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/ZJZAC/Passport-aware-Normalization

공식 코드

Passport-aware Normalization for Deep Model Protection

https://github.com/Zinoex/certified-neural-approximations

공식 코드

Certified Neural Approximations of Nonlinear Dynamics

https://github.com/aaai-24/generative-based-kd

공식 코드

Generative Model-based Feature Knowledge Distillation for Action Recognition

https://github.com/aboveparadise/llmcbench

공식 코드

LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment

https://github.com/adrianbzg/tinyroberta-distillation-qa-es

공식 코드

Language Model Knowledge Distillation for Efficient Question Answering in Spanish

https://github.com/ahnobari/ActivationInformedMerging

공식 코드

Activation-Informed Merging of Large Language Models

https://github.com/aim-uofa/loraprune

공식 코드

LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning

https://github.com/aiot-mlsys-lab/svd-llm

공식 코드

SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression

https://github.com/aispeech-lab/LiMuSE

공식 코드

LiMuSE: Lightweight Multi-modal Speaker Extraction

https://github.com/albertomarchisio/swifttron

공식 코드

SwiftTron: An Efficient Hardware Accelerator for Quantized Transformers

https://github.com/alexandertheus/intra-fusion

공식 코드

Towards Meta-Pruning via Optimal Transport

https://github.com/algohunt/vqrf

공식 코드

Compressing Volumetric Radiance Fields to 1 MB

https://github.com/algorithmicresearchgroup/ml-research-agent

공식 코드

ML Research Benchmark

https://github.com/alibaba/AliceMind

공식 코드

From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model Compression

https://github.com/alibaba/EasyNLP

공식 코드

Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains

https://github.com/amanmohanty/idl-nncompress

공식 코드

Efficient CNN-LSTM based Image Captioning using Neural Network Compression

https://github.com/amazon-research/dq-bart

공식 코드

DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization

https://github.com/amirgholami/ZeroQ

공식 코드

ZeroQ: A Novel Zero Shot Quantization Framework

https://github.com/an-yongqi/systematic-outliers

공식 코드

Systematic Outliers in Large Language Models

https://github.com/ana-oprescu/greenllms

공식 코드

An exploration of the effect of quantisation on energy consumption and inference time of StarCoder2

https://github.com/andreacos/deep-neural-networks-robust-watermark

공식 코드

Robust and Large-Payload DNN Watermarking via Fixed, Distribution-Optimized, Weights

https://github.com/anony4paper/quan_study

공식 코드

Characterizing and Understanding the Behavior of Quantized Models for Reliable Deployment

https://github.com/antspy/quantized_distillation

공식 코드

Model compression via distillation and quantization

https://github.com/apple/ml-spin

공식 코드

SPIN: An Empirical Evaluation on Sharing Parameters of Isotropic Networks

https://github.com/ars-ashuha/variational-dropout-sparsifies-dnn

공식 코드

The State of Sparsity in Deep Neural Networks

https://github.com/asahi417/lm-vocab-trimmer

공식 코드

An Efficient Multilingual Language Model Compression through Vocabulary Trimming

https://github.com/asappresearch/flop

공식 코드

Structured Pruning of Large Language Models

https://github.com/augustgw/early-exit-transformer

공식 코드

Training dynamic models using early exits for automatic speech recognition on resource-constrained devices

https://github.com/biarmic/pytorch-compression-for-mcu

공식 코드

Deep Compression for PyTorch Model Deployment on Microcontrollers

https://github.com/bigdata-inha/Pool-of-Experts-code

공식 코드

Pool of Experts: Realtime Querying Specialized Knowledge in Massive Neural Networks

https://github.com/blauigris/jumpstart-cpaior

공식 코드

Training Thinner and Deeper Neural Networks: Jumpstart Regularization

https://github.com/bnkausik/occam_gradient_descent

공식 코드

Occam Gradient Descent

https://github.com/brucewsy/ad-kd

공식 코드

AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression

https://github.com/brycexu/BNN_Kernel

공식 코드

A Computing Kernel for Network Binarization on PyTorch

https://github.com/bytedance/abq-llm

공식 코드

ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models

https://github.com/cambridge-mlg/miracle

공식 코드

Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters

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