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 3871–3880 of 4891 papers

TitleStatusHype
DiffuSolve: Diffusion-based Solver for Non-convex Trajectory Optimization—0
Combining Entropy and Matrix Nuclear Norm for Enhanced Evaluation of Language Models—0
Combining GCN Structural Learning with LLM Chemical Knowledge for or Enhanced Virtual Screening—0
Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers—0
Combining Recurrent, Convolutional, and Continuous-time Models with Linear State Space Layers—0
Combining Retrospective Approximation with Importance Sampling for Optimising Conditional Value at Risk—0
Combining the band-limited parameterization and Semi-Lagrangian Runge--Kutta integration for efficient PDE-constrained LDDMM—0
Communication-Efficient Decentralized Federated Learning via One-Bit Compressive Sensing—0
Communication-Efficient Distributed Statistical Inference—0
Communication Optimization for Decentralized Learning atop Bandwidth-limited Edge Networks—0
Show:102550
← PrevPage 388 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified