Papers with Code 아카이브

Quantization

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 2
평가표: 10
보존된 평가 기록: 32

Quantization is a promising technique to reduce the computation cost of neural network training, which can replace high-cost floating-point numbers (e.g., float32) with low-cost fixed-point numbers (e.g., int8/int16).

Source: Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers

코드

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

https://github.com/fuxianghuang1/PWCF

공식 코드

Probability Weighted Compact Feature for Domain Adaptive Retrieval

https://github.com/fwesel/qff

공식 코드

Quantized Fourier and Polynomial Features for more Expressive Tensor Network Models

https://github.com/fxqzb/deep-geometry-post-processing

공식 코드

Deep Geometry Post-Processing for Decompressed Point Clouds

https://github.com/fzp0424/ec-guide-kddup-2024

공식 코드

EC-Guide: A Comprehensive E-Commerce Guide for Instruction Tuning and Quantization

https://github.com/gabriel-turinici/huber-energy-measure-quantization

공식 코드

Diversity in deep generative models and generative AI

https://github.com/gaffey/excp

공식 코드

ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking

https://github.com/gaochang-bjtu/1-bit-fqt

공식 코드

1-Bit FQT: Pushing the Limit of Fully Quantized Training to 1-bit

https://github.com/gaoj0017/RaBitQ

공식 코드

RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Search

https://github.com/gaoshen90/XLCNet

공식 코드

Lightweight Deep Learning Based Channel Estimation for Extremely Large-Scale Massive MIMO Systems

https://github.com/gatech-eic/edge-llm

공식 코드

EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Layerwise Unified Compression and Adaptive Layer Tuning and Voting

https://github.com/gauravfs-14/awesome-tinyml

공식 코드

From Tiny Machine Learning to Tiny Deep Learning: A Survey

https://github.com/geon0325/set2box

공식 코드

Set2Box: Similarity Preserving Representation Learning of Sets

https://github.com/georgia-tech-synergy-lab/LogarithmicPosit

공식 코드

Algorithm-Hardware Co-Design of Distribution-Aware Logarithmic-Posit Encodings for Efficient DNN Inference

https://github.com/georgia-tech-synergy-lab/clamp-vit

공식 코드

CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs

https://github.com/georgia-tech-synergy-lab/microscopiq-llm-quantization

공식 코드

MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization

https://github.com/ggerganov/llama.cpp

공식 코드

Highly Optimized Kernels and Fine-Grained Codebooks for LLM Inference on Arm CPUs

https://github.com/giclab/potacc

공식 코드

Accelerating PoT Quantization on Edge Devices

https://github.com/gilshm/sparq

공식 코드

Post-Training Sparsity-Aware Quantization

https://github.com/gimpong/AAAI21-WSDHQ

공식 코드

Weakly Supervised Deep Hyperspherical Quantization for Image Retrieval

https://github.com/gimpong/WWW22-HCQ

공식 코드

Hybrid Contrastive Quantization for Efficient Cross-View Video Retrieval

https://github.com/gistvision/bnas

공식 코드

Learning Architectures for Binary Networks

https://github.com/giuse/DNE

공식 코드

Playing Atari with Six Neurons

https://github.com/glemhel/activationsgradientscompressionformp

공식 코드

Activations and Gradients Compression for Model-Parallel Training

https://github.com/gmum/mango

공식 코드

Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text Attacks

https://github.com/gongcheng1919/bias-compensation

공식 코드

Minimize Quantization Output Error with Bias Compensation

https://github.com/goodevening13/aquakv

공식 코드

Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models

https://github.com/google-research/federated/tree/1b31b84/compressed_communication

공식 코드

Optimizing the Communication-Accuracy Trade-off in Federated Learning with Rate-Distortion Theory

https://github.com/google-research/federated/tree/master/distributed_dp

공식 코드

The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation

https://github.com/google-research/google-research

공식 코드

ES-ENAS: Efficient Evolutionary Optimization for Large Hybrid Search Spaces

https://github.com/google-research/google-research/tree/master/pruning_identified_exemplars

공식 코드

What Do Compressed Deep Neural Networks Forget?

https://github.com/google-research/google-research/tree/master/scann

공식 코드

Accelerating Large-Scale Inference with Anisotropic Vector Quantization

https://github.com/google/aqt

공식 코드

Binarized Neural Machine Translation

https://github.com/google/bband-adaband

공식 코드

Adaptive Debanding Filter

https://github.com/google/qkeras

공식 코드

Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors

https://github.com/googleinterns/learning-bag-of-words

공식 코드

Revealing and Protecting Labels in Distributed Training

https://github.com/goukoutaki/FSDH

공식 코드

Fast Supervised Discrete Hashing and its Analysis

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