Alibay Osmanli

Computer Vision Group

School of Electronic Engineering and Computer Science

Queen Mary University of London

London, UK

I am a PhD researcher in the Computer Vision Group at Queen Mary University of London. My research focuses on computer vision, video understanding, and uncertainty estimation, with an emphasis on building models and evaluation methods that make visual reasoning more grounded and reliable.

My first paper, Grounding Video Reasoning in Physical Signals, introduces a benchmark for evaluating what, when, and where reasoning in physical video understanding across prompt families and perturbation settings.

I hold an MSc in Artificial Intelligence from Queen Mary University of London, where I worked on projects in machine learning, computer vision, and statistical modeling. Prior to that, I completed my BSc in Computer Engineering at Koç University (Istanbul, Turkey).

My broader interests lie at the intersection of artificial intelligence, computer vision, and reliable machine learning, particularly in settings where model decisions need to be interpretable and robust.

selected publications

Grounding Video Reasoning in Physical Signals

Alibay Osmanli, Zixu Cheng, and Shaogang Gong

arXiv preprint arXiv:2604.21873, 2026

Abs DOI arXiv Bib HTML PDF Code

We introduce a grounded benchmark for physical video understanding that evaluates what, when, and where reasoning across multiple video sources, physics domains, prompt families, and perturbation settings. The results show that spatial grounding remains the weakest part of current video question-answering systems and motivate physically grounded, prompt-aware diagnostics alongside aggregate accuracy.
@article{osmanli2026grounding, title = {Grounding Video Reasoning in Physical Signals}, author = {Osmanli, Alibay and Cheng, Zixu and Gong, Shaogang}, journal = {arXiv preprint arXiv:2604.21873}, year = {2026}, doi = {10.48550/arXiv.2604.21873}, }