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
FiT: Flexible Vision Transformer for Diffusion ModelCode3
Star Attention: Efficient LLM Inference over Long SequencesCode3
TimeMachine: A Time Series is Worth 4 Mambas for Long-term ForecastingCode3
Taming Diffusion Probabilistic Models for Character ControlCode3
vHeat: Building Vision Models upon Heat ConductionCode3
EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image SegmentationCode3
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
Residual Kolmogorov-Arnold Network for Enhanced Deep LearningCode3
DUFOMap: Efficient Dynamic Awareness MappingCode3
Nd-BiMamba2: A Unified Bidirectional Architecture for Multi-Dimensional Data ProcessingCode3
NeuralOM: Neural Ocean Model for Subseasonal-to-Seasonal SimulationCode3
Effects of charging and discharging capabilities on trade-offs between model accuracy and computational efficiency in pumped thermal electricity storageCode3
On the Efficiency of NLP-Inspired Methods for Tabular Deep LearningCode3
MAPE-PPI: Towards Effective and Efficient Protein-Protein Interaction Prediction via Microenvironment-Aware Protein EmbeddingCode3
Dataset Distillation with Neural Characteristic Function: A Minmax PerspectiveCode3
MetaDE: Evolving Differential Evolution by Differential EvolutionCode3
CoverM: Read alignment statistics for metagenomicsCode3
Consistency Models Made EasyCode3
MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation SystemCode3
HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation ModelCode3
Human-like Episodic Memory for Infinite Context LLMsCode3
Is Mamba Effective for Time Series Forecasting?Code3
BeautyMap: Binary-Encoded Adaptable Ground Matrix for Dynamic Points Removal in Global MapsCode3
A Foundation Model for the Earth SystemCode3
Show:102550
← PrevPage 3 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified