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 611–620 of 4891 papers

TitleStatusHype
Q-MambaIR: Accurate Quantized Mamba for Efficient Image Restoration—0
Generalizable Implicit Neural Representations via Parameterized Latent Dynamics for Baroclinic Ocean Forecasting—0
Purifying Approximate Differential Privacy with Randomized Post-processing—0
Improving (α, f)-Byzantine Resilience in Federated Learning via layerwise aggregation and cosine distanceCode0
LandMarkSystem Technical ReportCode2
Stochastic Engrams for Efficient Continual Learning with Binarized Neural Networks—0
Retinal Fundus Multi-Disease Image Classification using Hybrid CNN-Transformer-Ensemble ArchitecturesCode0
Dual-Task Learning for Dead Tree Detection and Segmentation with Hybrid Self-Attention U-Nets in Aerial ImageryCode0
InternVL-X: Advancing and Accelerating InternVL Series with Efficient Visual Token CompressionCode1
VADMamba: Exploring State Space Models for Fast Video Anomaly DetectionCode1
Show:102550
← PrevPage 62 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified