Papers with Code 아카이브
Computational Efficiency
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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/zirconium233/dtpf
공식 코드Distilling Textual Priors from LLM to Efficient Image Fusion
https://github.com/ziweihe/fovea-transformer
공식 코드Fovea Transformer: Efficient Long-Context Modeling with Structured Fine-to-Coarse Attention
https://github.com/ziyangwang007/mamba-unet
공식 코드Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentation
https://github.com/ziyuchen7/specnet2
공식 코드SpecNet2: Orthogonalization-free spectral embedding by neural networks
https://github.com/ziyueqingwan/localglobalattention
공식 코드Local-Global Attention: An Adaptive Mechanism for Multi-Scale Feature Integration
https://github.com/zju-fast-lab/fsgp_bgk
공식 코드Real-time Spatial-temporal Traversability Assessment via Feature-based Sparse Gaussian Process
https://github.com/zly555/mpewsvms
공식 코드Linear Algorithms for Robust and Scalable Nonparametric Multiclass Probability Estimation
https://github.com/zmyybc/alphanet
공식 코드AlphaNet: Scaling Up Local-frame-based Atomistic Interatomic Potential
https://github.com/zongqianli/prompt-tuning-survey
공식 코드https://github.com/zongqianwu/st-cot
공식 코드Rethinking Chain-of-Thought from the Perspective of Self-Training
https://github.com/zongrenzou/timehjpde4sciml
공식 코드https://github.com/zononhzy/lamnet
공식 코드Unifying Dimensions: A Linear Adaptive Approach to Lightweight Image Super-Resolution
https://github.com/zouyilin2000/pockit
공식 코드Vectorized Sparse Second-Order Forward Automatic Differentiation for Optimal Control Direct Methods
https://github.com/zrw00/graceful
공식 코드Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining
https://github.com/zwang78/moediff-sr
공식 코드MoEDiff-SR: Mixture of Experts-Guided Diffusion Model for Region-Adaptive MRI Super-Resolution
https://github.com/zxhuang1698/ZeroShape
공식 코드https://github.com/zxnyyyyy/sprmamba
공식 코드SPRMamba: Surgical Phase Recognition for Endoscopic Submucosal Dissection with Mamba
https://github.com/zyoungxu/garamost
공식 코드https://github.com/zzd1992/flashswinattention
공식 코드Flash Window Attention: speedup the attention computation for Swin Transformer
https://github.com/zzd1992/flashwindowattention
공식 코드Flash Window Attention: speedup the attention computation for Swin Transformer
https://gitlab.cg.tuwien.ac.at/srasoulzadeh/archcomplete.git
공식 코드https://gitlab.com/SCoRe-Group/SABNAtk
공식 코드https://gitlab.com/SCoRe-Group/SABNAtk-Benchmarks
공식 코드https://gitlab.com/TStepi/spyct
공식 코드https://gitlab.com/asolovykh/mlip-i-pi-tutorial
공식 코드Path-integral molecular dynamics with actively-trained and universal machine learning force fields
https://gitlab.com/trougnouf/rawnind_jddc
공식 코드Learning Joint Denoising, Demosaicing, and Compression from the Raw Natural Image Noise Dataset
https://github.com/0417keito/JEN-1-COMPOSER-pytorch
JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion Models
https://github.com/0417keito/JEN-1-pytorch
JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion Models
https://github.com/0jason000/Inception_V4
https://github.com/0jason000/inception_v3
https://github.com/1044197988/TF.Keras-Commonly-used-models
https://github.com/2023-MindSpore-1/ms-code-203
https://github.com/2024-MindSpore-1/Code7/tree/main/cspdarknet53
https://github.com/21-projects-for-deep-learning/image2text
https://github.com/AIGAnimation/CAMDM
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.