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 2901–2925 of 4891 papers

TitleStatusHype
Joint Hierarchical Priors and Adaptive Spatial Resolution for Efficient Neural Image Compression—0
Contextualizing MLP-Mixers Spatiotemporally for Urban Data Forecast at ScaleCode1
Learning Difference Equations with Structured Grammatical Evolution for Postprandial Glycaemia Prediction—0
TopicFM+: Boosting Accuracy and Efficiency of Topic-Assisted Feature MatchingCode1
On efficient computation in active inferenceCode1
SUGAR: Spherical Ultrafast Graph Attention Framework for Cortical Surface Registration—0
Provably Efficient UCB-type Algorithms For Learning Predictive State Representations—0
DeepMediX: A Deep Learning-Driven Resource-Efficient Medical Diagnosis Across the SpectrumCode0
Weighted Anisotropic-Isotropic Total Variation for Poisson DenoisingCode0
Practical and Asymptotically Exact Conditional Sampling in Diffusion ModelsCode1
Large-scale Bayesian Structure Learning for Gaussian Graphical Models using Marginal Pseudo-likelihoodCode0
Scalable method for Bayesian experimental design without integrating over posterior distributionCode0
RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization BenchmarkCode4
Approximate Dynamic Programming for Constrained Piecewise Affine Systems with Stability and Safety Guarantees—0
What Truly Matters in Trajectory Prediction for Autonomous Driving?—0
DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species GenomeCode2
A denoised Mean Teacher for domain adaptive point cloud registrationCode0
Verification of Neural Network Control Systems using Symbolic Zonotopes and Polynotopes—0
Scaling MLPs: A Tale of Inductive BiasCode1
PathMLP: Smooth Path Towards High-order HomophilyCode0
Towards quantum enhanced adversarial robustness in machine learning—0
Highly accurate and efficient deep learning paradigm for full-atom protein loop modeling with KarmaLoopCode1
Neural Multigrid Memory For Computational Fluid DynamicsCode0
Dynamic Implicit Image Function for Efficient Arbitrary-Scale Image RepresentationCode1
InRank: Incremental Low-Rank LearningCode1
Show:102550
← PrevPage 117 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified