SOTAVerified

Dynamic neural networks

Dynamic neural networks are adaptable models that can change their structure or parameters during training or inference based on input complexity or computational constraints. They offer benefits like improved efficiency, adaptability, and scalability compared to static architectures.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–37 of 37 papers

TitleStatusHype
Monadic Deep Learning—0
Neuroevolving Electronic Dynamical Networks—0
Nimble: Efficiently Compiling Dynamic Neural Networks for Model Inference—0
Analysis of Memory Organization for Dynamic Neural Networks—0
On-Demand Resource Management for 6G Wireless Networks Using Knowledge-Assisted Dynamic Neural Networks—0
Parametric Taylor series based latent dynamics identification neural networks—0
DyCL: Dynamic Neural Network Compilation Via Program Rewriting and Graph Optimization—0
Cavs: A Vertex-centric Programming Interface for Dynamic Neural Networks—0
A Survey on Dynamic Neural Networks for Natural Language Processing—0
The Dark Side of Dynamic Routing Neural Networks: Towards Efficiency Backdoor Injection—0
Dynamic Neural Networks: A Survey—0
Siamese Labels Auxiliary Learning—0
Show:102550
← PrevPage 2 of 2Next →

No leaderboard results yet.