Related papers: HQP: Sensitivity-Aware Hybrid Quantization and Pru…

Neural networks are both computationally intensive and memory intensive, making them difficult to deploy on embedded systems with limited hardware resources. To address this limitation, we introduce "deep compression", a three stage…

Deploying Large Language Models (LLMs) on edge devices faces severe computational and memory constraints, limiting real-time processing and on-device intelligence. Hybrid architectures combining Structured State Space Models (SSMs) with…

Deep learning networks excel at classification, yet identifying minimal architectures that reliably solve a task remains challenging. We present a computational methodology for systematically exploring and analyzing the relationships among…

Camouflaged Object Detection (COD) aims to segment targets that share extreme textural and structural similarities with their complex environments. Leveraging their capacity for long-range dependency modeling, Transformer-based detectors…

The computational burden and inherent redundancy of large-scale datasets challenge the training of contemporary machine learning models. Data pruning offers a solution by selecting smaller, informative subsets, yet existing methods…

Neural radiance fields (NeRF) have garnered significant attention, with recent works such as Instant-NGP accelerating NeRF training and evaluation through a combination of hashgrid-based positional encoding and neural networks. However,…

The large computing and memory cost of deep neural networks (DNNs) often precludes their use in resource-constrained devices. Quantizing the parameters and operations to lower bit-precision offers substantial memory and energy savings for…

Hybrid LLM architectures that combine Attention and State Space Models (SSMs) achieve state-of-the-art accuracy and runtime performance. Recent work has demonstrated that applying compression and distillation to Attention-only models yields…

Post-Training Quantization (PTQ) and Quantization-Aware Training (QAT) represent two mainstream model quantization approaches. However, PTQ often leads to unacceptable performance degradation in quantized models, while QAT imposes…

Affective computing systems are increasingly embedded in pervasive and interactive environments, such as adaptive games, assistive technologies, and resource-constrained platforms, where computational efficiency must be balanced with…

Compressing Deep Neural Network (DNN) models to alleviate the storage and computation requirements is essential for practical applications, especially for resource limited devices. Although capable of reducing a reasonable amount of model…

With the tremendous success of deep learning, there exists imminent need to deploy deep learning models onto edge devices. To tackle the limited computing and storage resources in edge devices, model compression techniques have been widely…

In a quantitative sequential database, numerous efficient algorithms have been developed for high-utility sequential pattern mining (HUSPM). HUSPM establishes a relationship between frequency and significance in the real world and reflects…

Network pruning has been the driving force for the acceleration of neural networks and the alleviation of model storage/transmission burden. With the advent of AutoML and neural architecture search (NAS), pruning has become topical with…

Current inference systems for Mixture-of-Experts (MoE) models primarily employ static parallelization strategies. However, these static approaches cannot consistently achieve optimal performance across different inference scenarios, as they…

Ensemble learning has gain attention in resent deep learning research as a way to further boost the accuracy and generalizability of deep neural network (DNN) models. Recent ensemble training method explores different training algorithms or…

Federated Learning (FL) is a promising privacy-preserving distributed learning framework where a server aggregates models updated by multiple devices without accessing their private datasets. Hierarchical FL (HFL), as a device-edge-cloud…

PQuantML is a new open-source, hardware-aware neural network model compression library tailored to end-to-end workflows. Motivated by the need to deploy performant models to environments with strict latency constraints, PQuantML simplifies…

Pruning large neural networks while maintaining their performance is often desirable due to the reduced space and time complexity. In existing methods, pruning is done within an iterative optimization procedure with either heuristically…

This paper presents a novel framework combining group equivariant convolutional neural networks (G-CNNs) with equivariant-aware structured pruning to produce compact, transformation-invariant models for resource-constrained environments.…