Layer-Aware Video Composition via Split-then-Merge Ozgur Kara, Yujia Chen, Ming-Hsuan Yang, James M. Rehg, Wen-Sheng Chu, Du Tran In Submission, 2026 Split-then-Merge (StM) is a new video composition framework that improves control and handles data scarcity by splitting unlabeled videos into foreground and background layers, and then self-composing them. Project Webpage / Paper Media: UIUC News / Official Google Channels in Instagram / Twitter
	DiffVax: Optimization-Free Image Immunization Against Diffusion-Based Editing Tarik Can Ozden*, Ozgur Kara*, Oguzhan Akcin, Kerem Zaman, Shashank Srivastava, Sandeep P. Chinchali, James M. Rehg ICLR 2026 (The Fourteenth International Conference on Learning Representations) DiffVax is an optimization-free image immunization framework that effectively protects against diffusion-based editing, generalizes to unseen content, is robust against counter-attacks, and shows promise in safeguarding video content. Project Webpage / Paper / Code (coming soon)
	DiffEye: Diffusion-Based Continuous Eye-Tracking Data Generation Conditioned on Natural Images Ozgur Kara*, Harris Nisar*, James M. Rehg NeurIPS 2025 (The Thirty-ninth Annual Conference on Neural Information Processing Systems) We propose DiffEye, a diffusion-based generative model for creating realistic, raw eye-tracking trajectories conditioned on natural images, which outperforms existing methods on scanpath generation tasks. Project Webpage / Paper / Code
	ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models Ozgur Kara, Krishna Kumar Singh, Feng Liu, Duygu Ceylan, James M. Rehg, Tobias Hinz CVPR 2025 (IEEE/CVF Conference on Computer Vision and Pattern Recognition) ShotAdapter enables text-to-multi-shot video generation with minimal fine-tuning, providing users control over shot number, duration, and content through shot-specific text prompts, along with a multi-shot video dataset collection pipeline. Project Webpage / Paper
	RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models Ozgur Kara, Bariscan Kurtkaya, Hidir Yesiltepe, James M. Rehg, Pinar Yanardag CVPR 2024, Highlight (IEEE/CVF Conference on Computer Vision and Pattern Recognition) RAVE is a zero-shot, lightweight, and fast framework for text-guided video editing, supporting videos of any length utilizing text-to-image pretrained diffusion models. Project Webpage / Paper / Code / HuggingFace Demo / Video Media: Voxel51 Talk / NewGenAI / creativaier / JanRT / Future Thinker @Benji
	Towards Social AI: A Survey on Understanding Social Interactions Sangmin Lee, Minzhi Li, Bolin Lai, Wenqi Jia, Fiona Ryan, Xu Cao, Ozgur Kara, Bikram Boote, Weiyan Shi, Diyi Yang, James M. Rehg In Submission, 2025 This is the first survey to provide a comprehensive overview of machine learning studies on social understanding, encompassing both verbal and non-verbal approaches. Paper
	Transfer Learning for Cross-dataset Isolated Sign Language Recognition in Under-Resourced Datasets Alp Kindiroglu*, Ozgur Kara*, Ogulcan Ozdemir, Lale Akarun FG 2024 (IEEE International Conference on Automatic Face and Gesture Recognition) This study provides a publicly available cross-dataset transfer learning benchmark from two existing public Turkish SLR datasets. Paper / Code
	Leveraging Object Priors for Point Tracking Bikram Boote, Anh Thai, Wenqi Jia, Ozgur Kara, Stefan Stojanov, James M. Rehg, Sangmin Lee ECCV 2024 ILR Workshop, Oral (Instance-Level Recognition Workshop at European Conference on Computer Vision) We propose a novel objectness regularization approach that guides points to be aware of object priors by forcing them to stay inside the the boundaries of object instances. Paper / Code
	Domain-Incremental Continual Learning for Mitigating Bias in Facial Expression and Action Unit Recognition Nikhil Churamani, Ozgur Kara, Hatice Gunes IEEE TAC 2022 (IEEE Transactions on Affective Computing) we propose the novel use of Continual Learning (CL), in particular, using Domain-Incremental Learning (Domain-IL) settings, as a potent bias mitigation method to enhance the fairness of Facial Expression Recognition (FER) systems. Paper / Code
	Molecular Index Modulation using Convolutional Neural Networks Ozgur Kara, Gokberk Yaylali, Ali Emre Pusane, Tuna Tugcu Nano Communication Networks 2022 We propose a novel convolutional neural network-based architecture for a uniquely designed molecular multiple-input-single-output topology, aimed at mitigating the detrimental effects of molecular interference in nano molecular communication. Paper / Code
	ISNAS-DIP: Image-Specific Neural Architecture Search for Deep Image Prior Metin Ersin Arican*, Ozgur Kara*, Gustav Bredell, Ender Konukoglu CVPR 2022 (IEEE/CVF Conference on Computer Vision and Pattern Recognition) ISNAS-DIP is an image-specific Neural Architecture Search (NAS) strategy designed for the Deep Image Prior (DIP) framework, offering significantly reduced training requirements compared to conventional NAS methods. Paper / Code / Video
	Towards Fair Affective Robotics: Continual Learning for Mitigating Bias in Facial Expression and Action Unit Recognition Ozgur Kara, Nikhil Churamani, Hatice Gunes LEAP-HRI 2021 (Workshop on Lifelong Learning and Personalization in Long-Term Human-Robot Interaction) We propose the novel use of Continual Learning (CL) as a potent bias mitigation method to enhance the fairness of Facial Expression Recognition (FER) systems. Paper / Code
	Neuroweaver: a platform for designing intelligent closed-loop neuromodulation systems Parisa Sarikhani, Hao-Lun Hsu, Ozgur Kara, Joon Kyung Kim, Hadi Esmaeilzadeh, Babak Mahmoudi Brain Stimulation: Basic, Translational, and Clinical Research in Neuromodulation, Elsevier, 2021 Our interactive platform enables the design of neuromodulation pipelines through a visually intuitive and user-friendly interface. (Google Summer of Code 2021 project) Paper / Code

