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 3201–3210 of 4891 papers

TitleStatusHype
Enhanced prediction accuracy with uncertainty quantification in monitoring CO2 sequestration using convolutional neural networks—0
STLGRU: Spatio-Temporal Lightweight Graph GRU for Traffic Flow PredictionCode0
HADAS: Hardware-Aware Dynamic Neural Architecture Search for Edge Performance ScalingCode1
Graph Convolutional Neural Networks with Diverse Negative Samples via Decomposed Determinant Point ProcessesCode0
SoftCTC -- Semi-Supervised Learning for Text Recognition using Soft Pseudo-LabelsCode1
Learning to Optimize in Model Predictive Control—0
Regularized ERM on random subspaces—0
Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping—0
Robust and Fast Measure of Information via Low-rank RepresentationCode0
Safe and Efficient Reinforcement Learning Using Disturbance-Observer-Based Control Barrier Functions—0
Show:102550
← PrevPage 321 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified