Papers with Code 아카이브

Model Compression

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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.

Source: KD-MRI: A knowledge distillation framework for image reconstruction and image restoration in MRI workflow

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/toshas/sttp

공식 코드

Spectral Tensor Train Parameterization of Deep Learning Layers

https://github.com/toshas/tbasis

공식 코드

T-Basis: a Compact Representation for Neural Networks

https://github.com/transmuteai/trailmet

공식 코드

Rethinking Compression: Reduced Order Modelling of Latent Features in Large Language Models

https://github.com/ttttttris/flat-llm

공식 코드

FLAT-LLM: Fine-grained Low-rank Activation Space Transformation for Large Language Model Compression

https://github.com/tuda-hwai/basis_sharing

공식 코드

Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model Compression

https://github.com/tyq1024/rlx2

공식 코드

RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch

https://github.com/ucla-starai/sparsepc

공식 코드

Sparse Probabilistic Circuits via Pruning and Growing

https://github.com/uiuctml/localize-and-stitch

공식 코드

Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic

https://github.com/unites-lab/moe-quantization

공식 코드

Examining Post-Training Quantization for Mixture-of-Experts: A Benchmark

https://github.com/uw-mad-dash/GradCompressionUtility

공식 코드

On the Utility of Gradient Compression in Distributed Training Systems

https://github.com/v0lta/wavelet-network-compression

공식 코드

Neural network compression via learnable wavelet transforms

https://github.com/vbdi/casp

공식 코드

CASP: Compression of Large Multimodal Models Based on Attention Sparsity

https://github.com/vcerqueira/model_compression_forecasting

공식 코드

Model Compression for Dynamic Forecast Combination

https://github.com/vectozavr/thanos

공식 코드

Thanos: A Block-wise Pruning Algorithm for Efficient Large Language Model Compression

https://github.com/venturusbr/cv-model-compression

공식 코드

Computer Vision Model Compression Techniques for Embedded Systems: A Survey

https://github.com/wangcn0201/AutoMC

공식 코드

AutoMC: Automated Model Compression based on Domain Knowledge and Progressive search strategy

https://github.com/wearepal/compression-subgroup

공식 코드

Are Compressed Language Models Less Subgroup Robust?

https://github.com/wonchulSon/DGKD

공식 코드

Densely Guided Knowledge Distillation using Multiple Teacher Assistants

https://github.com/wyze-AI/AdaptiveDistillation

공식 코드

Adaptive Distillation: Aggregating Knowledge from Multiple Paths for Efficient Distillation

https://github.com/x-lance/mbs

공식 코드

Multilingual Brain Surgeon: Large Language Models Can be Compressed Leaving No Language Behind

https://github.com/xiaxin1998/eodrec

공식 코드

Efficient On-Device Session-Based Recommendation

https://github.com/xinychen/vars

공식 코드

Discovering Dynamic Patterns from Spatiotemporal Data with Time-Varying Low-Rank Autoregression

https://github.com/xrc10/cross-distill

공식 코드

Cross-lingual Distillation for Text Classification

https://github.com/xuguodong03/SSKD

공식 코드

Knowledge Distillation Meets Self-Supervision

https://github.com/xuguodong03/UNIXKD

공식 코드

Computation-Efficient Knowledge Distillation via Uncertainty-Aware Mixup

https://github.com/xujxyang/opentrans

공식 코드

Transferable and Principled Efficiency for Open-Vocabulary Segmentation

https://github.com/yanyang19/ImPart

공식 코드

ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs

https://github.com/yasir-ghunaim/efficient-jmp

공식 코드

Towards Faster and More Compact Foundation Models for Molecular Property Prediction

https://github.com/yeshaokai/Robustness-Aware-Pruning-ADMM

공식 코드

Adversarial Robustness vs Model Compression, or Both?

https://github.com/yifei-he/localize-and-stitch

공식 코드

Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic

https://github.com/yiyudl/delicate

공식 코드

Chemical transformer compression for accelerating both training and inference of molecular modeling

https://github.com/yjwu17/ADMM-Compression-for-SNNs

공식 코드

Comprehensive SNN Compression Using ADMM Optimization and Activity Regularization

https://github.com/ylimit/ModelDiff

공식 코드

ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detection

https://github.com/ymoslem/model-compression

공식 코드

Efficient Speech Translation through Model Compression and Knowledge Distillation

https://github.com/yoshitomo-matsubara/torchdistill

공식 코드

torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation

https://github.com/yqtianust/dflare

공식 코드

Finding Deviated Behaviors of the Compressed DNN Models for Image Classifications

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.