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 3951–3975 of 4891 papers

TitleStatusHype
Knowledge Distillation Circumvents Nonlinearity for Optical Convolutional Neural Networks—0
Nested-block self-attention for robust radiotherapy planning segmentation—0
CausalX: Causal Explanations and Block Multilinear Factor Analysis—0
Machine Learning-Based Optimal Mesh Generation in Computational Fluid Dynamics—0
Learning-based Robust Motion Planning with Guaranteed Stability: A Contraction Theory Approach—0
FAITH: Fast iterative half-plane focus of expansion estimation using event-based optic flowCode0
Multifidelity Ensemble Kalman Filtering Using Surrogate Models Defined by Physics-Informed Autoencoders—0
Ps and Qs: Quantization-aware pruning for efficient low latency neural network inferenceCode0
PrivateMail: Supervised Manifold Learning of Deep Features With Differential Privacy for Image Retrieval—0
Generative Archimedean CopulasCode0
Computationally Efficient Learning of Statistical ManifoldsCode0
Sequence-based deep learning antibody design for in silico antibody affinity maturation—0
BPLight-CNN: A Photonics-based Backpropagation Accelerator for Deep Learning—0
The Variational Bayesian Inference for Network Autoregression Models—0
RFI Mitigation for One-bit UWB Radar Systems—0
On the Post-hoc Explainability of Deep Echo State Networks for Time Series Forecasting, Image and Video Classification—0
On the Fundamental Limits of Exact Inference in Structured Prediction—0
Structured Dropout Variational Inference for Bayesian Neural Networks—0
Top-k eXtreme Contextual Bandits with Arm HierarchyCode0
Ada-SISE: Adaptive Semantic Input Sampling for Efficient Explanation of Convolutional Neural Networks—0
Learning a Product Relevance Model from Click-Through Data in E-Commerce—0
Tight lower bounds for Dynamic Time WarpingCode0
Cerebral cortical communication overshadows computational energy-use, but these combine to predict synapse number—0
Dynamic Neural Networks: A Survey—0
Fast and Accurate Amplitude Demodulation of Wideband SignalsCode0
Show:102550
← PrevPage 159 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified