Papers with Code 아카이브
Model Compression
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 2
- 보존된 평가 기록
- 14
Model Compression is an actively pursued area of research over the last few years with the goal of deploying state-of-the-art deep networks in low-power and resource limited devices without significant drop in accuracy. Parameter pruning, low-rank factorization and weight quantization are some of the proposed methods to compress the size of deep networks.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Linearity-based neural network compression
DipSVD: Dual-importance Protected SVD for Efficient LLM Compression
RLRC: Reinforcement Learning-based Recovery for Compressed Vision-Language-Action Models
Model compression using knowledge distillation with integrated gradients
EAQuant: Enhancing Post-Training Quantization for MoE Models via Expert-Aware Optimization
Simple is what you need for efficient and accurate medical image segmentation
Attribution-guided Pruning for Compression, Circuit Discovery, and Targeted Correction in LLMs
FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation
Post-Training Quantization for Video Matting
Advances in Small-Footprint Keyword Spotting: A Comprehensive Review of Efficient Models and Algorithms
AWP: Activation-Aware Weight Pruning and Quantization with Projected Gradient Descent
MUC-G4: Minimal Unsat Core-Guided Incremental Verification for Deep Neural Network Compression
Structured Pruning and Quantization for Learned Image Compression
INSIGHT: A Survey of In-Network Systems for Intelligent, High-Efficiency AI and Topology Optimization
Smooth Model Compression without Fine-Tuning
FLAT-LLM: Fine-grained Low-rank Activation Space Transformation for Large Language Model Compression
Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates
Small Language Models: Architectures, Techniques, Evaluation, Problems and Future Adaptation
ResSVD: Residual Compensated SVD for Large Language Model Compression
Tensorization is a powerful but underexplored tool for compression and interpretability of neural networks
Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs
Efficient Speech Translation through Model Compression and Knowledge Distillation
Knowledge Grafting of Large Language Models
Efficient and Workload-Aware LLM Serving via Runtime Layer Swapping and KV Cache Resizing
Making deep neural networks work for medical audio: representation, compression and domain adaptation
LatentLLM: Attention-Aware Joint Tensor Compression
Is Quantum Optimization Ready? An Effort Towards Neural Network Compression using Adiabatic Quantum Computing
Edge-First Language Model Inference: Models, Metrics, and Tradeoffs
On Multilingual Encoder Language Model Compression for Low-Resource Languages
Certified Neural Approximations of Nonlinear Dynamics
Saten: Sparse Augmented Tensor Networks for Post-Training Compression of Large Language Models
RanDeS: Randomized Delta Superposition for Multi-Model Compression
Consistent Quantity-Quality Control across Scenes for Deployment-Aware Gaussian Splatting
Low-Complexity Inference in Continual Learning via Compressed Knowledge Transfer
KDH-MLTC: Knowledge Distillation for Healthcare Multi-Label Text Classification
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.