2 3 34

Tuan-Anh Nguyen

taprosoft

taprosoft

AI & ML interests

AI, ML, CV, Document Intelligence

Recent Activity

new activity about 10 hours ago

chunking-ai/pdf-playground:Docling Parameters

upvoted an article about 16 hours ago

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

updated a Space 1 day ago

chunking-ai/table-bench

View all activity

Organizations

taprosoft's activity

New activity in chunking-ai/pdf-playground about 10 hours ago

Docling Parameters

#1 opened 1 day ago by

Nebur21

upvoted an article about 16 hours ago

Article

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

2 days ago

• 196

updated a Space 1 day ago

TableBench

📊

Benchmark of OS PDF parsers on table dataset

liked 2 Spaces 1 day ago

TableBench

📊

Benchmark of OS PDF parsers on table dataset

PDFParsersPlayground

🐢

Convert PDFs to Markdown with open-source parsers

liked a Space 3 days ago

196

OCR

🍍

perfect ocr vlm :]

reacted to mkurman's post with 👍❤️ 3 days ago

Post

3671

Introducing a new architecture, MedIT One – a single-token transformer with LSTM-like recurrence.

It is extremely fast in training and inference, but we lack funding for large-scale training. Enjoy 🍓

https://github.com/MedITSolutionsKurman/medit-one

published a Space 3 days ago

TableBench

📊

Benchmark of OS PDF parsers on table dataset

updated a Space 6 days ago

PDFParsersPlayground

🐢

Convert PDFs to Markdown with open-source parsers

liked 2 Spaces 6 days ago

320

AI Deadlines

⚡

Schedule tasks efficiently using AI-generated deadlines

4.16k

Chatbot Arena Leaderboard

🏆

Display chatbot leaderboard and statistics

reacted to andito's post with 🔥🚀 6 days ago

Post

2425

Extremely bullish on @CohereForAI 's Aya Vision (8B & 32B) - new SOTA open-weight VLMs

- 8B wins up to 81% of the time in its class, better than Gemini Flash
- 32B beats Llama 3.2 90B!
- Covers 23 languages, excels in image captioning, VQA & more
- Integrated on transformers from Day 0!

Efficient multimodal models are here to stay!!🔥
Check out their blog! https://huggingface.co/blog/aya-vision