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 3781–3790 of 4891 papers

TitleStatusHype
Counting Objects by Diffused Index: geometry-free and training-free approach—0
On Learning the Transformer KernelCode0
How Does Momentum Benefit Deep Neural Networks Architecture Design? A Few Case Studies—0
Action-Sufficient State Representation Learning for Control with Structural Constraints—0
RankingMatch: Delving into Semi-Supervised Learning with Consistency Regularization and Ranking Loss—0
Streaming on-device detection of device directed speech from voice and touch-based invocation—0
A study on the efficacy of model pre-training in developing neural text-to-speech system—0
Predictive Maintenance for General Aviation Using Convolutional Transformers—0
Fast and Interpretable Consensus Clustering via Minipatch Learning—0
Graph Coloring: Comparing Cluster Graphs to Factor Graphs—0
Show:102550
← PrevPage 379 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified