs. To meet the…
Model merging has emerged as a powerful technique for combining task-specific weights, achieving superior performance in multi-target domain adaptation. However, when applied to practical scenarios, such as quantized models, new challenges…
Vector quantization (VQ) underpins modern generative and representation models by turning continuous latents into discrete tokens. Yet hard nearest-neighbor assignments are non-differentiable and are typically optimized with heuristic…
Post-training quantization offers an efficient pathway to deploy super-resolution models, yet existing methods treat weight and activation quantization independently, missing their critical interplay. Through controlled experiments on…
Zero-shot quantization (ZSQ) is promising for compressing and accelerating deep neural networks when the data for training full-precision models are inaccessible. In ZSQ, network quantization is performed using synthetic samples, thus, the…
As new optimizers gain traction and model quantization becomes standard for efficient deployment, a key question arises: how does the choice of optimizer affect model performance in the presence of quantization? Despite progress in both…
Referring Image Segmentation (RIS), aims to segment the object referred by a given sentence in an image by understanding both visual and linguistic information. However, existing RIS methods tend to explore top-performance models,…
Existing post-training quantization methods for large language models (LLMs) offer remarkable success. However, the increasingly marginal performance gains suggest that existing quantization strategies are insufficient to support the…
Post-training quantization (PTQ) efficiently compresses vision models, but unfortunately, it accompanies a certain degree of accuracy degradation. Reconstruction methods aim to enhance model performance by narrowing the gap between the…
End-to-end neural network models achieve improved performance on various automatic speech recognition (ASR) tasks. However, these models perform poorly on edge hardware due to large memory and computation requirements. While quantizing…