Roy Ganz
13 papers · 2023–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
π Renaissance Researcher (5) π Interdisciplinary Bridge π Cross-Pollinator (11) π Conference Polyglot (6) πΊοΈ Taxonomy Completionist (24)
π
Interdisciplinary Bridge
π
Conference Polyglot
(6)
β‘
Prolific Year
(5)
ποΈ
Keyword Collector
(55)
π
Century Club
(12)
β
The Questioner
Conferences
CVPR (4)
WACV (3)
ICCV (2)
ACL (1)
ICLR (1)
ICML (1)
NIPS (1)
Top co-authors
Keywords
vision-language model
(5)
visual question answering
(3)
large language model
(3)
adversarial training
(3)
diffusion model
(2)
adversarial robustness
(2)
document understanding
(2)
perceptually aligned gradient
(2)
image captioning
(2)
image generation
(2)
knowledge distillation
(1)
image synthesis
(1)
image editing
(1)
test-time adaptation
(1)
vision transformer
(1)
energy-based model
(1)
robust classification
(1)
vision language model
(1)
image inpainting
(1)
text-to-image generation
(1)
Papers
DREAM: Deep Research Evaluation with Agentic Metrics
ACL 2026
Class-Conditioned Transformation for Enhanced Robust Image Classification
WACV 2025
Adversaries With Incentives: A Strategic Alternative to Adversarial Robustness
ICLR 2025
Paint by Inpaint: Learning to Add Image Objects by Removing Them First
CVPR 2025
DocVLM: Make Your VLM an Efficient Reader
CVPR 2025
Enhancing Consistency-Based Image Generation via Adversarialy-Trained Classification and Energy-Based Discrimination
NIPS 2024
Question Aware Vision Transformer for Multimodal Reasoning
CVPR 2024
GRAM: Global Reasoning for Multi-Page VQA
CVPR 2024
CLIPAG: Towards Generator-Free Text-to-Image Generation
WACV 2024
FuseCap: Leveraging Large Language Models for Enriched Fused Image Captions
WACV 2024
Towards Models that Can See and Read
ICCV 2023
Do Perceptually Aligned Gradients Imply Robustness?
ICML 2023
CLIPTER: Looking at the Bigger Picture in Scene Text Recognition
ICCV 2023