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 421–430 of 4891 papers

TitleStatusHype
Heat flux for semi-local machine-learning potentialsCode1
Hexatagging: Projective Dependency Parsing as TaggingCode1
A practical PINN framework for multi-scale problems with multi-magnitude loss termsCode1
A machine learning-based viscoelastic-viscoplastic model for epoxy nanocomposites with moisture contentCode1
An Extensible Benchmark Suite for Learning to Simulate Physical SystemsCode1
ACEnet: Anatomical Context-Encoding Network for Neuroanatomy SegmentationCode1
DispFormer: Pretrained Transformer for Flexible Dispersion Curve Inversion from Global Synthesis to Regional ApplicationsCode1
Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation LearningCode1
M3-Jepa: Multimodal Alignment via Multi-directional MoE based on the JEPA frameworkCode1
DiRe-JAX: A JAX based Dimensionality Reduction Algorithm for Large-scale DataCode1
Show:102550
← PrevPage 43 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified