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 2801–2850 of 4891 papers

TitleStatusHype
Artificial to Spiking Neural Networks Conversion for Scientific Machine Learning—0
Robust GAN inversion—0
Robust Networked Federated Learning for Localization—0
Communication-Efficient Decentralized Federated Learning via One-Bit Compressive Sensing—0
Reduced Simulations for High-Energy Physics, a Middle Ground for Data-Driven Physics Research—0
Stochastic Graph Bandit Learning with Side-Observations—0
NSF: Neural Surface Fields for Human Modeling from Monocular Depth—0
BayOTIDE: Bayesian Online Multivariate Time series Imputation with functional decompositionCode1
A Generalization of Continuous Relaxation in Structured Pruning—0
EdgeMoE: Fast On-Device Inference of MoE-based Large Language Models—0
Optimal Transport-inspired Deep Learning Framework for Slow-Decaying Kolmogorov n-width Problems: Exploiting Sinkhorn Loss and Wasserstein Kernel—0
SGMM: Stochastic Approximation to Generalized Method of Moments—0
Advancing Distributed AC Optimal Power Flow for Integrated Transmission-Distribution Systems—0
QKSAN: A Quantum Kernel Self-Attention Network—0
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language ModelsCode2
Reinforcement learning informed evolutionary search for autonomous systems testing—0
Benchmarking Data Efficiency and Computational Efficiency of Temporal Action Localization Models—0
Probabilistic load forecasting with Reservoir Computing—0
VNI-Net: Vector Neurons-based Rotation-Invariant Descriptor for LiDAR Place Recognition—0
Missing Data Imputation Based on Dynamically Adaptable Structural Equation Modeling with Self-AttentionCode0
Tumor-Centered Patching for Enhanced Medical Image Segmentation—0
Accel-GCN: High-Performance GPU Accelerator Design for Graph Convolution NetworksCode1
TurboViT: Generating Fast Vision Transformers via Generative Architecture Search—0
Split Learning for Distributed Collaborative Training of Deep Learning Models in Health Informatics—0
Domain Reduction Strategy for Non Line of Sight ImagingCode0
Efficient Real-time Path Planning with Self-evolving Particle Swarm Optimization in Dynamic ScenariosCode1
Learning Computational Efficient Bots with Costly Features—0
Artificial-Spiking Hierarchical Networks for Vision-Language Representation Learning—0
Online Transition-Based Feature Generation for Anomaly Detection in Concurrent Data Streams—0
Spike-and-slab shrinkage priors for structurally sparse Bayesian neural networks—0
Advancing Brain-Computer Interface System Performance in Hand Trajectory Estimation with NeuroKinect—0
Partially Observable Multi-Agent Reinforcement Learning with Information Sharing—0
SCQPTH: an efficient differentiable splitting method for convex quadratic programmingCode0
Exploring Winograd Convolution for Cost-effective Neural Network Fault Tolerance—0
FedPop: Federated Population-based Hyperparameter TuningCode1
Fast Uncertainty Quantification of Spent Nuclear Fuel with Neural Networks—0
Deep Neural Operator Driven Real Time Inference for Nuclear Systems to Enable Digital Twin Solutions—0
Shortcut-V2V: Compression Framework for Video-to-Video Translation based on Temporal Redundancy Reduction—0
SEDA: Self-Ensembling ViT with Defensive Distillation and Adversarial Training for robust Chest X-rays ClassificationCode0
Probabilistic MIMO U-Net: Efficient and Accurate Uncertainty Estimation for Pixel-wise RegressionCode1
ST-MLP: A Cascaded Spatio-Temporal Linear Framework with Channel-Independence Strategy for Traffic Forecasting—0
SEMI-CenterNet: A Machine Learning Facilitated Approach for Semiconductor Defect Inspection—0
AutoSeqRec: Autoencoder for Efficient Sequential RecommendationCode0
Localization of DOA trajectories -- Beyond the grid—0
A practical PINN framework for multi-scale problems with multi-magnitude loss termsCode1
EgoPoser: Robust Real-Time Egocentric Pose Estimation from Sparse and Intermittent Observations Everywhere—0
PETformer: Long-term Time Series Forecasting via Placeholder-enhanced TransformerCode1
JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion ModelsCode1
Objects do not disappear: Video object detection by single-frame object location anticipationCode1
A Hierarchical Destroy and Repair Approach for Solving Very Large-Scale Travelling Salesman Problem—0
Show:102550
← PrevPage 57 of 98Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified