ivelin/SmolVLM-Instruct-vqav2
Updated
•
2
Ivelin Ivanov
ivelin
AI & ML interests
computer vision, vision-language models, multi modal transformers
Recent Activity
upvoted
an
article
25 days ago
SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data
liked
a Space
26 days ago
facebook/physical_reasoning_leaderboard
liked
a dataset
26 days ago
facebook/IntPhys2
Organizations
ivelin/donut-refexp-combined-v1-backup
Image-to-Text
•
Updated
•
18
ivelin/donut-refexp-combined-v1
Visual Question Answering
•
Updated
•
19
•
4
ivelin/donut-refexp-draft-precision2decs-backup
Image-to-Text
•
Updated
•
14
ivelin/donut-refexp-draft-precision2decs
Image-to-Text
•
Updated
•
44
ivelin/donut-refexp-draft-backup
Image-to-Text
•
Updated
•
13
ivelin/donut-refexp-draft
Image-to-Text
•
Updated
•
13
ivelin/donut-docvqa-demo
Image-to-Text
•
Updated
•
14
ivelin/donut-base-sroie
Image-to-Text
•
Updated
•
15
ivelin/sroie_donut_processor
Updated