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 331–340 of 4891 papers

TitleStatusHype
A High-Dimensional Feature Selection Algorithm Based on Multiobjective Differential Evolution—0
Generative Discovery of Partial Differential Equations by Learning from Math Handbooks—0
Assessing Tenstorrent's RISC-V MatMul Acceleration Capabilities—0
Auto Tensor Singular Value Thresholding: A Non-Iterative and Rank-Free Framework for Tensor Denoising—0
UltraGauss: Ultrafast Gaussian Reconstruction of 3D Ultrasound Volumes—0
Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model—0
USPR: Learning a Unified Solver for Profiled RoutingCode0
RL-DAUNCE: Reinforcement Learning-Driven Data Assimilation with Uncertainty-Aware Constrained Ensembles—0
Approximation-free Control for Signal Temporal Logic Specifications using Spatiotemporal TubesCode0
Continuous Thought MachinesCode5
Show:102550
← PrevPage 34 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified