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 351–375 of 4891 papers

TitleStatusHype
Dynamic Multimodal FusionCode1
Efficient Two-Stream Network for Violence Detection Using Separable Convolutional LSTMCode1
Dynamic Implicit Image Function for Efficient Arbitrary-Scale Image RepresentationCode1
Embracing Collaboration Over Competition: Condensing Multiple Prompts for Visual In-Context LearningCode1
An adaptive augmented Lagrangian method for training physics and equality constrained artificial neural networksCode1
End-to-end Prostate Cancer Detection in bpMRI via 3D CNNs: Effects of Attention Mechanisms, Clinical Priori and Decoupled False Positive ReductionCode1
Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLMCode1
Efficient Aggregated Kernel Tests using Incomplete U-statisticsCode1
Dynamic Clustering and Cluster Contrastive Learning for Unsupervised Person Re-identificationCode1
Dynamic Cardiac MRI Reconstruction Using Combined Tensor Nuclear Norm and Casorati Matrix Nuclear Norm RegularizationsCode1
Estimating Koopman operators with sketching to provably learn large scale dynamical systemsCode1
Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic ModelsCode1
Rethinking Brain Tumor Segmentation from the Frequency Domain PerspectiveCode1
Evidential Deep Learning: Enhancing Predictive Uncertainty Estimation for Earth System Science ApplicationsCode1
Adaptive Focus for Efficient Video RecognitionCode1
Exploiting Deblurring Networks for Radiance FieldsCode1
DynamicDet: A Unified Dynamic Architecture for Object DetectionCode1
EXTENDING CONDITIONAL CONVOLUTION STRUCTURES FOR ENHANCING MULTITASKING CONTINUAL LEARNINGCode1
Adaptive Fourier Neural Operators: Efficient Token Mixers for TransformersCode1
FADRM: Fast and Accurate Data Residual Matching for Dataset DistillationCode1
Dual Prototype Evolving for Test-Time Generalization of Vision-Language ModelsCode1
Dynamic Group Convolution for Accelerating Convolutional Neural NetworksCode1
An Asynchronous Intensity Representation for Framed and Event Video SourcesCode1
Fast and Accurate Entity Recognition with Iterated Dilated ConvolutionsCode1
Efficient and Accurate Pneumonia Detection Using a Novel Multi-Scale Transformer ApproachCode1
Show:102550
← PrevPage 15 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified