Related papers: Data Generation for Hardware-Friendly Post-Trainin…

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…

Post-training quantization (PTQ) plays a crucial role in the democratization of large language models (LLMs). However, existing low-bit quantization and sparsification techniques are difficult to balance accuracy and efficiency due to the…

Recently, an extensive amount of research has been focused on compressing and accelerating Deep Neural Networks (DNN). So far, high compression rate algorithms require part of the training dataset for a low precision calibration, or a…

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…

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…

Recent advancements in machine learning achieved by Deep Neural Networks (DNNs) have been significant. While demonstrating high accuracy, DNNs are associated with a huge number of parameters and computations, which leads to high memory…

Due to highly constrained computing power and memory, deploying 3D lidar-based detectors on edge devices equipped in autonomous vehicles and robots poses a crucial challenge. Being a convenient and straightforward model compression…

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…

AutoRegressive Visual Generation (ARVG) models retain an architecture compatible with language models, while achieving performance comparable to diffusion-based models. Quantization is commonly employed in neural networks to reduce model…

Structured pruning and quantization are fundamental techniques used to reduce the size of deep neural networks (DNNs) and typically are applied independently. Applying these techniques jointly via co-optimization has the potential to…

Network quantization is an essential procedure in deep learning for development of efficient fixed-point inference models on mobile or edge platforms. However, as datasets grow larger and privacy regulations become stricter, data sharing…

Recently, dataset-generation-based zero-shot learning has shown promising results by training a task-specific model with a dataset synthesized from large pre-trained language models (PLMs). The final task-specific model often achieves…

Hyperdimensional Computing (HDC) is emerging as a promising approach for edge AI, offering a balance between accuracy and efficiency. However, current HDC-based applications often rely on high-precision models and/or encoding matrices to…

Post-training quantization (PTQ) is the go-to compression technique for large generative models, such as stable diffusion or large language models. PTQ methods commonly keep the softmax activation in higher precision as it has been shown to…

Consider the following distributed optimization scenario. A worker has access to training data that it uses to compute the gradients while a server decides when to stop iterative computation based on its target accuracy or delay…

The use of low-bit quantization has emerged as an indispensable technique for enabling the efficient training of large-scale models. Despite its widespread empirical success, a rigorous theoretical understanding of its impact on learning…

Zero-shot recognition models require extensive training data for generalization. However, in zero-shot 3D classification, collecting 3D data and captions is costly and laborintensive, posing a significant barrier compared to 2D vision.…

Data-free quantization aims to achieve model quantization without accessing any authentic sample. It is significant in an application-oriented context involving data privacy. Converting noise vectors into synthetic samples through a…

Large language models (LLMs) deliver strong performance, but their high compute and memory costs make deployment difficult in resource-constrained scenarios. Weight-only post-training quantization (PTQ) is appealing, as it reduces memory…

A major limitation of prompt tuning is its dependence on large labeled training datasets. Under few-shot learning settings, prompt tuning lags far behind full-model fine-tuning, limiting its scope of application. In this paper, we leverage…