Scholar
Michael Dorkenwald
Google Scholar ID: KY5nvLUAAAAJ
PhD candidate at University of Amsterdam
Citations & Impact
Citations
311
H-index
9
i10-index
9
Publications
13
Co-authors
12
list available
Publications
Resume (English only)
Academic Achievements
- Sep 2025: One paper accepted to NeurIPS'25 on elastic pruning of ViTs
- Jul 2025: One paper accepted to BMVC'25 on introducing a new video-language benchmark
- Jun 2025: One paper accepted to TMLR on LLMs as implicit optimizers for VLMs
- Nov 2024: Gave a talk at the Surf research bootcamp on large scale video learning
- Sep 2024: Workshop organizer of 'Self Supervised Learning: What is Next?' at ECCV'24
- Jul 2024: One paper accepted to ECCV'24 on masked video modeling
- Jun 2024: Gave a talk at TNO in den Hague and at the National Institute for Informatics in Tokyo
- Apr 2024: Teaching Assistant for the Foundation Models (FoMo) course
- Feb 2024: One paper accepted to CVPR'24 on enabling object localisation abilities in VLMs
- Jul 2023: Attended the International Computer Vision Summer School in Sicily
Background
- Research interests include self-supervised video representation learning and multimodal vision–language models. Worked in Björn Ommer's research group at Heidelberg University, focusing on understanding human and object dynamics within generative frameworks, primarily for video synthesis.
Miscellany
- Part of the ELLIS PhD program in cooperation with Qualcomm.
