Vidore Leaderboard
🥇
189
Browse and compare visual document retrieval models
AI & ML interests
Retrieval, Computer Vision, LLM
Recent Activity
View all activity
Add ViDoRe V3 (MTEB embed)
#14 opened 1 day ago
by
antoineedy
manuÂ
Training Hyperparameter for Colqwen2.5-v0.2 reproduce
2
#10 opened about 2 months ago
by
Ryenhails
manuÂ
Add LICENSE file
#13 opened 16 days ago
by
jewittje
manuÂ
updated
a
Space
19 days ago
manuÂ
revert-tabs
#12 opened 19 days ago
by
manu
antoineedyÂ
updated
a
Space
23 days ago
QuentinJGÂ
updated
8
datasets
about 1 month ago
vidore/vidore_v3_finance_fr
Viewer
•
Updated
•
13.1k
•
1.15k
vidore/vidore_v3_physics
Viewer
•
Updated
•
16.6k
•
1.57k
•
2
vidore/vidore_v3_energy
Viewer
•
Updated
•
10.7k
•
1.58k
•
1
vidore/vidore_v3_computer_science
Viewer
•
Updated
•
8.95k
•
1.93k
•
1
vidore/vidore_v3_pharmaceuticals
Viewer
•
Updated
•
14.9k
•
1.3k
vidore/vidore_v3_industrial
Viewer
•
Updated
•
16.7k
•
1.69k
•
1
vidore/vidore_v3_finance_en
Viewer
•
Updated
•
13.6k
•
1.86k
•
3
vidore/vidore_v3_hr
Viewer
•
Updated
•
13.4k
•
1.75k
•
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
6688
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
- 4 replies