open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.

Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。

mlops course project - an automatic ml pipeline for a regression model improvement (tabular datasets)

AI Toolkit for Healthcare Imaging

Visualize and compare datasets, target values and associations, with one line of code.

NLP project: Questions generation from relations

Urban segmentation on multi channel satellite images to identify Residential and Industrial built up areas

Final Project Paper Report in Recommendation System Course (Reichman University)

Text based Stress Classification and Gender Bias Detection on “Dreaddit” Dataset

Deep Learning for humans

Benchmarks for popular CNN models