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 3741–3750 of 4891 papers

TitleStatusHype
Efficient Tensor Contraction via Fast Count Sketch—0
DnS: Distill-and-Select for Efficient and Accurate Video Indexing and RetrievalCode1
Harmonic Power-Flow Study of Polyphase Grids with Converter-Interfaced Distributed Energy Resources, Part I: Modelling Framework and Algorithm—0
Connection Sensitivity Matters for Training-free DARTS: From Architecture-Level Scoring to Operation-Level Sensitivity Analysis—0
Boundary Graph Neural Networks for 3D SimulationsCode0
Algorithm Unrolling for Massive Access via Deep Neural Network with Theoretical Guarantee—0
Training or Architecture? How to Incorporate Invariance in Neural Networks—0
Precise phase retrieval for propagation-based images using discrete mathematics—0
Pre-Trained Models: Past, Present and Future—0
Quantum Speedup of Natural Gradient for Variational Bayes—0
Show:102550
← PrevPage 375 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified