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

Showing 21012125 of 4891 papers

TitleStatusHype
Audio-based Anomaly Detection in Industrial Machines Using Deep One-Class Support Vector Data Description0
A Linearized Alternating Direction Multiplier Method for Federated Matrix Completion Problems0
Signal-SGN: A Spiking Graph Convolutional Network for Skeletal Action Recognition via Learning Temporal-Frequency Dynamics0
Heuristic Deep Reinforcement Learning for Phase Shift Optimization in RIS-assisted Secure Satellite Communication Systems with RSMA0
Hierarchical Lexical Manifold Projection in Large Language Models: A Novel Mechanism for Multi-Scale Semantic Representation0
High-dimensional Mixed Graphical Models0
Design Amortization for Bayesian Optimal Experimental Design0
DER Hosting capacity for distribution networks: definitions, attributes, use-cases and challenges0
DepthGAN: GAN-based Depth Generation of Indoor Scenes from Semantic Layouts0
Auction-Based Ex-Post-Payment Incentive Mechanism Design for Horizontal Federated Learning with Reputation and Contribution Measurement0
Deployment Pipeline from Rockpool to Xylo for Edge Computing0
Dependent Matérn Processes for Multivariate Time Series0
A Two-Stage Rotation-Based Super-Resolution Signature Estimation for Spatial Wideband Systems0
Dependency-Aware Semi-Structured Sparsity of GLU Variants in Large Language Models0
A Lightweight Feature Fusion Architecture For Resource-Constrained Crowd Counting0
IISE PG&E Energy Analytics Challenge 2025: Hourly-Binned Regression Models Beat Transformers in Load Forecasting0
Heat Kernel Goes Topological0
Density Approximation of Affine Jump Diffusions via Closed-Form Moment Matching0
Dense Prediction on Sequences with Time-Dilated Convolutions for Speech Recognition0
Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation0
AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers0
Denoising VAE as an Explainable Feature Reduction and Diagnostic Pipeline for Autism Based on Resting state fMRI0
A lightweight deep learning pipeline with DRDA-Net and MobileNet for breast cancer classification0
HDformer: A Higher Dimensional Transformer for Diabetes Detection Utilizing Long Range Vascular Signals0
Denoising Atmospheric Temperature Measurements Taken by the Mars Science Laboratory on the Martian Surface0
Show:102550
← PrevPage 85 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05Unverified