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 2701–2725 of 4891 papers

TitleStatusHype
Attention is Naturally Sparse with Gaussian Distributed Input—0
CATP: Cross-Attention Token Pruning for Accuracy Preserved Multimodal Model Inference—0
Improved model-free bounds for multi-asset options using option-implied information and deep learning—0
Learning-based model augmentation with LFRsCode0
MugenNet: A Novel Combined Convolution Neural Network and Transformer Network with its Application for Colonic Polyp Image Segmentation—0
A Novel Feature Map Enhancement Technique Integrating Residual CNN and Transformer for Alzheimer Diseases Diagnosis—0
Computation and Communication Efficient Lightweighting Vertical Federated Learning for Smart Building IoT—0
SelfReplay: Adapting Self-Supervised Sensory Models via Adaptive Meta-Task Replay—0
P-Hologen: An End-to-End Generative Framework for Phase-Only HologramsCode0
Multi-scale Unified Network for Image Classification—0
Reachability Analysis Using Constrained Polynomial Logical ZonotopesCode0
Transformers-based architectures for stroke segmentation: A review—0
Retentive Decision Transformer with Adaptive Masking for Reinforcement Learning based Recommendation Systems—0
Hawk: Accurate and Fast Privacy-Preserving Machine Learning Using Secure Lookup Table Computation—0
Tiny Models are the Computational Saver for Large ModelsCode0
CCDSReFormer: Traffic Flow Prediction with a Criss-Crossed Dual-Stream Enhanced Rectified Transformer Model—0
Benchmarking Video Frame Interpolation—0
Understanding the Functional Roles of Modelling Components in Spiking Neural Networks—0
Stochastic parameter reduced-order model based on hybrid machine learning approaches—0
A Unified Module for Accelerating STABLE-DIFFUSION: LCM-LORA—0
Crypto Inverse-Power Options and Fractional Stochastic Volatility—0
Fast and Unified Path Gradient Estimators for Normalizing Flows—0
Medical Image Data Provenance for Medical Cyber-Physical System—0
Spectral Motion Alignment for Video Motion Transfer using Diffusion Models—0
Non-Convex Robust Hypothesis Testing using Sinkhorn Uncertainty Sets—0
Show:102550
← PrevPage 109 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified