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 4876–4891 of 4891 papers

TitleStatusHype
Topology-based Representative Datasets to Reduce Neural Network Training ResourcesCode0
Novel OCT mosaicking pipeline with Feature- and Pixel-based registrationCode0
Novel optimized crow search algorithm for feature selectionCode0
Unifying Dimensions: A Linear Adaptive Approach to Lightweight Image Super-ResolutionCode0
Training Domain Specific Models for Energy-Efficient Object DetectionCode0
End-to-End Deep Learning for Structural Brain Imaging: A Unified FrameworkCode0
ZeroShape: Regression-based Zero-shot Shape ReconstructionCode0
Repulsive Latent Score Distillation for Solving Inverse ProblemsCode0
Deep Learning Evidence for Global Optimality of Gerver's SofaCode0
Training-Free Exponential Context Extension via Cascading KV CacheCode0
Sparse Covariance Neural NetworksCode0
Electric Field Models of Transcranial Magnetic Stimulation Coils with Arbitrary Geometries: Reconstruction from Incomplete Magnetic Field MeasurementsCode0
A Targeted Accuracy Diagnostic for Variational ApproximationsCode0
Boosting MLPs with a Coarsening Strategy for Long-Term Time Series ForecastingCode0
Efficient Transformer Encoders for Mask2Former-style modelsCode0
A Survey on Prompt TuningCode0
Show:102550
← PrevPage 196 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified