https://github.com/yunusa2k2/vGamba
공식 코드vGamba: Attentive State Space Bottleneck for efficient Long-range Dependencies in Visual Recognition
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/yuqinie98/patchtst
공식 코드Revisiting PCA for time series reduction in temporal dimension
https://github.com/yutao-0718/gl-fno
공식 코드Global-local Fourier Neural Operator for Accelerating Coronal Magnetic Field Model
https://github.com/yutingng/gen-AC
공식 코드https://github.com/yutongwangbit/voom
공식 코드VOOM: Robust Visual Object Odometry and Mapping using Hierarchical Landmarks
https://github.com/yuxixie/coral
공식 코드COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement
https://github.com/yxsu/LtR.jl
공식 코드https://github.com/yygroup/autocfd
공식 코드Fine-tuning a Large Language Model for Automating Computational Fluid Dynamics Simulations
https://github.com/yynil/rwkvtts
공식 코드https://github.com/z-fabian/flash-diffusion
공식 코드Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion Models
https://github.com/zavareh1/Wav-KAN
공식 코드https://github.com/zax130/modetv2
공식 코드https://github.com/zclzcl0223/TimeLinear
공식 코드How Much Can Time-related Features Enhance Time Series Forecasting?
https://github.com/zechengli19/uni-sign
공식 코드Uni-Sign: Toward Unified Sign Language Understanding at Scale
https://github.com/zefang-liu/TPP-LLM
공식 코드TPP-LLM: Modeling Temporal Point Processes by Efficiently Fine-Tuning Large Language Models
https://github.com/zhangce01/DPE-CLIP
공식 코드Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models
https://github.com/zhangce01/dualadapter
공식 코드Enhancing Vision-Language Few-Shot Adaptation with Negative Learning
https://github.com/zhangce01/simnl
공식 코드Enhancing Vision-Language Few-Shot Adaptation with Negative Learning
https://github.com/zhanglbthu/prtgaussian
공식 코드PRTGaussian: Efficient Relighting Using 3D Gaussians with Precomputed Radiance Transfer
https://github.com/zhangye-zoe/fcis
공식 코드https://github.com/zhao-xingyuan/must
공식 코드https://github.com/zhaodongsun/contrast-phys
공식 코드https://github.com/zhaojw1998/accomontage-3
공식 코드Structured Multi-Track Accompaniment Arrangement via Style Prior Modelling
https://github.com/zhaozb08/MixPL-SPO
공식 코드Learning Mixtures of Plackett-Luce Models from Structured Partial Orders
https://github.com/zhenweian/dynamic_moe
공식 코드Harder Tasks Need More Experts: Dynamic Routing in MoE Models
https://github.com/zhichao-aws/opensearch-sparse-model-tuning-sample
공식 코드Exploring $\ell_0$ Sparsification for Inference-free Sparse Retrievers
https://github.com/zhidilin/gpssmproj
공식 코드https://github.com/zhihan1996/dnabert_2
공식 코드DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome
https://github.com/zhiningliu1998/selfelicit
공식 코드SelfElicit: Your Language Model Secretly Knows Where is the Relevant Evidence
https://github.com/zhishe-wang/swinfuse
공식 코드SwinFuse: A Residual Swin Transformer Fusion Network for Infrared and Visible Images
https://github.com/zhiyongwangwzy/conlinucb
공식 코드Efficient Explorative Key-term Selection Strategies for Conversational Contextual Bandits
https://github.com/zhiyuanli218/segret
공식 코드SegRet: An Efficient Design for Semantic Segmentation with Retentive Network
https://github.com/zhu1116/args-diff
공식 코드https://github.com/zhuogege1943/dgc
공식 코드Dynamic Group Convolution for Accelerating Convolutional Neural Networks
https://github.com/zhuoinoulu/svnet
공식 코드SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud Representation
https://github.com/zihan-liu-00/atkse
공식 코드Are Gradients on Graph Structure Reliable in Gray-box Attacks?
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.