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 1031–1040 of 4891 papers

TitleStatusHype
UDiTQC: U-Net-Style Diffusion Transformer for Quantum Circuit Synthesis—0
Context-Aware Neural Gradient Mapping for Fine-Grained Instruction Processing—0
Context-CrackNet: A Context-Aware Framework for Precise Segmentation of Tiny Cracks in Pavement images—0
UltraLightSqueezeNet: A Deep Learning Architecture for Malaria Classification with up to 54x fewer trainable parameters for resource constrained devices—0
Permutation-based multi-objective evolutionary feature selection for high-dimensional data—0
GreedyPixel: Fine-Grained Black-Box Adversarial Attack Via Greedy Algorithm—0
SpikePack: Enhanced Information Flow in Spiking Neural Networks with High Hardware Compatibility—0
LiDAR-Based Vehicle Detection and Tracking for Autonomous Racing—0
EFiGP: Eigen-Fourier Physics-Informed Gaussian Process for Inference of Dynamic Systems—0
Autonomous Structural Memory Manipulation for Large Language Models Using Hierarchical Embedding Augmentation—0
Show:102550
← PrevPage 104 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified