Research Vision
I work on building next-generation multi-modal spatio-temporal reasoning systems that understand and act in complex environments. My goal is to enable transformative advances in the automation of man-made environments through intelligent multi-agent collaboration, in which mobile robots will work alongside humans supported by augmented assistance. More concretely, I am interested in developing systems for multi-modal reasoning over 3D maps, ego-centric and exocentric video feeds, digital twins, and operational documents, enabling continuous, online execution of environment-level goals.
3D Understanding
Compact, semantically rich 3D representations (e.g. Gaussian Splatting) and spatially grounded 3D vision-language models, learned with large-scale pre-training. I extend static 3D maps into digital twins that capture how a scene behaves and responds — not just how it looks.
Ego-centric Understanding
Spatially aware video models that process the continuous, ego-centric streams of AR glasses and robots — handling rapid motion, occlusion, and long-form memory, and supporting proactive, multi-turn dialogue rather than single-shot answers.
Mobile Robot Deployment
The applied end goal: mobile robots working alongside AR-equipped humans as continuously sensing, reasoning nodes — detecting deviations from plans, tracking progress, and moving from reactive control toward proactive orchestration in construction, logistics, and healthcare.
About Me
I am a Research Scientist at INSAIT, developing spatio-temporal reasoning systems that operate over multi-modal data, such as 3D maps, digital twins, and ego-centric video streams, to enable collaboration between robots and humans in complex environments. I completed my PhD at the Computer Vision Lab at ETH Zürich, advised by Prof. Luc Van Gool and Dr. Danda Pani Paudel, focusing on 3D reconstruction and visual understanding. Toward the end of my PhD I interned at Meta Reality Labs in Zürich, working on 4D reconstruction. Before that I was a full-time Teaching Assistant at the University of Belgrade, School of Electrical Engineering, where I also earned my MSc and BSc in signal processing and control theory. I am a long-time member of the organizing committee of PSIML, an annual AI summer school in Serbia.
Beyond Research
Mentoring
- – Supervised 10 students (mostly PhD) at INSAIT
- – Supervised 11 MSc/BSc students at ETH Zürich
- – Committee for 12 BSc theses at University of Belgrade
Teaching & Services
- – Research consultant for 2 AI startups
- – TA for Computer Vision course at ETH Zürich
- – TA for 7 courses at University of Belgrade
Community
- – Reviewer for CVPR, ECCV, ICCV, WACV, NeurIPS
- – Organizing annual AI summer school in Serbia
- – Pushing student research initiatives in Serbia