Papers Model Compression
“Model Compression” 태그가 달린 논문 1,632편 · 필터 해제
Large Language Model Compression via the Nested Activation-Aware Decomposition
In this paper, we tackle the critical challenge of compressing large language models (LLMs) to facilitate their practical deployment and broader adoption. We introduce a novel post-training compression paradigm that focu…
Language ModelingLanguage ModellingLarge Language ModelModel CompressionInhibiDistilbert: Knowledge Distillation for a ReLU and Addition-based Transformer
This work explores optimizing transformer-based language models by integrating model compression techniques with inhibitor attention, a novel alternative attention mechanism. Inhibitor attention employs Manhattan distanc…
Knowledge DistillationModel CompressionSentiment AnalysisClusComp: A Simple Paradigm for Model Compression and Efficient Finetuning
As large language models (LLMs) scale, model compression is crucial for edge deployment and accessibility. Weight-only quantization reduces model size but suffers from performance degradation at lower bit widths. Moreove…
GPUModel CompressionQuantizationCompMarkGS: Robust Watermarking for Compressed 3D Gaussian Splatting
3D Gaussian Splatting (3DGS) enables rapid differentiable rendering for 3D reconstruction and novel view synthesis, leading to its widespread commercial use. Consequently, copyright protection via watermarking has become…
3DGS3D ReconstructionModel CompressionNovel View Synthesis+1SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression
Despite significant advancements, the practical deployment of Large Language Models (LLMs) is often hampered by their immense sizes, highlighting the need for effective compression techniques. Singular Value Decompositio…
Language ModelingLanguage ModellingLarge Language ModelModel CompressionFragile Mastery: Are Domain-Specific Trade-Offs Undermining On-Device Language Models?
The application of on-device language models (ODLMs) on resource-constrained edge devices is a multi-dimensional problem that strikes a fine balance between computational effectiveness, memory, power usage, and linguisti…
Model CompressionRaspberry Pi 4Sometimes Painful but Certainly Promising: Feasibility and Trade-offs of Language Model Inference at the Edge
The rapid rise of Language Models (LMs) has expanded the capabilities of natural language processing, powering applications from text generation to complex decision-making. While state-of-the-art LMs often boast hundreds…
CPUGPULanguage ModelingLanguage Modelling+3Position-Aware Depth Decay Decoding ($D^3$): Boosting Large Language Model Inference Efficiency
Due to the large number of parameters, the inference phase of Large Language Models (LLMs) is resource-intensive. Unlike traditional model compression, which needs retraining, recent dynamic computation methods show that…
GSM8KLanguage ModelingLanguage ModellingLarge Language Model+2Are We There Yet? A Measurement Study of Efficiency for LLM Applications on Mobile Devices
Recent advancements in large language models (LLMs) have prompted interest in deploying these models on mobile devices to enable new applications without relying on cloud connectivity. However, the efficiency constraints…
CPUGPUModel CompressionTowards Superior Quantization Accuracy: A Layer-sensitive Approach
Large Vision and Language Models have exhibited remarkable human-like intelligence in tasks such as natural language comprehension, problem-solving, logical reasoning, and knowledge retrieval. However, training and servi…
Logical ReasoningModel CompressionQuantizationSensitivityEmpowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models
The rapid advancement of artificial intelligence (AI) technologies has led to an increasing deployment of AI models on edge and terminal devices, driven by the proliferation of the Internet of Things (IoT) and the need f…
Edge-computingModel CompressionSurveyIteRABRe: Iterative Recovery-Aided Block Reduction
Large Language Models (LLMs) have grown increasingly expensive to deploy, driving the need for effective model compression techniques. While block pruning offers a straightforward approach to reducing model size, existin…
Model CompressionACAM-KD: Adaptive and Cooperative Attention Masking for Knowledge Distillation
Dense visual prediction tasks, such as detection and segmentation, are crucial for time-critical applications (e.g., autonomous driving and video surveillance). While deep models achieve strong performance, their efficie…
Autonomous Drivingfeature selectionKnowledge DistillationModel Compression+3CASP: Compression of Large Multimodal Models Based on Attention Sparsity
In this work, we propose an extreme compression technique for Large Multimodal Models (LMMs). While previous studies have explored quantization as an efficient post-training compression method for Large Language Models (…
Model CompressionQuantizationLVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compression
Despite recent efforts in understanding the compression impact on large language models (LLMs) in terms of their downstream task performance and trustworthiness on relatively simpler uni-modal benchmarks (for example, qu…
BenchmarkingCommon Sense ReasoningHallucinationLanguage Modeling+6TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation
The challenge of reducing the size of Large Language Models (LLMs) while maintaining their performance has gained significant attention. However, existing methods, such as model distillation and transfer learning, often …
Model CompressionTransfer Learning10K is Enough: An Ultra-Lightweight Binarized Network for Infrared Small-Target Detection
The widespread deployment of InfRared Small-Target Detection(IRSTD) algorithms on edge devices necessitates the exploration of model compression techniques. Binary neural networks (BNNs) are distinguished by their except…
BinarizationModel CompressionBeyond the Tip of Efficiency: Uncovering the Submerged Threats of Jailbreak Attacks in Small Language Models
Small language models (SLMs) have become increasingly prominent in the deployment on edge devices due to their high efficiency and low computational cost. While researchers continue to advance the capabilities of SLMs th…
Knowledge DistillationModel CompressionQuantizationVision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategies
In recent years, vision transformers (ViTs) have emerged as powerful and promising techniques for computer vision tasks such as image classification, object detection, and segmentation. Unlike convolutional neural networ…
image-classificationImage ClassificationModel Compressionobject-detection+1AfroXLMR-Comet: Multilingual Knowledge Distillation with Attention Matching for Low-Resource languages
Language model compression through knowledge distillation has emerged as a promising approach for deploying large language models in resource-constrained environments. However, existing methods often struggle to maintain…
Knowledge DistillationLanguage ModelingLanguage ModellingModel Compression