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 51–75 of 4891 papers

TitleStatusHype
Apollo: Band-sequence Modeling for High-Quality Audio RestorationCode3
FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion ModelCode3
TensorNEAT: A GPU-accelerated Library for NeuroEvolution of Augmenting TopologiesCode3
vHeat: Building Vision Models upon Heat ConductionCode3
RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language ProcessingCode3
FlashVideo:Flowing Fidelity to Detail for Efficient High-Resolution Video GenerationCode3
TimeMachine: A Time Series is Worth 4 Mambas for Long-term ForecastingCode3
EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image SegmentationCode3
Residual Kolmogorov-Arnold Network for Enhanced Deep LearningCode3
DUFOMap: Efficient Dynamic Awareness MappingCode3
NeuralOM: Neural Ocean Model for Subseasonal-to-Seasonal SimulationCode3
On the Efficiency of NLP-Inspired Methods for Tabular Deep LearningCode3
Effects of charging and discharging capabilities on trade-offs between model accuracy and computational efficiency in pumped thermal electricity storageCode3
Nd-BiMamba2: A Unified Bidirectional Architecture for Multi-Dimensional Data ProcessingCode3
Dataset Distillation with Neural Characteristic Function: A Minmax PerspectiveCode3
MAPE-PPI: Towards Effective and Efficient Protein-Protein Interaction Prediction via Microenvironment-Aware Protein EmbeddingCode3
CoverM: Read alignment statistics for metagenomicsCode3
Consistency Models Made EasyCode3
MetaDE: Evolving Differential Evolution by Differential EvolutionCode3
HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation ModelCode3
Human-like Episodic Memory for Infinite Context LLMsCode3
Is Mamba Effective for Time Series Forecasting?Code3
A Foundation Model for the Earth SystemCode3
BeautyMap: Binary-Encoded Adaptable Ground Matrix for Dynamic Points Removal in Global MapsCode3
Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State SpacesCode3
Show:102550
← PrevPage 3 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified