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 476–500 of 4891 papers

TitleStatusHype
Real-Time Machine-Learning-Based Optimization Using Input Convex Long Short-Term Memory NetworkCode1
Quantized Distillation: Optimizing Driver Activity Recognition Models for Resource-Constrained EnvironmentsCode1
Improving Computational Efficiency for Powered Descent Guidance via Transformer-based Tight Constraint PredictionCode1
Solving High Frequency and Multi-Scale PDEs with Gaussian ProcessesCode1
Mixed Models with Multiple Instance LearningCode1
Optimization-Free Test-Time Adaptation for Cross-Person Activity RecognitionCode1
Lookup Table meets Local Laplacian Filter: Pyramid Reconstruction Network for Tone MappingCode1
Structured Multi-Track Accompaniment Arrangement via Style Prior ModellingCode1
Learning Continuous Network Emerging Dynamics from Scarce Observations via Data-Adaptive Stochastic ProcessesCode1
qPOTS: Efficient batch multiobjective Bayesian optimization via Pareto optimal Thompson samplingCode1
Merging Experts into One: Improving Computational Efficiency of Mixture of ExpertsCode1
QUIK: Towards End-to-End 4-Bit Inference on Generative Large Language ModelsCode1
EViT: An Eagle Vision Transformer with Bi-Fovea Self-AttentionCode1
On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic EnvironmentsCode1
Robust-GBDT: GBDT with Nonconvex Loss for Tabular Classification in the Presence of Label Noise and Class ImbalanceCode1
xVal: A Continuous Numerical Tokenization for Scientific Language ModelsCode1
Fast, Expressive SE(n) Equivariant Networks through Weight-Sharing in Position-Orientation SpaceCode1
DeepZero: Scaling up Zeroth-Order Optimization for Deep Model TrainingCode1
VENOM: A Vectorized N:M Format for Unleashing the Power of Sparse Tensor CoresCode1
DeformUX-Net: Exploring a 3D Foundation Backbone for Medical Image Segmentation with Depthwise Deformable ConvolutionCode1
Improving Facade Parsing with Vision Transformers and Line IntegrationCode1
AsymFormer: Asymmetrical Cross-Modal Representation Learning for Mobile Platform Real-Time RGB-D Semantic SegmentationCode1
Detach-ROCKET: Sequential feature selection for time series classification with random convolutional kernelsCode1
Evidential Deep Learning: Enhancing Predictive Uncertainty Estimation for Earth System Science ApplicationsCode1
Prompt Tuned Embedding Classification for Multi-Label Industry Sector AllocationCode1
Show:102550
← PrevPage 20 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified