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 511–520 of 4891 papers

TitleStatusHype
Focus on Local: Finding Reliable Discriminative Regions for Visual Place RecognitionCode1
Efficient Learning of Mesh-Based Physical Simulation with BSMS-GNNCode1
FocusTrack: A Self-Adaptive Local Sampling Algorithm for Efficient Anti-UAV TrackingCode1
Fully 11 Convolutional Network for Lightweight Image Super-ResolutionCode1
AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video RecognitionCode1
Flash Window Attention: speedup the attention computation for Swin TransformerCode1
Birdie: Advancing State Space Models with Reward-Driven Objectives and CurriculaCode1
FlexDiT: Dynamic Token Density Control for Diffusion TransformerCode1
Algorithmic Differentiation for Automated Modeling of Machine Learned Force FieldsCode1
Five A^+ Network: You Only Need 9K Parameters for Underwater Image EnhancementCode1
Show:102550
← PrevPage 52 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified