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/cfm-uestc/DRQ

공식 코드

Deep Recurrent Quantization for Generating Sequential Binary Codes

https://github.com/chandar-lab/efficientllms

공식 코드

Exploring Quantization for Efficient Pre-Training of Transformer Language Models

https://github.com/changyuanwang17/apq-dm

공식 코드

Towards Accurate Post-training Quantization for Diffusion Models

https://github.com/changyuanwang17/qvlm

공식 코드

Q-VLM: Post-training Quantization for Large Vision-Language Models

https://github.com/cheeun/cadyq

공식 코드

CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution

https://github.com/cheeun/odm

공식 코드

Overcoming Distribution Mismatch in Quantizing Image Super-Resolution Networks

https://github.com/cheliosoops/bitq

공식 코드

BitQ: Tailoring Block Floating Point Precision for Improved DNN Efficiency on Resource-Constrained Devices

https://github.com/chen-zhong-jing/co3_algorithm

공식 코드

Convert, compress, correct: Three steps toward communication-efficient DNN training

https://github.com/chengtao-lv/ptq4sam

공식 코드

PTQ4SAM: Post-Training Quantization for Segment Anything

https://github.com/chengzhang-98/lqer

공식 코드

LQER: Low-Rank Quantization Error Reconstruction for LLMs

https://github.com/chenllliang/dnd-transformer

공식 코드

A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation

https://github.com/chenmnz/prefixquant

공식 코드

PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization

https://github.com/chensy7/efficient-vit

공식 코드

Compressing Vision Transformers for Low-Resource Visual Learning

https://github.com/chentingpc/dpq_embedding_compression

공식 코드

Differentiable Product Quantization for End-to-End Embedding Compression

https://github.com/choijeongsoo/utut

공식 코드

Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation

https://github.com/chorowski-lab/hcpc

공식 코드

Variable-rate hierarchical CPC leads to acoustic unit discovery in speech

https://github.com/chris210634/mudg

공식 코드

Multimodal Unsupervised Domain Generalization by Retrieving Across the Modality Gap

https://github.com/chrisdong-thu/gaussiantoken

공식 코드

GaussianToken: An Effective Image Tokenizer with 2D Gaussian Splatting

https://github.com/chrundle/biprop

공식 코드

Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Network

https://github.com/chumingqian/Model_Compression_For_YOLOV3-V4

공식 코드

Group channel pruning and spatial attention distilling for object detection

https://github.com/chxy95/HDRUNet

공식 코드

HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization

https://github.com/cjf00000/StatQuant

공식 코드

A Statistical Framework for Low-bitwidth Training of Deep Neural Networks

https://github.com/clevercool/SQuant

공식 코드

SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation

https://github.com/clevercool/ant_micro22

공식 코드

ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization

https://github.com/clovaai/frostnet

공식 코드

FrostNet: Towards Quantization-Aware Network Architecture Search

https://github.com/clubiedong/kvcachequantization

공식 코드

QAQ: Quality Adaptive Quantization for LLM KV Cache

https://github.com/cmd2001/KVTuner

공식 코드

KVTuner: Sensitivity-Aware Layer-wise Mixed Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference

https://github.com/cmu-safari/rawhash

공식 코드

RawHash: Enabling Fast and Accurate Real-Time Analysis of Raw Nanopore Signals for Large Genomes

https://github.com/codermillat/StudyAbroadGPT

공식 코드

A LoRA-Based Approach to Fine-Tuning LLMs for Educational Guidance in Resource-Constrained Settings

https://github.com/codestar12/Parallel-Independent-Blockwise-Distillation

공식 코드

Parallel Blockwise Knowledge Distillation for Deep Neural Network Compression

https://github.com/cogsys-tuebingen/cp_eval

공식 코드

Comprehensive Analysis of the Object Detection Pipeline on UAVs

https://github.com/comeusr/low-precisionsghmc

공식 코드

Enhancing Low-Precision Sampling via Stochastic Gradient Hamiltonian Monte Carlo

https://github.com/compostieai/guava-disease-detection

공식 코드

Device-friendly Guava fruit and leaf disease detection using deep learning

https://github.com/concyclics/logquantkv

공식 코드

LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy Preservation

https://github.com/conzel/cerwu

공식 코드

Reducing Storage of Pretrained Neural Networks by Rate-Constrained Quantization and Entropy Coding

https://github.com/cool-xuan/vqflow

공식 코드

VQ-Flow: Taming Normalizing Flows for Multi-Class Anomaly Detection via Hierarchical Vector Quantization

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