Professional Service

• Workshop Organizer: AI for Visual Content Generation Editing and Understanding (CVEU) [Webpage]
  • CVPR 2026 (Lead Organizer)
  • SIGGRAPH 2025 (Co-organizer)
  • CVPR 2025 (Lead Organizer)
• Outstanding Reviewer:
  • ICCV 2025 (Top 2%)
  • CVPR 2025 (Top 5%)
  • ECCV 2024 (Top 10%)
• Program Committee / Reviewer:
  • CVPR 2024, 2025, 2026
  • ICCV 2025
  • ECCV 2024
  • NeurIPS 2023, 2025
  • ICML 2024
  • ICLR 2024, 2025
  • AAAI 2025
  • IEEE Transactions on Affective Computing
  • ACM Transactions on Graphics

Invited Talks

• Voxel51 Computer Vision Meetup, Visual AI for Video Use Cases 2026
• Google Computer Vision Reading Group, ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models 2025
• UIUC Computer Vision Group Lunch, RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models 2024
• Voxel51 Computer Vision Meetup, GenAI for Video: Diffusion-Based Editing and Generation, [Recording] 2024
• More Than 101, Review of Basic Probability and Introduction to Diffusion Models 2023

Teaching

• CS444 Deep Learning for Computer Vision, UIUC 2026 Spring
• ECE2026 Introduction to Signal Processing, Georgia Institute of Technology 2022 Fall

