Papers Model Compression
“Model Compression” 태그가 달린 논문 1,632편 · 필터 해제
Tensorization of neural networks for improved privacy and interpretability
We present a tensorization algorithm for constructing tensor train representations of functions, drawing on sketching and cross interpolation ideas. The method only requires black-box access to the target function and a …
Model CompressionNeural Architecture Codesign for Fast Physics Applications
We develop a pipeline to streamline neural architecture codesign for physics applications to reduce the need for ML expertise when designing models for novel tasks. Our method employs neural architecture search and netwo…
High-Level SynthesisModel CompressionNetwork PruningNeural Architecture Search+1UPAQ: A Framework for Real-Time and Energy-Efficient 3D Object Detection in Autonomous Vehicles
To enhance perception in autonomous vehicles (AVs), recent efforts are concentrating on 3D object detectors, which deliver more comprehensive predictions than traditional 2D object detectors, at the cost of increased mem…
3D Object DetectionAutonomous VehiclesModel CompressionObject+3CURing Large Models: Compression via CUR Decomposition
Large deep learning models have achieved remarkable success but are resource-intensive, posing challenges such as memory usage. We introduce CURing, a novel model compression method based on CUR matrix decomposition, whi…
Model CompressionEffective and Efficient Mixed Precision Quantization of Speech Foundation Models
This paper presents a novel mixed-precision quantization approach for speech foundation models that tightly integrates mixed-precision learning and quantized model parameter estimation into one single model compression s…
Model Compressionparameter estimationQuantizationLightGNN: Simple Graph Neural Network for Recommendation
Graph neural networks (GNNs) have demonstrated superior performance in collaborative recommendation through their ability to conduct high-order representation smoothing, effectively capturing structural information withi…
Computational EfficiencyGraph Neural NetworkKnowledge DistillationModel CompressionStrategic Fusion Optimizes Transformer Compression
This study investigates transformer model compression by systematically pruning its layers. We evaluated 14 pruning strategies across nine diverse datasets, including 12 strategies based on different signals obtained fro…
Knowledge DistillationModel CompressionOptimizing Small Language Models for In-Vehicle Function-Calling
We propose a holistic approach for deploying Small Language Models (SLMs) as function-calling agents within vehicles as edge devices, offering a more flexible and robust alternative to traditional rule-based systems. By …
Model CompressionQuantizationRandom Conditioning for Diffusion Model Compression with Distillation
Diffusion models generate high-quality images through progressive denoising but are computationally intensive due to large model sizes and repeated sampling. Knowledge distillation--transferring knowledge from a comp…
DenoisingKnowledge DistillationmodelModel CompressionCoA: Towards Real Image Dehazing via Compression-and-Adaptation
Learning-based image dehazing algorithms have shown remarkable success in synthetic domains. However, real image dehazing is still in suspense due to computational resource constraints and the diversity of real-world…
Image DehazingModel CompressionOnce-Tuning-Multiple-Variants: Tuning Once and Expanded as Multiple Vision-Language Model Variants
Vision-language model (VLM) is one of the most important models for multi-modal tasks. Real industrial applications often meet the challenge of adapting VLMs to different scenarios, such as varying hardware platforms…
Language ModelingLanguage ModellingModel CompressionDeepCompress-ViT: Rethinking Model Compression to Enhance Efficiency of Vision Transformers at the Edge
Vision Transformers (ViTs) excel in tackling complex vision tasks, yet their substantial size poses significant challenges for applications on resource-constrained edge devices. The increased size of these models lea…
Model CompressionImproving Acoustic Scene Classification in Low-Resource Conditions
Acoustic Scene Classification (ASC) identifies an environment based on an audio signal. This paper explores ASC in low-resource conditions and proposes a novel model, DS-FlexiNet, which combines depthwise separable convo…
Acoustic Scene ClassificationClassificationData AugmentationKnowledge Distillation+3Feature Alignment-Based Knowledge Distillation for Efficient Compression of Large Language Models
This study proposes a knowledge distillation algorithm based on large language models and feature alignment, aiming to effectively transfer the knowledge of large pre-trained models into lightweight student models, there…
Knowledge DistillationModel CompressionSelf-Supervised LearningTransfer LearningOptimization and Scalability of Collaborative Filtering Algorithms in Large Language Models
With the rapid development of large language models (LLMs) and the growing demand for personalized content, recommendation systems have become critical in enhancing user experience and driving engagement. Collaborative f…
Collaborative FilteringComputational EfficiencyModel CompressionRecommendation SystemsHTR-JAND: Handwritten Text Recognition with Joint Attention Network and Knowledge Distillation
Despite significant advances in deep learning, current Handwritten Text Recognition (HTR) systems struggle with the inherent complexity of historical documents, including diverse writing styles, degraded text quality, an…
Computational EfficiencyHandwritten Text RecognitionHTRKnowledge Distillation+4Singular Value Scaling: Efficient Generative Model Compression via Pruned Weights Refinement
While pruning methods effectively maintain model performance without extra training costs, they often focus solely on preserving crucial connections, overlooking the impact of pruned weights on subsequent fine-tuning or …
Model CompressionCoSurfGS:Collaborative 3D Surface Gaussian Splatting with Distributed Learning for Large Scene Reconstruction
3D Gaussian Splatting (3DGS) has demonstrated impressive performance in scene reconstruction. However, most existing GS-based surface reconstruction methods focus on 3D objects or limited scenes. Directly applying these …
3DGSGPUModel CompressionSurface ReconstructionGQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference
With the rapid growth in the scale and complexity of large language models (LLMs), the costs of training and inference have risen substantially. Model compression has emerged as a mainstream solution to reduce memory usa…
GPULanguage ModelingLanguage ModellingLarge Language Model+2Edge-AI for Agriculture: Lightweight Vision Models for Disease Detection in Resource-Limited Settings
This research paper presents the development of a lightweight and efficient computer vision pipeline aimed at assisting farmers in detecting orange diseases using minimal resources. The proposed system integrates advance…
Computational EfficiencyFederated LearningModel Compressionobject-detection+1