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 726–750 of 4891 papers

TitleStatusHype
PI-Controlled Variable Time-Step Power System Simulation Using an Adaptive Order Differential Transformation Method—0
MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation SystemCode3
TPDiff: Temporal Pyramid Video Diffusion Model—0
MindGYM: Enhancing Vision-Language Models via Synthetic Self-Challenging Questions—0
Federated Smoothing ADMM for Localization—0
Automatic Operator-level Parallelism Planning for Distributed Deep Learning -- A Mixed-Integer Programming Approach—0
Reliable Solution to Dynamic Optimization Problems using Integrated Residual Regularized Direct Collocation—0
STEAD: Spatio-Temporal Efficient Anomaly Detection for Time and Compute Sensitive ApplicationsCode1
A Triple-Inertial Accelerated Alternating Optimization Method for Deep Learning TrainingCode0
Gradient-guided Attention Map Editing: Towards Efficient Contextual Hallucination Mitigation—0
Rel-UNet: Reliable Tumor Segmentation via Uncertainty Quantification in nnU-Net—0
Revisiting Frank-Wolfe for Structured Nonconvex Optimization—0
Efficient and Accurate Estimation of Lipschitz Constants for Hybrid Quantum-Classical Decision Models—0
ELECTRA: A Cartesian Network for 3D Charge Density Prediction with Floating Orbitals—0
LatexBlend: Scaling Multi-concept Customized Generation with Latent Textual Blending—0
EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer—0
MC-GRU:a Multi-Channel GRU network for generalized nonlinear structural response prediction across structures—0
Federated Multimodal Learning with Dual Adapters and Selective Pruning for Communication and Computational EfficiencyCode0
Just Functioning as a Hook for Two-Stage Referring Multi-Object Tracking—0
ActiveInitSplat: How Active Image Selection Helps Gaussian Splatting—0
SEAP: Training-free Sparse Expert Activation Pruning Unlock the Brainpower of Large Language ModelsCode1
Reinforcement Learning Based Symbolic Regression for Load Modeling—0
Adaptive Extensive Cancellation Algorithm and Harmonic Enhanced Heart Rate Estimation based on MMWave Radar—0
Skelite: Compact Neural Networks for Efficient Iterative SkeletonizationCode0
A Unified View of Optimal Kernel Hypothesis Testing—0
Show:102550
← PrevPage 30 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified