Mert Çökelek, PhD student in Computer Science and Engineering

Can you briefly introduce yourself and share your background in AI research?

I am Mert Cokelek. I hold a Master’s in Computer Science and Engineering from Koç University. Before that, I completed my Bachelor’s in Computer Science and Engineering at Hacettepe University. I am continuing my PhD at Koç and working as an AI Research Engineer at Codeway. My research interests and experience lie in Computer Vision, Generative AI, and Virtual Reality. I am working on audio-visual models in 360.

What initially sparked your interest in the field of AI? Was there a particular moment or experience that inspired you to pursue this area of study?

My interest in AI traces back to my undergraduate years at Hacettepe University, where I began studying with my current advisors, Aykut Erdem and Erkut Erdem, in the “Dream” program. In my third year at university, I intended to keep my experience range as wide as possible. I’ve tried to see various perspectives of social, industrial, and academic life. I realized how happy I am doing AI research supervised by arguably the best academics in my country. Reading papers, thinking of novel ways of applying the ideas in those papers, and coding them still feel like I am doing my hobbies rather than working, which is the best part.

Could you tell us about your current research or thesis topic in AI? What motivated you to choose this specific area?

In my master’s thesis, I focused on the audio-visual perception of omnidirectional videos in VR. The problem was to model the human visual attention mechanism in VR environments to predict where people are most likely to look and fixate. I started working on this research direction back in my undergraduate studies. Honestly, I did not specifically choose this topic. I was a young kid motivated to dive into AI research and loved computer vision. This project was the only one available to me back then, and I am glad it was. Since 2020, we have done a lot in this literature. I started with 2D static images, moved to 360 images, and then videos. Finally, we completed the task with a novel 360 audio-visual pipeline, which is the current state-of-the-art. I want to make some changes in my PhD studies and start focusing on Generative AI. With my experience in the audio-visual domain, we can do some good research in multi-modal Generative AI.

Can you share a memorable experience or achievement from your AI research journey so far? What did you learn from that experience?

Very recently, our paper was accepted to BMVC 2023. It was my first in-person conference, and I went on the stage to present our work for the first time. I’ve been dreaming about that moment for a long time, but it still feels unreal. Meeting with people worldwide (including a research group working on the same topic as us) and attending various workshops and poster sessions was amazing. Apart from the academic perspective, I have seen a new country and its culture. The travel was for only a week, but I don’t think I will ever forget the moments I had.

How do you balance your academic workload, personal life, and the demands of your AI research? Do you have any strategies or tips that have helped you maintain a healthy work-life balance?

I have struggled to balance it for a long time. I am converging to a good spot by:

1. Having a good sleep (may sound like a cliche, but it’s a must)
2. Making work fun (e.g., finding a nice coffeeshop with cool music, discussing with friends)
3. Finding a de-focuser (e.g., workouts) that makes me isolated from work and other daily life problems. It may tire your body, but it’s worth to relax your head) 
4. Dreaming: Thinking about where I’ve been and where I want to be. Seeing my past progress encourages me, and visualizing my future motivates me to keep going.

How do you stay updated with the latest developments and research papers in the field of AI? Are there any particular resources or platforms you rely on?

I frequently track the updates in Google Scholar, X, and Medium blog posts. Following the leading researchers in your field would be good. A public channel (e.g., on Element, Discord, or Slack) is great if you miss something. Also, having weekly meetings with colleagues for paper discussions is helpful.

A book and movie that you recommend (they don’t have to be related to ai)

A Song of Ice and Fire: A masterpiece that combines fantasy and intrigues. You can’t just put it on the shelf after reading it, it has a special material that requires you to think about for hours.

The Matrix (1, 2, 3): I don’t think I should describe it :). It has inspired great discussions about AI and the nature of reality.