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/pytorch/fairseq

공식 코드

wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations

https://github.com/pytorch/fbgemm

공식 코드

FBGEMM: Enabling High-Performance Low-Precision Deep Learning Inference

https://github.com/qdushl/waterloo-point-cloud-database-6.0

공식 코드

Perceptual Quality Assessment of Trisoup-Lifting Encoded 3D Point Clouds

https://github.com/qi-yangsjtu/ggsc

공식 코드

A Benchmark for Gaussian Splatting Compression and Quality Assessment Study

https://github.com/qianlou/SHE

공식 코드

SHE: A Fast and Accurate Deep Neural Network for Encrypted Data

https://github.com/qinnzou/Zero-Shot-Hashing

공식 코드

Transductive Zero-Shot Hashing for Multilabel Image Retrieval

https://github.com/qiuk2/aar

공식 코드

Efficient Autoregressive Audio Modeling via Next-Scale Prediction

https://github.com/qiuzx2/micpq

공식 코드

Efficient Document Retrieval by End-to-End Refining and Quantizing BERT Embedding with Contrastive Product Quantization

https://github.com/qualcomm-ai-research/fp8-quantization

공식 코드

FP8 Quantization: The Power of the Exponent

https://github.com/qualcomm-ai-research/lr-qat

공식 코드

Low-Rank Quantization-Aware Training for LLMs

https://github.com/qualcomm-ai-research/oscillations-qat

공식 코드

Overcoming Oscillations in Quantization-Aware Training

https://github.com/qualcomm-ai-research/transformer-quantization

공식 코드

Understanding and Overcoming the Challenges of Efficient Transformer Quantization

https://github.com/quantized-gbdt/quantized-gbdt

공식 코드

Quantized Training of Gradient Boosting Decision Trees

https://github.com/qvip22/data

공식 코드

QVIP: An ILP-based Formal Verification Approach for Quantized Neural Networks

https://github.com/qwenlm/qwen2

공식 코드

Qwen2 Technical Report

https://github.com/qyp2000/varsr

공식 코드

Visual Autoregressive Modeling for Image Super-Resolution

https://github.com/racai-ai/romanian-distilbert

공식 코드

Distilling the Knowledge of Romanian BERTs Using Multiple Teachers

https://github.com/rachmadvwp/snn4agents

공식 코드

SNN4Agents: A Framework for Developing Energy-Efficient Embodied Spiking Neural Networks for Autonomous Agents

https://github.com/raivnlab/adanns

공식 코드

AdANNS: A Framework for Adaptive Semantic Search

https://github.com/rajarshisaha95/distoptconstrcomm

공식 코드

Efficient Randomized Subspace Embeddings for Distributed Optimization under a Communication Budget

https://github.com/rajmadan96/softquantization

공식 코드

Soft Quantization using Entropic Regularization

https://github.com/rakutentech/hq

공식 코드

Efficient Cross-Modal Retrieval via Deep Binary Hashing and Quantization

https://github.com/rakutentech/iterative_training

공식 코드

Iterative Training: Finding Binary Weight Deep Neural Networks with Layer Binarization

https://github.com/ramdrop/edgevl

공식 코드

Self-Adapting Large Visual-Language Models to Edge Devices across Visual Modalities

https://github.com/ramoraydrake/amed

공식 코드

AMED: Automatic Mixed-Precision Quantization for Edge Devices

https://github.com/raywan-110/adaqp

공식 코드

Adaptive Message Quantization and Parallelization for Distributed Full-graph GNN Training

https://github.com/razvandu/layerwisequant

공식 코드

Layer-Wise Quantization: A Pragmatic and Effective Method for Quantizing LLMs Beyond Integer Bit-Levels

https://github.com/rishgoyal/FXPQuantCNN

공식 코드

Fixed-point Quantization of Convolutional Neural Networks for Quantized Inference on Embedded Platforms

https://github.com/rishi2019194/deep_learning_project

공식 코드

Extracting Usable Predictions from Quantized Networks through Uncertainty Quantification for OOD Detection

https://github.com/robobachelor/keyword-spotting-stm32

공식 코드

Keyword Spotting System and Evaluation of Pruning and Quantization Methods on Low-power Edge Microcontrollers

https://github.com/rocm/tensorcast

공식 코드

Error Diffusion: Post Training Quantization with Block-Scaled Number Formats for Neural Networks

https://github.com/rodrihgh/cissir

공식 코드

CISSIR: Beam Codebooks with Self-Interference Reduction Guarantees for Integrated Sensing and Communication Beyond 5G

https://github.com/rpelke/analog-cim-sim

공식 코드

Optimizing Binary and Ternary Neural Network Inference on RRAM Crossbars using CIM-Explorer

https://github.com/rpelke/cim-e

공식 코드

Optimizing Binary and Ternary Neural Network Inference on RRAM Crossbars using CIM-Explorer

https://github.com/ru-system-software-and-security/bppattack

공식 코드

BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning

https://github.com/rucaibox/lc-rec

공식 코드

Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation

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