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 1231–1240 of 4891 papers

TitleStatusHype
Subspace Langevin Monte Carlo—0
A Survey on Inference Optimization Techniques for Mixture of Experts ModelsCode3
GaraMoSt: Parallel Multi-Granularity Motion and Structural Modeling for Efficient Multi-Frame Interpolation in DSA ImagesCode1
PASCO (PArallel Structured COarsening): an overlay to speed up graph clustering algorithmsCode0
Rare Event Detection in Imbalanced Multi-Class Datasets Using an Optimal MIP-Based Ensemble Weighting ApproachCode0
Threshold Neuron: A Brain-inspired Artificial Neuron for Efficient On-device Inference—0
Lightweight Safety Classification Using Pruned Language Models—0
E-CAR: Efficient Continuous Autoregressive Image Generation via Multistage Modeling—0
Compressed Sensing Based Residual Recovery Algorithms and Hardware for Modulo Sampling—0
SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training—0
Show:102550
← PrevPage 124 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified