Papers Model Compression
“Model Compression” 태그가 달린 논문 1,632편 · 필터 해제
LatentLLM: Attention-Aware Joint Tensor Compression
Modern foundation models such as large language models (LLMs) and large multi-modal models (LMMs) require a massive amount of computational and memory resources. We propose a new framework to convert such LLMs/LMMs into …
Model CompressionTensor DecompositionEdge-First Language Model Inference: Models, Metrics, and Tradeoffs
The widespread adoption of Language Models (LMs) across industries is driving interest in deploying these services across the computing continuum, from the cloud to the network edge. This shift aims to reduce costs, lowe…
BenchmarkingLanguage ModelingLanguage ModellingModel CompressionIs Quantum Optimization Ready? An Effort Towards Neural Network Compression using Adiabatic Quantum Computing
Quantum optimization is the most mature quantum computing technology to date, providing a promising approach towards efficiently solving complex combinatorial problems. Methods such as adiabatic quantum computing (AQC) h…
Model CompressionNeural Network CompressionQuantizationOn Multilingual Encoder Language Model Compression for Low-Resource Languages
In this paper, we combine two-step knowledge distillation, structured pruning, truncation, and vocabulary trimming for extremely compressing multilingual encoder-only language models for low-resource languages. Our novel…
Knowledge DistillationLanguage ModelingLanguage ModellingModel Compression+5Saten: Sparse Augmented Tensor Networks for Post-Training Compression of Large Language Models
The efficient implementation of large language models (LLMs) is crucial for deployment on resource-constrained devices. Low-rank tensor compression techniques, such as tensor-train (TT) networks, have been widely studied…
Model CompressionTensor NetworksRanDeS: Randomized Delta Superposition for Multi-Model Compression
From a multi-model compression perspective, model merging enables memory-efficient serving of multiple models fine-tuned from the same base, but suffers from degraded performance due to interference among their task-spec…
modelModel CompressionConsistent Quantity-Quality Control across Scenes for Deployment-Aware Gaussian Splatting
To reduce storage and computational costs, 3D Gaussian splatting (3DGS) seeks to minimize the number of Gaussians used while preserving high rendering quality, introducing an inherent trade-off between Gaussian quantity …
3DGSModel CompressionNovel View SynthesisLow-Complexity Inference in Continual Learning via Compressed Knowledge Transfer
Continual learning (CL) aims to train models that can learn a sequence of tasks without forgetting previously acquired knowledge. A core challenge in CL is balancing stability -- preserving performance on old tasks -- an…
class-incremental learningClass Incremental LearningContinual LearningIncremental Learning+3Semantic Retention and Extreme Compression in LLMs: Can We Have Both?
The exponential growth in Large Language Model (LLM) deployment has intensified the need for efficient model compression techniques to reduce computational and memory costs. While pruning and quantization have shown prom…
Language ModelingLanguage ModellingLarge Language ModelModel Compression+1KDH-MLTC: Knowledge Distillation for Healthcare Multi-Label Text Classification
The increasing volume of healthcare textual data requires computationally efficient, yet highly accurate classification approaches able to handle the nuanced and complex nature of medical terminology. This research prese…
ClassificationHyperparameter OptimizationKnowledge DistillationModel Compression+4Sponge Attacks on Sensing AI: Energy-Latency Vulnerabilities and Defense via Model Pruning
Recent studies have shown that sponge attacks can significantly increase the energy consumption and inference latency of deep neural networks (DNNs). However, prior work has focused primarily on computer vision and natur…
Model CompressionEdge-Optimized Deep Learning & Pattern Recognition Techniques for Non-Intrusive Load Monitoring of Energy Time Series
The growing global energy demand and the urgent need for sustainability call for innovative ways to boost energy efficiency. While advanced energy-saving systems exist, they often fall short without user engagement. Prov…
Model CompressionNon-Intrusive Load MonitoringTime SeriesOnboard Optimization and Learning: A Survey
Onboard learning is a transformative approach in edge AI, enabling real-time data processing, decision-making, and adaptive model training directly on resource-constrained devices without relying on centralized servers. …
Decision MakingModel CompressionPrivacy PreservingSurveyOptimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques
Large Language Models (LLMs) have revolutionized many areas of artificial intelligence (AI), but their substantial resource requirements limit their deployment on mobile and edge devices. This survey paper provides a com…
Knowledge DistillationMixture-of-ExpertsModel CompressionQuantizationRadio: Rate-Distortion Optimization for Large Language Model Compression
In recent years, the compression of large language models (LLMs) has emerged as a key problem in facilitating LLM deployment on resource-limited devices, reducing compute costs, and mitigating the environmental footprint…
Language ModelingLanguage ModellingLarge Language ModelModel Compression+1Smart Environmental Monitoring of Marine Pollution using Edge AI
Oil spill incidents pose severe threats to marine ecosystems and coastal environments, necessitating rapid detection and monitoring capabilities to mitigate environmental damage. In this paper, we demonstrate how artific…
Edge-computingModel CompressionTowards Faster and More Compact Foundation Models for Molecular Property Prediction
Advancements in machine learning for molecular property prediction have improved accuracy but at the expense of higher computational cost and longer training times. Recently, the Joint Multi-domain Pre-training (JMP) fou…
Model CompressionMolecular Property PredictionProperty PredictionLow-Rank Matrix Approximation for Neural Network Compression
Deep Neural Networks (DNNs) have encountered an emerging deployment challenge due to large and expensive memory and computation requirements. In this paper, we present a new Adaptive-Rank Singular Value Decomposition (AR…
Model CompressionNeural Network CompressionOn-Device Qwen2.5: Efficient LLM Inference with Model Compression and Hardware Acceleration
Transformer-based Large Language Models (LLMs) have significantly advanced AI capabilities but pose considerable challenges for deployment on edge devices due to high computational demands, memory bandwidth constraints, …
CPUModel CompressionQuantizationAerial Image Classification in Scarce and Unconstrained Environments via Conformal Prediction
This paper presents a comprehensive empirical analysis of conformal prediction methods on a challenging aerial image dataset featuring diverse events in unconstrained environments. Conformal prediction is a powerful post…
Conformal Predictionimage-classificationImage ClassificationModel Compression+1