Juan Balarini PRO

jpbalarini's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a Space 1 day ago

Running on Zero

325

325

Qwen Image Edit Camera Control

🎬

Fast 4 step inference with Qwen Image Edit 2509

upvoted an article 4 days ago

view article

Article

ViDoRe V3: a comprehensive evaluation of retrieval for enterprise use-cases

By and 4 others •

5 days ago

• 34

liked a model 4 days ago

ibm-granite/granite-vision-3.3-2b-embedding

Feature Extraction • 3B • Updated Aug 16 • 4.09k • 22

liked a dataset 7 days ago

vidore/colpali_train_set

Viewer • Updated Jun 20 • 119k • 3.74k • 87

liked a model 10 days ago

ModernVBERT/colmodernvbert-merged

Visual Document Retrieval • 0.3B • Updated 20 days ago • 2

commented on Introducing ColQwen-Omni: Retrieve in every modality 10 days ago

view reply

Is there any benchmark contrasting this to ColQwen2.5 v2 for example?
Thanks!

liked a model 10 days ago

nvidia/omni-embed-nemotron-3b

Feature Extraction • 5B • Updated Oct 9 • 41.4k • 62

liked a model 16 days ago

XiaomiMiMo/MiMo-Audio-7B-Instruct

Any-to-Any • 8B • Updated Sep 23 • 6.54k • 129

upvoted an article 16 days ago

view article

Article

Supercharge your OCR Pipelines with Open Models

20 days ago

• 228

liked a model 20 days ago

deepseek-ai/DeepSeek-OCR

Image-Text-to-Text • 3B • Updated 6 days ago • 3M • • 2.57k

liked a model 23 days ago

PaddlePaddle/PaddleOCR-VL

Image-Text-to-Text • 1.0B • Updated 6 days ago • 36k • 1.24k

liked a model 24 days ago

facebook/MobileLLM-Pro

Text Generation • 1B • Updated 16 days ago • 4.65k • 141

liked a model 26 days ago

nanonets/Nanonets-OCR2-3B

Image-Text-to-Text • 4B • Updated 25 days ago • 84.9k • 435

liked 3 models about 1 month ago

ibm-granite/granite-docling-258M

Image-Text-to-Text • 0.3B • Updated Sep 23 • 129k • 1.01k

lerobot/pi05_base

4B • Updated Oct 2 • 1.1k • 25

ModernVBERT/bimodernvbert

Visual Document Retrieval • Updated Oct 2 • 213 • 3

liked 3 Spaces about 2 months ago

Running

27

27

PP-StructureV3 Online Demo

📊

Next-Gen High-Precision Doc Parsing Solution

Running

69

69

PP-OCRv5 Online Demo

🌍

Universal-Scene Text Recognition Model with High-Accuracy

Running on Zero

23

23

KOSMOS-2.5 Document AI Demo

📄

Upload an image to generate markdown, extract text, or ask questions

liked a model about 2 months ago

Qwen/Qwen3-Next-80B-A3B-Thinking

Text Generation • 81B • Updated Sep 15 • 124k • • 440