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 251–275 of 4891 papers

TitleStatusHype
Exploring _0 Sparsification for Inference-free Sparse RetrieversCode1
ExpoMamba: Exploiting Frequency SSM Blocks for Efficient and Effective Image EnhancementCode1
Fast ABC-Boost: A Unified Framework for Selecting the Base Class in Multi-Class ClassificationCode1
Fast Sequence Based Embedding with Diffusion GraphsCode1
Birdie: Advancing State Space Models with Reward-Driven Objectives and CurriculaCode1
Evidential Deep Learning: Enhancing Predictive Uncertainty Estimation for Earth System Science ApplicationsCode1
EViT: An Eagle Vision Transformer with Bi-Fovea Self-AttentionCode1
Efficient Learning of Mesh-Based Physical Simulation with BSMS-GNNCode1
Towards Reliable Medical Image Segmentation by utilizing Evidential Calibrated UncertaintyCode1
Exploiting Deblurring Networks for Radiance FieldsCode1
Learning From Alarms: A Robust Learning Approach for Accurate Photoplethysmography-Based Atrial Fibrillation Detection using Eight Million Samples Labeled with Imprecise Arrhythmia AlarmsCode1
Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic ModelsCode1
3D Gaussian Splatting against Moving Objects for High-Fidelity Street Scene ReconstructionCode1
CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMsCode1
Event-based Video Reconstruction via Potential-assisted Spiking Neural NetworkCode1
Exploiting Redundancy: Separable Group Convolutional Networks on Lie GroupsCode1
A new computationally efficient algorithm to solve Feature Selection for Functional Data Classification in high-dimensional spacesCode1
α-DPO: Adaptive Reward Margin is What Direct Preference Optimization NeedsCode1
Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PCCode1
Bidirectional Recurrence for Cardiac Motion Tracking with Gaussian Process Latent CodingCode1
Enhancing Medical Image Registration via Appearance Adjustment NetworksCode1
Equivariant Hypergraph Diffusion Neural OperatorsCode1
Energy-based physics-informed neural network for frictionless contact problems under large deformationCode1
End-to-end Prostate Cancer Detection in bpMRI via 3D CNNs: Effects of Attention Mechanisms, Clinical Priori and Decoupled False Positive ReductionCode1
BetterNet: An Efficient CNN Architecture with Residual Learning and Attention for Precision Polyp SegmentationCode1
Show:102550
← PrevPage 11 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified