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 571–580 of 4891 papers

TitleStatusHype
FedPaI: Achieving Extreme Sparsity in Federated Learning via Pruning at Initialization—0
Efficient n-body simulations using physics informed graph neural networks—0
Learning-Based Approximate Nonlinear Model Predictive Control Motion Cueing—0
Dynamic Graph Structure Estimation for Learning Multivariate Point Process using Spiking Neural Networks—0
DynMoLE: Boosting Mixture of LoRA Experts Fine-Tuning with a Hybrid Routing MechanismCode0
GLiNER-BioMed: A Suite of Efficient Models for Open Biomedical Named Entity RecognitionCode1
Data-driven Power Loss Identification through Physics-Based Thermal Model Backpropagation—0
On the Steady-State Distributionally Robust Kalman FilterCode0
CoMatch: Dynamic Covisibility-Aware Transformer for Bilateral Subpixel-Level Semi-Dense Image Matching—0
Optimization of Layer Skipping and Frequency Scaling for Convolutional Neural Networks under Latency Constraint—0
Show:102550
← PrevPage 58 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified