Vidore Leaderboard
🥇
188
Explore visual document retrieval model rankings
AI & ML interests
Retrieval, Computer Vision, LLM
Recent Activity
View all activity
manuÂ
Training Hyperparameter for Colqwen2.5-v0.2 reproduce
2
#10 opened about 2 months ago
by
Ryenhails
manuÂ
Add LICENSE file
#13 opened 12 days ago
by
jewittje
manuÂ
updated
a
Space
15 days ago
manuÂ
revert-tabs
#12 opened 15 days ago
by
manu
antoineedyÂ
updated
a
Space
19 days ago
QuentinJGÂ
updated
8
datasets
27 days ago
vidore/vidore_v3_finance_fr
Viewer
•
Updated
•
13.1k
•
952
vidore/vidore_v3_physics
Viewer
•
Updated
•
16.6k
•
1.21k
•
2
vidore/vidore_v3_energy
Viewer
•
Updated
•
10.7k
•
1.17k
•
1
vidore/vidore_v3_computer_science
Viewer
•
Updated
•
8.95k
•
1.51k
•
1
vidore/vidore_v3_pharmaceuticals
Viewer
•
Updated
•
14.9k
•
1.03k
vidore/vidore_v3_industrial
Viewer
•
Updated
•
16.7k
•
1.4k
•
1
vidore/vidore_v3_finance_en
Viewer
•
Updated
•
13.6k
•
1.53k
•
3
vidore/vidore_v3_hr
Viewer
•
Updated
•
13.4k
•
1.53k
•
4
antoineedyÂ
updated
a
dataset
about 1 month ago
antoineedyÂ
published
a
dataset
about 1 month ago
antoineedyÂ
updated
a
dataset
about 1 month ago
antonioloisonÂ
authored
a
paper
about 1 month ago
tonywu71Â
authored
a
paper
about 1 month ago
Post
6534
deepseek-ai/DeepSeek-OCR is out! 🔥 my take ⤵️
> pretty insane it can parse and re-render charts in HTML
> it uses CLIP and SAM features concatenated, so better grounding
> very efficient per vision tokens/performance ratio
> covers 100 languages
> pretty insane it can parse and re-render charts in HTML
> it uses CLIP and SAM features concatenated, so better grounding
> very efficient per vision tokens/performance ratio
> covers 100 languages
- 3 replies
antonioloisonÂ
authored
a
paper
about 2 months ago