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 4501–4525 of 4891 papers

TitleStatusHype
GARG-AML against Smurfing: A Scalable and Interpretable Graph-Based Framework for Anti-Money LaunderingCode0
SDLFormer: A Sparse and Dense Locality-enhanced Transformer for Accelerated MR Image ReconstructionCode0
AutoSeqRec: Autoencoder for Efficient Sequential RecommendationCode0
Striving for Faster and Better: A One-Layer Architecture with Auto Re-parameterization for Low-Light Image EnhancementCode0
Two-Stage Neural Contextual Bandits for Personalised News RecommendationCode0
CONCORD: Concept-Informed Diffusion for Dataset DistillationCode0
Tiny Models are the Computational Saver for Large ModelsCode0
Preference Neural NetworkCode0
GAMMA: A General Agent Motion Model for Autonomous DrivingCode0
Computing Valid p-value for Optimal Changepoint by Selective Inference using Dynamic ProgrammingCode0
DPC-Net: Deep Pose Correction for Visual LocalizationCode0
Functional Autoencoder for Smoothing and Representation LearningCode0
Fully Linear Graph Convolutional Networks for Semi-Supervised Learning and ClusteringCode0
Two-Step Question Retrieval for Open-Domain QACode0
MambaOcc: Visual State Space Model for BEV-based Occupancy Prediction with Local Adaptive ReorderingCode0
Two-way Node Popularity Model for Directed and Bipartite NetworksCode0
From Roots to Rewards: Dynamic Tree Reasoning with RLCode0
Computationally Efficient Learning of Statistical ManifoldsCode0
MANO: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution ShiftsCode0
FREEtree: A Tree-based Approach for High Dimensional Longitudinal Data With Correlated FeaturesCode0
SEDA: Self-Ensembling ViT with Defensive Distillation and Adversarial Training for robust Chest X-rays ClassificationCode0
Free Parametrization of L2-bounded State Space ModelsCode0
Pretraining Deformable Image Registration Networks with Random ImagesCode0
FrameRS: A Video Frame Compression Model Composed by Self supervised Video Frame Reconstructor and Key Frame SelectorCode0
M-ar-K-Fast Independent Component AnalysisCode0
Show:102550
← PrevPage 181 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified