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 4161–4170 of 4891 papers

TitleStatusHype
Spike-FlowNet: Event-based Optical Flow Estimation with Energy-Efficient Hybrid Neural NetworksCode1
A High-Performance Object Proposals based on Horizontal High Frequency Signal—0
SDVTracker: Real-Time Multi-Sensor Association and Tracking for Self-Driving Vehicles—0
Texture Superpixel Clustering from Patch-based Nearest Neighbor Matching—0
Robust, Occlusion-aware Pose Estimation for Objects Grasped by Adaptive HandsCode1
Energy-efficient and Robust Cumulative Training with Net2Net Transformation—0
Learning Directly from Grammar Compressed TextCode0
A Neuromorphic Proto-Object Based Dynamic Visual Saliency Model with an FPGA Implementation—0
Solving ODE with Universal Flows: Approximation Theory for Flow-Based Models—0
TxSim:Modeling Training of Deep Neural Networks on Resistive Crossbar Systems—0
Show:102550
← PrevPage 417 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified