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 3111–3120 of 4891 papers

TitleStatusHype
TurboViT: Generating Fast Vision Transformers via Generative Architecture Search—0
Turn Waste into Worth: Rectifying Top-k Router of MoE—0
Two-Bit Networks for Deep Learning on Resource-Constrained Embedded Devices—0
Two for the Price of One: Integrating Large Language Models to Learn Biophysical Interactions—0
TxSim:Modeling Training of Deep Neural Networks on Resistive Crossbar Systems—0
U2-Former: A Nested U-shaped Transformer for Image Restoration—0
UDiTQC: U-Net-Style Diffusion Transformer for Quantum Circuit Synthesis—0
UHD Image Dehazing via anDehazeFormer with Atmospheric-aware KV Cache—0
UKAN: Unbound Kolmogorov-Arnold Network Accompanied with Accelerated Library—0
Ultra Fast Speech Separation Model with Teacher Student Learning—0
Show:102550
← PrevPage 312 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified