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/rucaibox/quantizedempirical

공식 코드

Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study

https://github.com/ruhig6/ibvc

공식 코드

IBVC: Interpolation-driven B-frame Video Compression

https://github.com/ruikangliu/IntactKV

공식 코드

IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact

https://github.com/ruikangliu/flatquant

공식 코드

FlatQuant: Flatness Matters for LLM Quantization

https://github.com/ruikangliu/quantized-reasoning-models

공식 코드

Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models

https://github.com/ruiyinglu/hvq-trans

공식 코드

Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detection

https://github.com/runkzhang/epint

공식 코드

Cross-Modal Epileptic Signal Harmonization: Frequency Domain Mapping Quantization for Pre-training a Unified Neurophysiological Transformer

https://github.com/ruqizhang/low-precision-sgld

공식 코드

Low-Precision Stochastic Gradient Langevin Dynamics

https://github.com/s3l-official/qebverif

공식 코드

QEBVerif: Quantization Error Bound Verification of Neural Networks

https://github.com/sachitkuhar/plum

공식 코드

PLUM: Improving Inference Efficiency By Leveraging Repetition-Sparsity Trade-Off

https://github.com/sahajgarg/low_precision_nn

공식 코드

Confounding Tradeoffs for Neural Network Quantization

https://github.com/saic-fi/mobilequant

공식 코드

MobileQuant: Mobile-friendly Quantization for On-device Language Models

https://github.com/sail-sg/attention-sink

공식 코드

When Attention Sink Emerges in Language Models: An Empirical View

https://github.com/sail-sg/simlayerkv

공식 코드

SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction

https://github.com/saintslab/adver-fine

공식 코드

Adversarial Fine-tuning of Compressed Neural Networks for Joint Improvement of Robustness and Efficiency

https://github.com/saintslab/i-exact

공식 코드

Activation Compression of Graph Neural Networks using Block-wise Quantization with Improved Variance Minimization

https://github.com/samirmoustafa/mixq

공식 코드

Efficient Mixed Precision Quantization in Graph Neural Networks

https://github.com/samsad35/code-mdvae

공식 코드

A multimodal dynamical variational autoencoder for audiovisual speech representation learning

https://github.com/samsunglabs/myqasr

공식 코드

A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization

https://github.com/samuelhorvath/maestro-lod

공식 코드

Maestro: Uncovering Low-Rank Structures via Trainable Decomposition

https://github.com/sands-lab/layer-wise-aaai20

공식 코드

On the Discrepancy between the Theoretical Analysis and Practical Implementations of Compressed Communication for Distributed Deep Learning

https://github.com/saqibjaved1/MQAT

공식 코드

Modular Quantization-Aware Training for 6D Object Pose Estimation

https://github.com/saqibjaved1/QT-DoG

공식 코드

QT-DoG: Quantization-aware Training for Domain Generalization

https://github.com/satoru2001/cukdfir

공식 코드

Context Unaware Knowledge Distillation for Image Retrieval

https://github.com/satzbeleg/keras-hrp

공식 코드

Rediscovering Hashed Random Projections for Efficient Quantization of Contextualized Sentence Embeddings

https://github.com/satzbeleg/study-hrp

공식 코드

Rediscovering Hashed Random Projections for Efficient Quantization of Contextualized Sentence Embeddings

https://github.com/sauradip/gap

공식 코드

Post-Processing Temporal Action Detection

https://github.com/sauravpr/hyperbolic_federated_classification

공식 코드

Federated Classification in Hyperbolic Spaces via Secure Aggregation of Convex Hulls

https://github.com/scale-lab/FCNiris

공식 코드

A Resource-Efficient Embedded Iris Recognition System Using Fully Convolutional Networks

https://github.com/scut-bip-lab/ea-3dgs

공식 코드

EA-3DGS: Efficient and Adaptive 3D Gaussians with Highly Enhanced Quality for outdoor scenes

https://github.com/sdamirsa/llm-vlm-in-gastroenterology

공식 코드

Vision-Language and Large Language Model Performance in Gastroenterology: GPT, Claude, Llama, Phi, Mistral, Gemma, and Quantized Models

https://github.com/sebulo/LoQT

공식 코드

LoQT: Low-Rank Adapters for Quantized Pretraining

https://github.com/secretflow/spu

공식 코드

Ditto: Quantization-aware Secure Inference of Transformers upon MPC

https://github.com/secure-ai-systems-group/qu-anti-zation

공식 코드

Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes

https://github.com/sempraety/pruning-via-merging

공식 코드

Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging

https://github.com/seolabcornell/torch2chip

공식 코드

Torch2Chip: An End-to-end Customizable Deep Neural Network Compression and Deployment Toolkit for Prototype Hardware Accelerator Design

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