riddhimanrana/fastvlm-0.5b-captions
Image-Text-to-Text
•
99.1M
•
Updated
•
286
•
3
Riddhiman Rana
riddhimanrana
AI & ML interests
I'm passionate about building real-time AI systems using MLX, FastViT-HD, YOLOv11n, and Fast-VLM, focusing on visual context streaming, semantic indexing, temporal vision context, and multimodal reasoning for robotics and assistive intelligence.
Organizations
None yet