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 201–225 of 4891 papers

TitleStatusHype
RWKV-UNet: Improving UNet with Long-Range Cooperation for Effective Medical Image SegmentationCode2
Fast Adversarial Attacks on Language Models In One GPU MinuteCode2
DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species GenomeCode2
SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement LearningCode2
FastBlend: a Powerful Model-Free Toolkit Making Video Stylization EasierCode2
DistPred: A Distribution-Free Probabilistic Inference Method for Regression and ForecastingCode2
A Survey on Diffusion Models for Anomaly DetectionCode2
BiFormer: Vision Transformer with Bi-Level Routing AttentionCode2
Advances in 4D Generation: A SurveyCode2
Emulating Self-attention with Convolution for Efficient Image Super-ResolutionCode2
Enhancing Autonomous Driving Systems with On-Board Deployed Large Language ModelsCode2
SuperFlow++: Enhanced Spatiotemporal Consistency for Cross-Modal Data PretrainingCode2
Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical SystemsCode2
Fast Calibrated Explanations: Efficient and Uncertainty-Aware Explanations for Machine Learning ModelsCode2
Geometry Aware Operator Transformer as an Efficient and Accurate Neural Surrogate for PDEs on Arbitrary DomainsCode2
Learning local equivariant representations for quantum operatorsCode2
REINFORCE++: A Simple and Efficient Approach for Aligning Large Language ModelsCode2
Efficient Real-time Path Planning with Self-evolving Particle Swarm Optimization in Dynamic ScenariosCode1
Efficient RAW Image Deblurring with Adaptive Frequency ModulationCode1
Efficient Two-Stream Network for Violence Detection Using Separable Convolutional LSTMCode1
BetterNet: An Efficient CNN Architecture with Residual Learning and Attention for Precision Polyp SegmentationCode1
Efficient Neural Network Robustness Certification with General Activation FunctionsCode1
EfficientPose: Scalable single-person pose estimationCode1
Electronic-structure properties from atom-centered predictions of the electron densityCode1
Benchmark Dataset for Precipitation Forecasting by Post-Processing the Numerical Weather PredictionCode1
Show:102550
← PrevPage 9 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified