VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes
Paper • 2509.25339 • Published • 10
Soumya Shamarao Jahagirdar
soumyasj
·
AI & ML interests
Deep learning, Multi-modal learning, Computer Vision
Recent Activity
published a dataset 27 days ago
soumyasj/video-benchmarks-nonblind published a dataset 27 days ago
soumyasj/Meta-Video updated a dataset 29 days ago
soumyasj/video-benchmarks-nonblindOrganizations
upvoted a paper about 1 year ago
upvoted an article almost 2 years ago
Article
SmolVLM Grows Smaller – Introducing the 256M & 500M Models!
- +1
andito, mfarre, merve
• • 197