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 2001–2010 of 4891 papers

TitleStatusHype
Benchmark Evaluation of Image Fusion algorithms for Smartphone Camera Capture—0
ModeConv: A Novel Convolution for Distinguishing Anomalous and Normal Structural BehaviorCode0
An Interpretable and Efficient Sleep Staging Algorithm: DetectsleepNetCode0
Unconditional Stability Analysis of N-Port Networks Based on Structured Singular Value Computation—0
Octo-planner: On-device Language Model for Planner-Action Agents—0
A Closer Look into Mixture-of-Experts in Large Language ModelsCode2
SC-MoE: Switch Conformer Mixture of Experts for Unified Streaming and Non-streaming Code-Switching ASR—0
Graph Neural Networks for Emulation of Finite-Element Ice Dynamics in Greenland and Antarctic Ice Sheets—0
T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on EdgeCode4
High Fidelity Text-to-Speech Via Discrete Tokens Using Token Transducer and Group Masked Language Model—0
Show:102550
← PrevPage 201 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified