I worked on making sense of images,
Now I am working on images making sense.
About Me
I am Tuna ([tu-nah]), a PhD student in Computer Science at Virginia Tech, affiliated with the Computer Science Department and The Sanghani Center for Artificial Intelligence and Data Analytics. My research focuses on image and video diffusion models, driven by a passion for advancing generative AI techniques. Since 2023, I have been working with Prof. Pinar Yanardag and previously, I was supervised by Prof. Lale Akarun during my M.Sc. at Bogazici University.
Before coming to the US for my Ph.D., I worked as a Machine Learning Engineer at Lyrebird Studio and Vispera. You can find more about my work accomplishments on my resumé page and download my resume from here.
Current Interests:
- Image and Video Diffusion Models
- Representation Learning
- Few-Shot Learning
Personal News
- Feb 2025 - My new preprint ConceptAttention is available at arXiv.
- Nov 2024 - My new preprint MotionFlow is available at arXiv.
- Nov 2024 - My new preprint MotionShop is available at arXiv.
- Oct 2024 - I have been awarded a research grant from Deloitte to work on mechanistic interpretability for large language models.
- Oct 2024 - I completed my internship at Adobe, where I worked on Video Diffusion Transformers models, focusing on instruction-based video editing.
- Jun 2024 - I started my research internship at Adobe in the Summer 2024.
- Jun 2024 - My paper, Conditional Information Gain Trellis has been accepted to Pattern Recognition Letters.
- May 2024 - My paper, CONFORM, has been accepted to CVPR 2024.
- Mar 2024 - My new preprint CLoRA is available at arXiv.
- Jan 2024 - Open-sourced the code for my paper: CONFORM.
- Dec 2023 - My new preprint CONFORM is available at arXiv.
- Aug 2023 - I started my PhD in Computer Science with Pinar Yanardag Delul.