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 3801–3825 of 4891 papers

TitleStatusHype
The 5th AI City ChallengeCode1
Partitioning sparse deep neural networks for scalable training and inference—0
Consistent and symmetry preserving data-driven interface reconstruction for the level-set method—0
Landmark-Aware and Part-based Ensemble Transfer Learning Network for Facial Expression Recognition from Static images—0
A novel time-frequency Transformer based on self-attention mechanism and its application in fault diagnosis of rolling bearings—0
Consistent Accelerated Inference via Confident Adaptive TransformersCode1
Machine learning-assisted surrogate construction for full-core fuel performance analysis—0
Improving Hyper-Relational Knowledge Graph CompletionCode0
Uncertainty Surrogates for Deep Learning—0
The Butterfly Effect in Primary Visual Cortex—0
Towards Efficient Graph Convolutional Networks for Point Cloud HandlingCode0
ENOS: Energy-Aware Network Operator Search for Hybrid Digital and Compute-in-Memory DNN Accelerators—0
Deformable Capsules for Object Detection—0
Pyramidal Reservoir Graph Neural NetworkCode1
CondenseNet V2: Sparse Feature Reactivation for Deep NetworksCode1
Generalized Nesterov's Acceleration-incorporated Non-negative and Adaptive Latent Factor Analysis—0
A New Parallel Adaptive Clustering and its Application to Streaming Data—0
An Energy-efficient Aerial Backhaul System with Reconfigurable Intelligent Surface—0
CCSNet: a deep learning modeling suite for CO_2 storage—0
"Forget" the Forget Gate: Estimating Anomalies in Videos using Self-contained Long Short-Term Memory Networks—0
SDAN: Squared Deformable Alignment Network for Learning Misaligned Optical ZoomCode0
Fast DCTTS: Efficient Deep Convolutional Text-to-Speech—0
Linear systems with neural network nonlinearities: Improved stability analysis via acausal Zames-Falb multipliersCode0
Training Sparse Neural Network by Constraining Synaptic Weight on Unit Lp Sphere—0
Checkerboard Context Model for Efficient Learned Image CompressionCode1
Show:102550
← PrevPage 153 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified