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 2121–2130 of 4891 papers

TitleStatusHype
Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear q^π-Realizability and Concentrability—0
CLAQ: Pushing the Limits of Low-Bit Post-Training Quantization for LLMsCode0
Spectral-Refiner: Accurate Fine-Tuning of Spatiotemporal Fourier Neural Operator for Turbulent FlowsCode2
Probabilistic Graph Rewiring via Virtual NodesCode0
Enhancing Fast Feed Forward Networks with Load Balancing and a Master Leaf NodeCode1
Efficient Ensembles Improve Training Data Attribution—0
Node Identifiers: Compact, Discrete Representations for Efficient Graph LearningCode1
AdaFisher: Adaptive Second Order Optimization via Fisher InformationCode2
vHeat: Building Vision Models upon Heat ConductionCode3
Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection—0
Show:102550
← PrevPage 213 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified