Author

Roy Ganz

Observed name: Ganz, Roy

Institution: Amazon (United States)

Observed institutions: Amazon (United States), Technion – Israel Institute of Technology

OpenAlex ID: A5091239620

FuseCap: Leveraging Large Language Models for Enriched Fused Image Captions

2024 · Noam Rotstein, David Bensaïd, et al. · IEEE Winter Conference on Applications of Computer Vision · 82

PDF

Threat Model-Agnostic Adversarial Defense using Diffusion Models

2022 · Blau, Tsachi, Ganz, Roy, et al. · arXiv (Cornell University) · 37

PDF

Question Aware Vision Transformer for Multimodal Reasoning

2024 · Roy Ganz, Yair Kittenplon, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 36

PDF

CLIPTER: Looking at the Bigger Picture in Scene Text Recognition

2023 · Aviad Aberdam, David Bensaïd, et al. · IEEE/CVF International Conference on Computer Vision (ICCV) · 36

PDF

Paint by Inpaint: Learning to Add Image Objects by Removing Them First

2025 · Navve Wasserman, Noam Rotstein, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 34

PDF

Enhancing Diffusion-Based Image Synthesis with Robust Classifier Guidance

2022 · Kawar, Bahjat, Ganz, Roy, et al. · arXiv (Cornell University) · 33

PDF

Multimodal Semi-Supervised Learning for Text Recognition

2022 · Aberdam, Aviad, Ganz, Roy, et al. · arXiv (Cornell University) · 24

PDF

DocVLM: Make Your VLM an Efficient Reader

2025 · Mor Shpigel Nacson, Aviad Aberdam, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 23

PDF

GRAM: Global Reasoning for Multi-Page VQA

2024 · Tsachi Blau, Sharon Fogel, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 22

PDF

CLIPAG: Towards Generator-Free Text-to-Image Generation

2024 · Roy Ganz, Michael Elad · IEEE Winter Conference on Applications of Computer Vision · 16

PDF

Towards Models that Can See and Read

2023 · Roy Ganz, Oren Nuriel, et al. · IEEE/CVF International Conference on Computer Vision (ICCV) · 15

PDF

Do Perceptually Aligned Gradients Imply Adversarial Robustness?

2022 · Ganz, Roy, Kawar, Bahjat, et al. · arXiv (Cornell University) · 12

PDF

The Handoff Tax: Continuing Non-Native Trajectories in LLM Agents

2026 · Ganz, Roy, Nacson, Mor Shpigel, et al. · arXiv (Cornell University) · 9