Mentorship

• Furkan Horoz (METU, BS CS) Fall 2025-Present
  Multi-agentic slide generation (In preparation).
• Zeqian (Richard) Long (UIUC, BS CS) Summer 2025-Present
  Adversarial attacks on video diffusion models (In submission).
• Aditya Ved, Nalin Kundu (UIUC, BS CS) Spring 2025
  Developed deepfake prevention mobile app (URSA, Awarded 1st Place in Research Symposium).
• Miguel Aenlle (UIUC, BS CS) 2024-Present
  Google Summer of Code (GSoC) 2025 Contributor. Real-time video editing mobile app (URSA).
• Tarik Can Ozden (Bogazici University BS CS → UIUC MS CS) Spring 2024-Present
  Immunization model against deepfake attacks (DiffVax, ICLR 2026).
• Peter Guan (UIUC, BS CS) Fall 2024
  Real-time video editing mobile app (URSA).
• Sarper Yurtseven (YTU BS Maths. → Polimi MS Comp. Maths.) Summer 2024
  Google Summer of Code (GSoC) 2024 Contributor. Universal controller diffusion models.
• Ioannis Valasakis (King's College London, PhD) Summer 2023
  Google Summer of Code (GSoC) 2023 Contributor.
• Mehul Sinha (Manipal University, B.Tech → MS CS @ USC) Summer 2022
  Google Summer of Code (GSoC) 2022 Contributor.

Scholarships

• UIUC CS PhD Fellowship Addendum 2024-2026
• Georgia Tech ECE Departmental Fellowship 2022-2024
• Georgia Tech Otto F. and Jenny H. Krauss Fellowship 2022-2023
• Summer@EPFL Fully Funded Summer Internship Program 2022
• 2205 TUBITAK Undergraduate Scholarship Holder 2022
• Outstanding Success Scholarship Holder from Turkish Educational Foundation (TEV). 2019-2022
• 2247-C TUBITAK Research Internship Scholarship 2021-2022

Awards & Achievements

• Served as a mentor in the Google Summer of Code program in 2022, 2023, 2024, and 2025. 2025
• Recognized as an Outstanding Reviewer at ECCV, ranked among the top 10% of all reviewers. 2024
• Attended the 2023 International Computer Vision Summer School (ICVSS), ranked among the top 25% of 614 applicants (approximately 154 individuals), [Project] 2023
• Participated in the CIMPA Research School on Graph Structure and Complex Network Analysis. 2023
• Attended the highly competitive Summer@EPFL program, with a 2% acceptance rate. 2022
• Placed among the top 50 teams worldwide in the Google Developer’s Solution Challenge, selected from over 5,000 teams, [Project] 2022
• Placed 3^rd in the Yildiz Bootcamp and was directly invited to the Yildiz Technopark Pre-Incubation Program. 2022
• Successfully completed Google Summer of Code with the project "Graphical User Interface for OpenAI Gym," selected among 1,205 students from 6,991 applicants (17% acceptance rate), [Project] 2021
• Placed 3^rd out of 172 projects (top 1.7%) in the TUBITAK Undergraduate Research Project Competition. 2021
• Ranked among the top 10 teams regionwide in the Google Solution Challenge with the project titled "Torch in Darkness." 2020
• Placed 1^st out of 100 projects (top 1%) in the TUBITAK Undergraduate Research Project Competition for the project "Joint Depth Estimation and Object Detection Software," [Project] 2020
• Placed 3^rd out of 15 projects (top 20%) in the IEEE METU Pixery Hackathon with the project "Mobile Application for Blind People," [Project] 2020
• Finalist among 81 teams in the Turkish Airlines Travel Datathon. 2019
• Ranked 180^th out of 2 million (top 0.009%) in the Turkish National University Entrance Exam. 2018
• Received the Republic Honour Award at Kadikoy Anadolu High School, awarded to one student out of 340 annually. 2018
• Placed 3^rd nationwide in the TUBITAK High School Research Project Competition for the project "Drone for Landmine Detection Using GPS," [Project] 2018
• Placed 1^st regionwide in the TUBITAK High School Research Project Competition for the project "An Autonomous Hexapod for Helping Search Teams After Earthquake," [Project] 2017
• Accepted into the CS Bridge program, a two-week programming course led by Stanford TAs. 2016