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 1826–1850 of 4891 papers

TitleStatusHype
Deep Learning Improvements for Sparse Spatial Field Reconstruction—0
Leveraging Fine-Tuned Retrieval-Augmented Generation with Long-Context Support: For 3GPP StandardsCode1
MambaOcc: Visual State Space Model for BEV-based Occupancy Prediction with Local Adaptive ReorderingCode0
Efficient Detection of Toxic Prompts in Large Language Models—0
EE-MLLM: A Data-Efficient and Compute-Efficient Multimodal Large Language Model—0
Quantifying Behavioural Distance Between Mathematical Expressions—0
Approximation of the Proximal Operator of the _ Norm Using a Neural NetworkCode0
UKAN: Unbound Kolmogorov-Arnold Network Accompanied with Accelerated Library—0
HMoE: Heterogeneous Mixture of Experts for Language Modeling—0
A Lightweight Modular Framework for Low-Cost Open-Vocabulary Object Detection TrainingCode0
Ensemble Prediction via Covariate-dependent StackingCode0
Neural Horizon Model Predictive Control -- Increasing Computational Efficiency with Neural Networks—0
Implicit Grid Convolution for Multi-Scale Image Super-ResolutionCode1
ExpoMamba: Exploiting Frequency SSM Blocks for Efficient and Effective Image EnhancementCode1
MambaLoc: Efficient Camera Localisation via State Space Model—0
Efficient Budget Allocation for Large-Scale LLM-Enabled Virtual Screening—0
ELASTIC: Efficient Linear Attention for Sequential Interest Compression—0
CTR-KAN: KAN for Adaptive High-Order Feature Interaction ModelingCode0
Bee-yond the Plateau: Training QNNs with Swarm Algorithms—0
SpectralEarth: Training Hyperspectral Foundation Models at ScaleCode1
ColorMamba: Towards High-quality NIR-to-RGB Spectral Translation with MambaCode0
MobileMEF: Fast and Efficient Method for Multi-Exposure FusionCode1
FlashGS: Efficient 3D Gaussian Splatting for Large-scale and High-resolution RenderingCode3
H_2-optimal Model Reduction of Linear Quadratic Output Systems in Finite Frequency Range—0
MetaSeg: MetaFormer-based Global Contexts-aware Network for Efficient Semantic SegmentationCode1
Show:102550
← PrevPage 74 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified