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 921–930 of 4891 papers

TitleStatusHype
Linear Transformers as VAR Models: Aligning Autoregressive Attention Mechanisms with Autoregressive ForecastingCode0
Global Universal Scaling and Ultra-Small Parameterization in Machine Learning Interatomic Potentials with Super-Linearity—0
Long-term simulation of physical and mechanical behaviors using curriculum-transfer-learning based physics-informed neural networks—0
Mixed Integer Linear Programming for Active Contact Selection in Deep Brain Stimulation—0
Provably Efficient RLHF Pipeline: A Unified View from Contextual Bandits—0
Hierarchical Document Parsing via Large Margin Feature Matching and HeuristicsCode0
Latent Convergence Modulation in Large Language Models: A Novel Approach to Iterative Contextual Realignment—0
Calibrating LLMs with Information-Theoretic Evidential Deep LearningCode1
Bayesian Optimization by Kernel Regression and Density-based Exploration—0
Smell of Source: Learning-Based Odor Source Localization with Molecular Communication—0
Show:102550
← PrevPage 93 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified