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 4776–4800 of 4891 papers

TitleStatusHype
Density-Softmax: Efficient Test-time Model for Uncertainty Estimation and Robustness under Distribution ShiftsCode0
Exploring Molecule Generation Using Latent Space Graph DiffusionCode0
Exploring Kolmogorov-Arnold Networks for Interpretable Time Series ClassificationCode0
Real-Time Tea Leaf Disease Detection Using Deep Learning-Based ModelsCode0
Sketch-and-Lift: Scalable Subsampled Semidefinite Program for K-means ClusteringCode0
Real-Time Weather Image Classification with SVMCode0
Commonsense Knowledge Base Completion with Structural and Semantic ContextCode0
MVNet: Hyperspectral Remote Sensing Image Classification Based on Hybrid Mamba-Transformer Vision Backbone ArchitectureCode0
DensE: An Enhanced Non-commutative Representation for Knowledge Graph Embedding with Adaptive Semantic HierarchyCode0
Native Fortran Implementation of TensorFlow-Trained Deep and Bayesian Neural NetworksCode0
Native Language Identification with Big Bird EmbeddingsCode0
Explain to Fix: A Framework to Interpret and Correct DNN Object Detector PredictionsCode0
ReasoningV: Efficient Verilog Code Generation with Adaptive Hybrid Reasoning ModelCode0
A Multiscale Environment for Learning by DiffusionCode0
A Transformer Framework for Data Fusion and Multi-Task Learning in Smart CitiesCode0
Demystifying the Effect of Receptive Field Size in U-Net Models for Medical Image SegmentationCode0
Randomized Exploration for Non-Stationary Stochastic Linear BanditsCode0
Delayed Memory Unit: Modelling Temporal Dependency Through Delay GateCode0
EvoPruneDeepTL: An Evolutionary Pruning Model for Transfer Learning based Deep Neural NetworksCode0
A Multi-Document Coverage Reward for RELAXed Multi-Document SummarizationCode0
SkipSNN: Efficiently Classifying Spike Trains with Event-attentionCode0
Evaluating the Efficacy of Instance Incremental vs. Batch Learning in Delayed Label Environments: An Empirical Study on Tabular Data Streaming for Fraud DetectionCode0
Reconstruction of three-dimensional porous media using generative adversarial neural networksCode0
Recovering BanditsCode0
ADAGIO: Fast Data-aware Near-Isometric Linear EmbeddingsCode0
Show:102550
← PrevPage 192 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified