Aviad Dahan

I am a PhD student in Electrical Engineering at Tel Aviv University, working under the supervision of Prof. Raja Giryes and Prof. Lior Wolf.

My research focuses on deep learning for computer vision, with particular interests in:

• Image Editing - Generative models for image manipulation
• Video Editing - Temporal consistency in video generation
• Medical Image Segmentation - Adapting foundation models for medical imaging
• Speech & Audio - Audio-visual generation and personalization

Education

• PhD in Electrical Engineering, Tel Aviv University (2024 - Present)
• M.Sc. in Electrical Engineering (with honors), Tel Aviv University (2022 - 2024)
• M.Eng. in System Engineering, Technion (2017 - 2019)
• B.Sc. in Electrical Engineering, Technion (2009 - 2013)

Publications

ID-LoRA: Identity-Driven Audio-Video Personalization with In-Context LoRA Aviad Dahan*, Moran Yanuka*, Noa Kraicer, Lior Wolf, Raja Giryes arXiv preprint, 2026

Project arXiv Code

LiteAttention: A Temporal Sparse Attention for Diffusion Transformers Dor Shmilovich, Tony Wu, Aviad Dahan, Yuval Domb arXiv preprint, 2025

Project arXiv Code

Video Polyp Segmentation using Implicit Networks Aviad Dahan, Tal Shaharabany, Raja Giryes, Lior Wolf Medical Imaging with Deep Learning (MIDL), 2024

Paper Code

AutoSAM: Adapting SAM to Medical Images by Overloading the Prompt Encoder Tal Shaharabany, Aviad Dahan, Raja Giryes, Lior Wolf British Machine Vision Conference (BMVC), 2023

arXiv Code