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 131–140 of 4891 papers

TitleStatusHype
DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference AccelerationCode1
Unlocking Chemical Insights: Superior Molecular Representations from Intermediate Encoder LayersCode0
Vid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry and Physics for Mesh-free Simulation—0
SDS-Net: Shallow-Deep Synergism-detection Network for infrared small target detectionCode1
DynamicMind: A Tri-Mode Thinking System for Large Language Models—0
U-NetMN and SegNetMN: Modified U-Net and SegNet models for bimodal SAR image segmentation—0
Efficient Robust Conformal Prediction via Lipschitz-Bounded NetworksCode0
TALL -- A Trainable Architecture for Enhancing LLM Performance in Low-Resource Languages—0
A Survey on Vietnamese Document Analysis and Recognition: Challenges and Future Directions—0
DeePoly: A High-Order Accuracy Scientific Machine Learning Framework for Function Approximation and Solving PDEsCode1
Show:102550
← PrevPage 14 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified