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/cordercorder/quant_eval

공식 코드

A Comprehensive Evaluation of Quantization Strategies for Large Language Models

https://github.com/coreylammie/memristive-seizure-detection-and-prediction-by-parallel-convolutional-neural-networks

공식 코드

Seizure Detection and Prediction by Parallel Memristive Convolutional Neural Networks

https://github.com/cornell-relaxml/quip-sharp

공식 코드

QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks

https://github.com/cornell-relaxml/yaqa

공식 코드

Model-Preserving Adaptive Rounding

https://github.com/cornell-zhang/dnn-gating

공식 코드

Precision Gating: Improving Neural Network Efficiency with Dynamic Dual-Precision Activations

https://github.com/cornell-zhang/dnn-quant-ocs

공식 코드

Improving Neural Network Quantization without Retraining using Outlier Channel Splitting

https://github.com/cornell-zhang/llm-datatypes

공식 코드

Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs

https://github.com/cosimorulli/emvb

공식 코드

Efficient Multi-Vector Dense Retrieval Using Bit Vectors

https://github.com/cps-research-group/cps-ntu-public

공식 코드

Design Methodology for Deep Out-of-Distribution Detectors in Real-Time Cyber-Physical Systems

https://github.com/crossmodalgroup/dynamicvectorquantization

공식 코드

Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantization

https://github.com/crossmodalgroup/maskedvectorquantization

공식 코드

Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation

https://github.com/csguoh/intlora

공식 코드

IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Models

https://github.com/csiro-mlai/deep-mpc

공식 코드

Secure Quantized Training for Deep Learning

https://github.com/cuiying123456/gqfedwavg

공식 코드

GQFedWAvg: Optimization-Based Quantized Federated Learning in General Edge Computing Systems

https://github.com/cuong-pv/MetaAug

공식 코드

MetaAug: Meta-Data Augmentation for Post-Training Quantization

https://github.com/cuong-pv/MetaAug-PTQ

공식 코드

MetaAug: Meta-Data Augmentation for Post-Training Quantization

https://github.com/cvlab-yonsei/EWGS

공식 코드

Network Quantization with Element-wise Gradient Scaling

https://github.com/cwitkowitz/guitar-transcription-continuous

공식 코드

FretNet: Continuous-Valued Pitch Contour Streaming for Polyphonic Guitar Tablature Transcription

https://github.com/d-becking/ECQx

공식 코드

ECQ$^{\text{x}}$: Explainability-Driven Quantization for Low-Bit and Sparse DNNs

https://github.com/dagabo98/dt-quadruped-locomotion

공식 코드

Tiny Reinforcement Learning for Quadruped Locomotion using Decision Transformers

https://github.com/dan-lb/integrated_encoding_for_QuanvNN

공식 코드

Integrated Encoding and Quantization to Enhance Quanvolutional Neural Networks

https://github.com/danelee2601/supervised-fcn

공식 코드

Vector Quantized Time Series Generation with a Bidirectional Prior Model

https://github.com/dao-ailab/flash-attention

공식 코드

FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision

https://github.com/dapeter/nas-for-kws

공식 코드

Resource-efficient DNNs for Keyword Spotting using Neural Architecture Search and Quantization

https://github.com/darshandeshpande/audio-spectral-enhancement

공식 코드

Audio Spectral Enhancement: Leveraging Autoencoders for Low Latency Reconstruction of Long, Lossy Audio Sequences

https://github.com/datamllab/bed_camera

공식 코드

BED: A Real-Time Object Detection System for Edge Devices

https://github.com/datamllab/bed_gui

공식 코드

BED: A Real-Time Object Detection System for Edge Devices

https://github.com/datamllab/bed_main

공식 코드

BED: A Real-Time Object Detection System for Edge Devices

https://github.com/davidfanzz/llm_decoding

공식 코드

A Thorough Examination of Decoding Methods in the Era of LLMs

https://github.com/davidstutz/mlsys2021-bit-error-robustness

공식 코드

Bit Error Robustness for Energy-Efficient DNN Accelerators

https://github.com/davidstutz/random-bit-error-robustness

공식 코드

Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Accelerators

https://github.com/davisyoshida/abnormal-floats

공식 코드

NF4 Isn't Information Theoretically Optimal (and that's Good)

https://github.com/dblalock/bolt

공식 코드

Bolt: Accelerated Data Mining with Fast Vector Compression

https://github.com/dcgm/pero-pretraining

공식 코드

Self-supervised Pre-training of Text Recognizers

https://github.com/dd-duda/awesome-vit-quantization-acceleration

공식 코드

Model Quantization and Hardware Acceleration for Vision Transformers: A Comprehensive Survey

https://github.com/dd-duda/bitdecoding

공식 코드

BitDecoding: Unlocking Tensor Cores for Long-Context LLMs Decoding with Low-Bit KV Cache

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