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 4081–4090 of 4891 papers

TitleStatusHype
End-to-End JPEG Decoding and Artifacts Suppression Using Heterogeneous Residual Convolutional Neural Network—0
Acoustic Source Localization with the Angular Spectrum Approach in Continuously Stratified Media—0
Statistical Mechanical Analysis of Neural Network PruningCode0
Similarity Search for Efficient Active Learning and Search of Rare Concepts—0
On the Iteration Complexity of Hypergradient ComputationCode1
Localization Uncertainty Estimation for Anchor-Free Object Detection—0
Differential Privacy of Hierarchical Census Data: An Optimization Approach—0
Variational Autoencoding of PDE Inverse Problems—0
DRACO: Co-Optimizing Hardware Utilization, and Performance of DNNs on Systolic Accelerator—0
Coordination of OLTC and Smart Inverters for Optimal Voltage Regulation of Unbalanced Distribution Networks—0
Show:102550
← PrevPage 409 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified