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/Gaochenyin/Low-Rank-Tensor-Block-Hazard-Model

공식 코드

Causal Customer Churn Analysis with Low-rank Tensor Block Hazard Model

https://github.com/Gbouna/RE-TCN

공식 코드

Action Recognition in Real-World Ambient Assisted Living Environment

https://github.com/Global-Ecosystem-Health-Observatory/TreeMort

공식 코드

Dual-Task Learning for Dead Tree Detection and Segmentation with Hybrid Self-Attention U-Nets in Aerial Imagery

https://github.com/GraphPKU/GeoNGNN

공식 코드

On the Completeness of Invariant Geometric Deep Learning Models

https://github.com/Guang000/Awesome-Dataset-Distillation

공식 코드

Hyperbolic Dataset Distillation

https://github.com/HZXu-526/Human-Avatar

공식 코드

Efficient Neural Implicit Representation for 3D Human Reconstruction

https://github.com/Hansaka006/StNN-Dynamical-Systems

공식 코드

A Low-complexity Structured Neural Network to Realize States of Dynamical Systems

https://github.com/HaokunChen245/FedDAT

공식 코드

FedPop: Federated Population-based Hyperparameter Tuning

https://github.com/HarukiMoriarty/RUST-CBS

공식 코드

Accelerating Focal Search in Multi-Agent Path Finding with Tighter Lower Bounds

https://github.com/Heidelberg-NLP/amr-metric-suite

공식 코드

AMR Similarity Metrics from Principles

https://github.com/HongyangLL/M3-JEPA

공식 코드

M3-Jepa: Multimodal Alignment via Multi-directional MoE based on the JEPA framework

https://github.com/IAAR-Shanghai/Meta-Chunking

공식 코드

MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System

https://github.com/IAAR-Shanghai/SEAP

공식 코드

SEAP: Training-free Sparse Expert Activation Pruning Unlock the Brainpower of Large Language Models

https://github.com/IRVLab/so_dso_place_recognition

공식 코드

A Fast and Robust Place Recognition Approach for Stereo Visual Odometry Using LiDAR Descriptors

https://github.com/IdePHICS/Repetita-Iuvant

공식 코드

Repetita Iuvant: Data Repetition Allows SGD to Learn High-Dimensional Multi-Index Functions

https://github.com/ImCharlesY/SepLUT

공식 코드

SepLUT: Separable Image-adaptive Lookup Tables for Real-time Image Enhancement

https://github.com/ImaGonEs/all4one

공식 코드

All4One: Symbiotic Neighbour Contrastive Learning via Self-Attention and Redundancy Reduction

https://github.com/IntelLabs/causality-lab

공식 코드

Bayesian Structure Learning by Recursive Bootstrap

https://github.com/IntelligentControlSystems/l4acados

공식 코드

L4acados: Learning-based models for acados, applied to Gaussian process-based predictive control

https://github.com/JLU-WangXu/Octopus_Inspired_Optimization_OIO

공식 코드

Octopus Inspired Optimization Algorithm: Multi-Level Structures and Parallel Computing Strategies

https://github.com/JeongHun0716/MMS-LLaMA

공식 코드

MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens

https://github.com/Jiamian-Wang/HSI_baseline

공식 코드

A Simple and Efficient Reconstruction Backbone for Snapshot Compressive Imaging

https://github.com/JiaxiHe/Image-and-Video-Dehazing

공식 코드

Fast Single Image Dehazing via Multilevel Wavelet Transform based Optimization

https://github.com/JinaLeejnl/2D-TPE

공식 코드

2D-TPE: Two-Dimensional Positional Encoding Enhances Table Understanding for Large Language Models

https://github.com/JingqingZ/Semantic-HPO

공식 코드

Unsupervised Annotation of Phenotypic Abnormalities via Semantic Latent Representations on Electronic Health Records

https://github.com/JunjH/Boosting-Light-Weight-Depth-Estimation

공식 코드

Boosting Light-Weight Depth Estimation Via Knowledge Distillation

https://github.com/JunjH/light-weight-depth-estimation

공식 코드

Boosting Light-Weight Depth Estimation Via Knowledge Distillation

https://github.com/Kabir-Ehsan/Transformer_on_FPGA

공식 코드

A Runtime-Adaptive Transformer Neural Network Accelerator on FPGAs

https://github.com/KaiqiZhang/admm-pruning

공식 코드

Systematic Weight Pruning of DNNs using Alternating Direction Method of Multipliers

https://github.com/Karel911/TRACER

공식 코드

TRACER: Extreme Attention Guided Salient Object Tracing Network

https://github.com/KarenUllrich/Tutorial_BayesianCompressionForDL

공식 코드

Bayesian Compression for Deep Learning

https://github.com/KarenUllrich/pytorch-backprojection

공식 코드

Differentiable probabilistic models of scientific imaging with the Fourier slice theorem

https://github.com/Kayaba-Akihiko/3DDX

공식 코드

3DDX: Bone Surface Reconstruction from a Single Standard-Geometry Radiograph via Dual-Face Depth Estimation

https://github.com/KellerJordan/Muon

공식 코드

Muon is Scalable for LLM Training

https://github.com/Key5n/IncFed-MDRS

공식 코드

Federated Learning with Reservoir State Analysis for Time Series Anomaly Detection

https://github.com/KiljaeL/LOO-StabCP

공식 코드

Leave-One-Out Stable Conformal Prediction

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