Janek Haberer
Scholar

Janek Haberer

Google Scholar ID: s-sj0tIAAAAJ
Graduate Researcher, Kiel University
Deep LearningVision TransformerEdge AIFederated Learning
Citations & Impact
All-time
Citations
54
 
H-index
4
 
i10-index
2
 
Publications
10
 
Co-authors
2
list available
Publications
2 items
Resume (English only)
Academic Achievements
  • Published 8 papers in peer-reviewed conferences and journals, including NeurIPS, CVPR Workshop, ICML Workshop, IEEE Access, MobiSys, CoNEXT Workshop, and EWSN Workshop. Featured publication: HydraViT: Stacking Heads for a Scalable ViT, a novel approach to scaling Vision Transformers (ViTs) by stacking multiple attention heads.
Research Experience
  • Has 4 years of experience, primarily focusing on the design of efficient deep learning methods.
Education
  • PhD student in Computer Science at Kiel University
Background
  • Research interests include the design of efficient deep learning methods in resource-constrained environments, spanning Edge AI, dynamic vision transformers, federated learning, and progressive image compression. Passionate about advancing machine learning technologies and collaborating on impactful projects.