Matteo Omenetti's picture

Matteo Omenetti

MatteoOmenetti

·

matteo-omenetti

AI & ML interests

None yet

Recent Activity

upvoted a paper about 1 month ago

ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding

upvoted an article about 1 month ago

Granite 4.0 3B Vision: Compact Multimodal Intelligence for Enterprise Documents

new activity 6 months ago

deepseek-ai/DeepSeek-OCR:[BUG] Missing grounding of first element in the image when the element is of type Text

View all activity

Organizations

New activity in deepseek-ai/DeepSeek-OCR 6 months ago

[BUG] Missing grounding of first element in the image when the element is of type Text

#75 opened 6 months ago by

New activity in ibm-granite/granite-docling-258M 7 months ago

Model only output !!!!! when using with vllm

#22 opened 7 months ago by

New activity in HuggingFaceM4/DoclingMatix 8 months ago

Is there any tool converting DocTag into other formats like markdown?

#2 opened 8 months ago by

New activity in docling-project/SmolDocling-256M-preview 11 months ago

Is the chat_template.json file wrong?

#41 opened about 1 year ago by