đź‘‹ About Me
I am a Ph.D. candidate in Computer Science at the Center of Excellence (COE) in Generative AI (GenAI), advised by Prof. Peter Wonka.
My research focuses on controllable generative AI – in particular diffusion models, identity representation learning, vision–language alignment, and fine‑grained image editing.
🔥 News
- 2026.04 “NearID” preprint released on arXiv — identity representation learning with near-identity distractors (w/ Snap Research).
- 2026.01 Serving as reviewer for CVPR 2026, ECCV 2026, and SIGGRAPH 2026.
- 2025.12 Research collaboration with Snap Research on identity-aware visual representations.
- 2025.11 Let’s meet at ICCV 2025 in Honolulu, Hawaii.
- 2025.09 “Mind the Glitch” accepted to NeurIPS 2025 (Spotlight).
- 2025.07 Serving as reviewer for SIGGRAPH Asia 2025.
- 2025.06 “EditCLIP” accepted to ICCV 2025.
- 2025.04 “PartEdit” accepted to Siggraph 2025 - see you in Vancouver!
- 2024.11 Serving as reviewer for CVPR 2025.
- 2023.11 Serving as reviewer for CVPR 2024.
đź“ť Publications
PartEdit: Fine‑Grained Image Editing using Pre‑Trained Diffusion Models
ACM SIGGRAPH, 2025
Aleksandar Cvejic, Abdelrahman Eldesokey, Peter Wonka
[PDF] [Code] [Project page]
NearID: Identity Representation Learning via Near-identity Distractors
arXiv, 2026 (Under Review)
Aleksandar Cvejic, Rameen Abdal, Abdelrahman Eldesokey, Bernard Ghanem, Peter Wonka
KAUST Ă— Snap Research
[PDF] [Code] [Project page] [Video]
EditCLIP: Representation Learning for Image Editing
IEEE ICCV, 2025
Qian Wang, Aleksandar Cvejic, Abdelrahman Eldesokey, Peter Wonka
[PDF] [Code] [Project page]
Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven Generation
NeurIPS, 2025 (Spotlight)
Abdelrahman Eldesokey, Aleksandar Cvejic, Bernard Ghanem, Peter Wonka
[PDF] [Code] [Project page]
đź“– Education
- 2022 – 2027 Ph.D., Computer Science — King Abdullah University of Science & Technology (KAUST), GPA 3.89/4.00.
- 2019 – 2021 M.Sc., Computer & Control Engineering — Univ. of Novi Sad, GPA 10/10.
- 2015 – 2019 B.Sc., Computer & Control Engineering — Univ. of Novi Sad, GPA 9.74/10.
🏆 Honors and Awards
- 2022 NVIDIA Certification — Model Parallelism: Building and Deploying Large Neural Networks
- 2021 3rd place, STC AIoT Hackathon, Saudi Arabia
- 2018 – 2020 Ministry of Youth & Sports scholarship – top 500 students nationally (Serbia)
- 2015 – 2019 Ministry of Education scholarship – top 10% students nationally (Serbia)
- 2015 – 2019 University diploma for academic excellence each undergrad year – top 10%
đź“š Academic Service
- Conference reviewer: CVPR 2024–2026, ECCV 2026, SIGGRAPH 2026, SIGGRAPH Asia 2025.
đź’Ľ Experience
- 2025.12 – 2026.03 Research Collaborator (Remote) — Snap Research, Snap Inc. Identity-aware visual representations: problem discovery, dataset & benchmark pipeline, model training.
- 2025.09 – 2025.12 Teaching Assistant, CS294Y Neural Network Design and Training — KAUST (Instructor: Prof. Peter Wonka)
- 2024.09 – 2024.12 Teaching Assistant, CS323 Deep Learning for Visual Computing — KAUST (Instructor: Prof. Peter Wonka)
- 2021.03 – 2021.10 Computer Vision Research Intern — KAUST
- 2020.03 – 2021.02 Teaching Assistant — Univ. of Novi Sad (Algorithms & DS, XML/Web Services, etc.)
đź› Technical Skills
Programming: Python, C++, Java, C
ML Libraries: PyTorch (DDP), HuggingFace (Diffusers/Transformers/Accelerate/PEFT), Weights & Biases, NumPy, OpenCV
Models: Vision Transformers, Diffusion Models, GANs, VAEs, CLIP, Vision-Language Models
Efficiency: FP16/Mixed-Precision Training, LoRA/PEFT, DeepSpeed, Model Parallelism, Multi-GPU Distributed Training
Infrastructure: Git, Linux, Slurm (HPC), CUDA, Large-scale data curation