Nikola Zubić
Scholar

Nikola Zubić

Google Scholar ID: 65OImV0AAAAJ
PhD student at University of Zurich and ETH Zurich
Machine LearningSequence ModelingDeep Learning ArchitecturesState Space Models
Citations & Impact
All-time
Citations
378
 
H-index
5
 
i10-index
5
 
Publications
10
 
Co-authors
3
list available
Resume (English only)
Academic Achievements
  • ['"GG-SSMs: Graph-Generating State Space Models" accepted at CVPR 2025 as a Highlight Paper', '"Perturbed State Space Feature Encoders for Optical Flow with Event Cameras" accepted at CVPRW 2025', '"Limits of Deep Learning: Sequence Modeling through the Lens of Complexity Theory" accepted at ICLR 2025', '"State Space Models for Event Cameras" accepted at CVPR 2024 as a Spotlight Paper', '"From Chaos Comes Order: Ordering Event Representations for Object Recognition and Detection" accepted at ICCV 2023', 'Major project "Humanity's Last Exam" featured in The New York Times Magazine (Sep 2025)', 'Work on limitations of deep learning covered by Quanta Magazine (Feb 2025)', 'Invited talks at Google Research, Google DeepMind, Cohere for AI, KTH, ETH AI Center, and others']
Background
  • Ph.D. student in Computer Science at the Institute of Neuroinformatics, University of Zurich and ETH Zurich
  • Member of the Robotics and Perception Group (RPG), supervised by Professor Davide Scaramuzza
  • Associated Researcher at the ETH AI Center
  • Primary research interests: sequence modeling and machine learning fundamentals
  • Theoretical work informs efficient neural network architectures, with applications in neuromorphic (event-based) vision systems
  • Also interested in dynamical systems, theoretical computer science, and applied mathematics, especially at their intersections with computational and mathematical challenges