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

Showing 27262750 of 4891 papers

TitleStatusHype
Fast, Expressive SE(n) Equivariant Networks through Weight-Sharing in Position-Orientation SpaceCode1
An Integer Clustering Approach for Modeling Large-Scale EV Fleets with Guaranteed Performance0
DeepHGCN: Toward Deeper Hyperbolic Graph Convolutional NetworksCode0
The Inhibitor: ReLU and Addition-Based Attention for Efficient Transformers0
VENOM: A Vectorized N:M Format for Unleashing the Power of Sparse Tensor CoresCode1
DeepZero: Scaling up Zeroth-Order Optimization for Deep Model TrainingCode1
Randomized Dimension Reduction with Statistical Guarantees0
Robustifying State-space Models for Long Sequences via Approximate Diagonalization0
Variance-Aware Regret Bounds for Stochastic Contextual Dueling BanditsCode0
CoDBench: A Critical Evaluation of Data-driven Models for Continuous Dynamical Systems0
Iterative Semi-Supervised Learning for Abdominal Organs and Tumor SegmentationCode0
Efficient MPC for Emergency Evasive Maneuvers, Part I: Hybridization of the Nonlinear Problem0
Efficient MPC for Emergency Evasive Maneuvers, Part II: Comparative Assessment for Hybrid Control0
Adaptive-Solver Framework for Dynamic Strategy Selection in Large Language Model ReasoningCode0
Quantum-Based Feature Selection for Multi-classification Problem in Complex Systems with Edge Computing0
DeformUX-Net: Exploring a 3D Foundation Backbone for Medical Image Segmentation with Depthwise Deformable ConvolutionCode1
PlaceNav: Topological Navigation through Place Recognition0
Deep Representation Learning for Prediction of Temporal Event Sets in the Continuous Time DomainCode0
Efficient Anatomical Labeling of Pulmonary Tree Structures via Deep Point-Graph Representation-based Implicit FieldsCode0
Benchmarking and In-depth Performance Study of Large Language Models on Habana Gaudi Processors0
ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem SolvingCode3
Training and inference of large language models using 8-bit floating point0
Maximal Volume Matrix Cross Approximation for Image Compression and Least Squares Solution0
Multi-Modal Financial Time-Series Retrieval Through Latent Space Projections0
An analysis of the derivative-free loss method for solving PDEs0
Show:102550
← PrevPage 110 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05Unverified