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 1951–1975 of 4891 papers

TitleStatusHype
Pilot Contamination Aware Transformer for Downlink Power Control in Cell-Free Massive MIMO Networks—0
Deep Plug-and-Play HIO Approach for Phase Retrieval—0
Controlling Participation in Federated Learning with FeedbackCode0
Robust Offline Reinforcement Learning with Linearly Structured f-Divergence Regularization—0
RS-vHeat: Heat Conduction Guided Efficient Remote Sensing Foundation Model—0
Randomized-Grid Search for Hyperparameter Tuning in Decision Tree Model to Improve Performance of Cardiovascular Disease Classification—0
Dynamic Logistic Ensembles with Recursive Probability and Automatic Subset Splitting for Enhanced Binary ClassificationCode0
On the Effectiveness of Incremental Training of Large Language ModelsCode0
A Runtime-Adaptive Transformer Neural Network Accelerator on FPGAsCode0
Residual Attention Single-Head Vision Transformer Network for Rolling Bearing Fault Diagnosis in Noisy Environments—0
SuperMat: Physically Consistent PBR Material Estimation at Interactive Rates—0
Perceptually Optimized Super Resolution—0
Spatio-temporal Causal Learning for Streamflow Forecasting—0
SCASeg: Strip Cross-Attention for Efficient Semantic Segmentation—0
Enhancing Character-Level Understanding in LLMs through Token Internal Structure LearningCode0
Efficient Deployment of Transformer Models in Analog In-Memory Computing HardwareCode0
GMFlow: Global Motion-Guided Recurrent Flow for 6D Object Pose Estimation—0
UVCG: Leveraging Temporal Consistency for Universal Video Protection—0
Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image Compression—0
Jaya R Package -- A Parameter-Free Solution for Advanced Single and Multi-Objective Optimization—0
Flow Annealed Importance Sampling Bootstrap meets Differentiable Particle PhysicsCode0
Dynamic Causal Models of Time-Varying Connectivity—0
DP-CDA: An Algorithm for Enhanced Privacy Preservation in Dataset Synthesis Through Randomized Mixing—0
Debiasing Classifiers by Amplifying Bias with Latent Diffusion and Large Language Models—0
LTCF-Net: A Transformer-Enhanced Dual-Channel Fourier Framework for Low-Light Image Restoration—0
Show:102550
← PrevPage 79 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified