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/BaguaSys/bagua

공식 코드

BAGUA: Scaling up Distributed Learning with System Relaxations

https://github.com/BienLuky/EDA-DM

공식 코드

EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion Models

https://github.com/BoseCorp/efficient-neural-speech-enhancement

공식 코드

TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aids

https://github.com/BoyuanFeng/APNN-TC

공식 코드

APNN-TC: Accelerating Arbitrary Precision Neural Networks on Ampere GPU Tensor Cores

https://github.com/BurakHasircioglu/cep-fl

공식 코드

Communication Efficient Private Federated Learning Using Dithering

https://github.com/ByteFlow-AI/TokenFlow

공식 코드

TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation

https://github.com/CAT-teams/CAT

공식 코드

CAT: Compression-Aware Training for bandwidth reduction

https://github.com/CQUlearningsystemgroup/BitwiseBottleneck

공식 코드

Neural Network Activation Quantization with Bitwise Information Bottlenecks

https://github.com/CameronDiao/GLVQ-For-Classification-In-Randomized-NN-And-HDC

공식 코드

Generalized Learning Vector Quantization for Classification in Randomized Neural Networks and Hyperdimensional Computing

https://github.com/CandleLabAI/MotionAura-ICLR-2025

공식 코드

MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion

https://github.com/ChaofanTao/FAT_Quantization

공식 코드

FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware Transformation

https://github.com/Cheeun/AdaBM

공식 코드

AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resolution

https://github.com/Cheeun/DAQ-pytorch

공식 코드

DAQ: Channel-Wise Distribution-Aware Quantization for Deep Image Super-Resolution Networks

https://github.com/Cornell-RelaxML/QuIP

공식 코드

QuIP: 2-Bit Quantization of Large Language Models With Guarantees

https://github.com/Cornell-RelaxML/qtip

공식 코드

QTIP: Quantization with Trellises and Incoherence Processing

https://github.com/DSobscure/cgi_drl_platform

공식 코드

Identifying and Clustering Counter Relationships of Team Compositions in PvP Games for Efficient Balance Analysis

https://github.com/DZY122/DiTAS

공식 코드

DiTAS: Quantizing Diffusion Transformers via Enhanced Activation Smoothing

https://github.com/DequanWang/CoDeNet

공식 코드

Algorithm-hardware Co-design for Deformable Convolution

https://github.com/E-Nyamsuren/qLMM-Lua-Eval-Pipeline

공식 코드

Evaluating Quantized Large Language Models for Code Generation on Low-Resource Language Benchmarks

https://github.com/EkaterinaXie/LiteVAR

공식 코드

LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and Quantization

https://github.com/EunhyeokPark/PROFIT

공식 코드

PROFIT: A Novel Training Method for sub-4-bit MobileNet Models

https://github.com/ForzaETH/LLMxRobot

공식 코드

Enhancing Autonomous Driving Systems with On-Board Deployed Large Language Models

https://github.com/Fourier7754/AsymFormer

공식 코드

AsymFormer: Asymmetrical Cross-Modal Representation Learning for Mobile Platform Real-Time RGB-D Semantic Segmentation

https://github.com/GoatWu/APHQ-ViT

공식 코드

APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers

https://github.com/GoatWu/AdaLog

공식 코드

AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer

https://github.com/GongCheng1919/VecQ

공식 코드

VecQ: Minimal Loss DNN Model Compression With Vectorized Weight Quantization

https://github.com/Guoxoug/PTQ-acc-cal

공식 코드

An Underexplored Dilemma between Confidence and Calibration in Quantized Neural Networks

https://github.com/HandH1998/QQQ

공식 코드

QQQ: Quality Quattuor-Bit Quantization for Large Language Models

https://github.com/HarleyHK/JMPF

공식 코드

Joint Maximum Purity Forest with Application to Image Super-Resolution

https://github.com/HazyResearch/lp_rffs

공식 코드

Low-Precision Random Fourier Features for Memory-Constrained Kernel Approximation

https://github.com/HazyResearch/smallfry

공식 코드

On the Downstream Performance of Compressed Word Embeddings

https://github.com/HengRuiZ/brelu

공식 코드

Efficient Integer-Arithmetic-Only Convolutional Neural Networks

https://github.com/Humengxian/Efficient-Text-driven-Motion-Generation-via-Latent-Consistency-Training

공식 코드

Efficient Text-driven Motion Generation via Latent Consistency Training

https://github.com/IDEA-Emdoor-Lab/UniTTS

공식 코드

UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic information

https://github.com/IIP-Group/1BOX-MIMO-OFDM-simulator

공식 코드

Algorithm and VLSI Design for 1-bit Data Detection in Massive MIMO-OFDM

https://github.com/IIP-Sogang/speech-pooling-benchmark

공식 코드

Unsupervised Speech Representation Pooling Using Vector Quantization

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