Scholar
Yoad Tewel
Google Scholar ID: VSCSNhMAAAAJ
Tel Aviv University, NVIDIA
Citations & Impact
Citations
703
H-index
8
i10-index
8
Publications
16
Co-authors
7
list available
Publications
Resume (English only)
Academic Achievements
- 2025: Make It Count: Text-to-Image Generation with an Accurate Number of Objects (CVPR, 2025)
- 2024: Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models (ICLR, 2025)
- 2024: Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion Models (ICLR, 2025)
- 2024: Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models (NAACL, 2025)
- 2024: Training-Free Consistent Text-to-Image Generation (SIGGRAPH, 2024)
- 2023: Key-Locked Rank One Editing for Text-to-Image Personalization (SIGGRAPH, 2023)
- 2023: Zero-Shot Video Captioning with Evolving Pseudo-Tokens (BMVC, 2023)
- 2022: What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputs (NeurIPS, 2022)
- 2022: ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic (CVPR, 2022)
Research Experience
- Research Scientist at NVIDIA Research
Education
- PhD candidate in Computer Science at Tel-Aviv University; Supervisor: Prof. Lior Wolf
Background
- Research Interests: The intersection of computer vision, natural language processing, and machine learning; particularly exploring ways to leverage text-and-image foundation models for solving zero-shot tasks.
