Papers with Code 아카이브

Computational Efficiency

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 1
보존된 평가 기록: 1

Methods and optimizations to reduce the computational resources (e.g., time, memory, or power) needed for training and inference in models. This involves techniques that streamline processing, optimize algorithms, or leverage hardware to enhance performance without compromising accuracy.

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/jx-zhong-for-academic-purpose/Multibody_SE3

공식 코드

Multi-body SE(3) Equivariance for Unsupervised Rigid Segmentation and Motion Estimation

https://github.com/jzhang38/tinyllama

공식 코드

TinyLlama: An Open-Source Small Language Model

https://github.com/k2-fsa/icefall

공식 코드

CR-CTC: Consistency regularization on CTC for improved speech recognition

https://github.com/kai3316/yolic-labeling

공식 코드

YOLIC: An Efficient Method for Object Localization and Classification on Edge Devices

https://github.com/kaka-cao/m3amba

공식 코드

M$^3$amba: CLIP-driven Mamba Model for Multi-modal Remote Sensing Classification

https://github.com/kakaobrain/sparse-detr

공식 코드

Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity

https://github.com/kalviny/IMTA

공식 코드

Improved Techniques for Training Adaptive Deep Networks

https://github.com/kamanphoebe/look-into-moes

공식 코드

A Closer Look into Mixture-of-Experts in Large Language Models

https://github.com/karlnapf/nystrom-kexpfam

공식 코드

Efficient and principled score estimation with Nyström kernel exponential families

https://github.com/karlotness/nn-benchmark

공식 코드

An Extensible Benchmark Suite for Learning to Simulate Physical Systems

https://github.com/karma211225/karmaloop

공식 코드

Highly accurate and efficient deep learning paradigm for full-atom protein loop modeling with KarmaLoop

https://github.com/kateduffy/maiac-emulator

공식 코드

A framework for deep learning emulation of numerical models with a case study in satellite remote sensing

https://github.com/katharineshapcott/rank-similarity

공식 코드

Confusion-based rank similarity filters for computationally-efficient machine learning on high dimensional data

https://github.com/katiana22/latent-deeponet

공식 코드

Learning in latent spaces improves the predictive accuracy of deep neural operators

https://github.com/kaydotdev/stochastic-quantization

공식 코드

Robust Clustering on High-Dimensional Data with Stochastic Quantization

https://github.com/kazabana/ce-ssl

공식 코드

CE-SSL: Computation-Efficient Semi-Supervised Learning for ECG-based Cardiovascular Diseases Detection

https://github.com/kazabana/fastecg

공식 코드

CE-SSL: Computation-Efficient Semi-Supervised Learning for ECG-based Cardiovascular Diseases Detection

https://github.com/kbui1993/official_aitv_poisson_denoising

공식 코드

Weighted Anisotropic-Isotropic Total Variation for Poisson Denoising

https://github.com/kelicht/ract

공식 코드

Learning Decision Trees and Forests with Algorithmic Recourse

https://github.com/kentaroy47/training-domain-specific-models

공식 코드

Training Domain Specific Models for Energy-Efficient Object Detection

https://github.com/kenziyuliu/lora-fairness

공식 코드

On Fairness of Low-Rank Adaptation of Large Models

https://github.com/kevopoulosk/Parametric-kernel-based-DMD-using-deep-learning

공식 코드

A parametric framework for kernel-based dynamic mode decomposition using deep learning

https://github.com/khtae8250/falcon

공식 코드

Falcon: Fair Active Learning using Multi-armed Bandits

https://github.com/khtao/StainNet

공식 코드

StainNet: a fast and robust stain normalization network

https://github.com/khtao/paramnet

공식 코드

ParamNet: A Dynamic Parameter Network for Fast Multi-to-One Stain Normalization

https://github.com/kiljael/faithful_gsv

공식 코드

Faithful Group Shapley Value

https://github.com/killingbear999/iclrnn

공식 코드

Input Convex Lipschitz RNN: A Fast and Robust Approach for Engineering Tasks

https://github.com/killingbear999/iclstm

공식 코드

Real-Time Machine-Learning-Based Optimization Using Input Convex Long Short-Term Memory Network

https://github.com/kimtae55/DeepFDR

공식 코드

DeepFDR: A Deep Learning-based False Discovery Rate Control Method for Neuroimaging Data

https://github.com/kimtae55/fchmrf-lis

공식 코드

A False Discovery Rate Control Method Using a Fully Connected Hidden Markov Random Field for Neuroimaging Data

https://github.com/kingdalfgoodman/lota-qaf

공식 코드

LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-Tuning

https://github.com/kinit-sk/deni

공식 코드

Fighting Randomness with Randomness: Mitigating Optimisation Instability of Fine-Tuning using Delayed Ensemble and Noisy Interpolation

https://github.com/kishor-bhaumik/stlgru

공식 코드

STLGRU: Spatio-Temporal Lightweight Graph GRU for Traffic Flow Prediction

https://github.com/klabum/baeopt

공식 코드

Identification of stormwater control strategies and their associated uncertainties using Bayesian Optimization

https://github.com/klinehan1/prox_op_nn

공식 코드

Approximation of the Proximal Operator of the $\ell_\infty$ Norm Using a Neural Network

https://github.com/kmheckel/q-S5

공식 코드

Q-S5: Towards Quantized State Space Models

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