SteerViT is a framework that allows you to guide a pretrained vision model's focus and features using natural language
Jona Ruthardt
JonaRuthardt
AI & ML interests
Vision-Language, Multimodality, Vision, LLMs
Recent Activity
authored a paper 2 days ago
Open Vision Banana: A Fully Open Recipe for Generative Visual Perception authored a paper 2 days ago
Zero-Shot Mission-Level Evaluation for Aerial MLLM Agents upvoted a paper 2 days ago
Open Vision Banana: A Fully Open Recipe for Generative Visual PerceptionOrganizations
datasets 5
JonaRuthardt/SteerViT
Viewer • Updated • 2.29M • 276 • 2
JonaRuthardt/CORE
Viewer • Updated • 2.39k • 142
JonaRuthardt/SteerViT-PhraseCutDataset
Viewer • Updated • 330k • 431
JonaRuthardt/SteerViT-gRefCOCO
Viewer • Updated • 222k • 45
JonaRuthardt/SteerViT-SAM3-bboxprompt
Viewer • Updated • 2.24M • 28