SOTAVerified

Computational Efficiency

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.

Papers

Showing 121130 of 4891 papers

TitleStatusHype
BiFormer: Vision Transformer with Bi-Level Routing AttentionCode2
MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision TasksCode2
Harder Tasks Need More Experts: Dynamic Routing in MoE ModelsCode2
L4acados: Learning-based models for acados, applied to Gaussian process-based predictive controlCode2
GotenNet: Rethinking Efficient 3D Equivariant Graph Neural NetworksCode2
Advances in 4D Generation: A SurveyCode2
BEBLID: Boosted efficient binary local image descriptorCode2
GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-MeshCode2
SparseLLM: Towards Global Pruning for Pre-trained Language ModelsCode2
FuXi Weather: A data-to-forecast machine learning system for global weatherCode2
Show:102550
← PrevPage 13 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05Unverified