Dana Aubakirova's picture

2 10

Dana Aubakirova

danaaubakirova

·

AI & ML interests

DocumentAI, Deep Learning, Multimodal Learning, Computer Vision, Image Processing, NLP

Recent Activity

upvoted a collection 22 days ago

ISSAI-KazLLM-1.0

View all activity

Articles

Introducing TextImage Augmentation for Document Images

LAVE: Zero-shot VQA Evaluation on Docmatix with LLMs - Do We Still Need Fine-Tuning?

Multimodal Augmentation for Documents: Recovering “Comprehension” in “Reading and Comprehension” task

Organizations

danaaubakirova's activity

New activity in danaaubakirova/mplugdocowl1.5-Omni-hf 6 months ago

Is this ready to be used with the transformers library?

#1 opened 6 months ago by

New activity in mPLUG/DocOwl 6 months ago

Update model_worker.py

#4 opened 6 months ago by