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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1641–1650 of 4891 papers

TitleStatusHype
Converting Transformers into DGNNs FormCode0
Controlling Participation in Federated Learning with FeedbackCode0
End-to-End Deep Learning for Structural Brain Imaging: A Unified FrameworkCode0
Sequential Monte Carlo Squared for online inference in stochastic epidemic modelsCode0
Energy-Based Reranking: Improving Neural Machine Translation Using Energy-Based ModelsCode0
Continuous vs. Discrete Optimization of Deep Neural NetworksCode0
FairViT: Fair Vision Transformer via Adaptive MaskingCode0
Continuous Normalizing Flows for Uncertainty-Aware Human Pose Estimation—0
Continual Learning via Online Leverage Score Sampling—0
Architectural Fusion Through Contextual Partitioning in Large Language Models: A Novel Approach to Parameterized Knowledge Integration—0
Show:102550
← PrevPage 165 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified