My research interests include natural language processing (vision-to-language applications and human-preferred language generation/evaluation), machine learning (fairness and reliability in distributed ML), and AI applications for social good.

Striking Up Conversations via Conversational Visual Question Generation.

I am a PhD candidate in the School of Electrical & Computer Engineering at Purdue University, working on Machine Learning, Natural Language Processing, and AI for Social Good. My current research...

IEEE Transactions on Emerging Topics in Computing, 2024.

My current research focuses on vision-to-language projects, such as visual storytelling and video question answering. My research interests span machine learning and deep learning...

In this project, we propose a meta-learning-based adaptive parameter selection methodology to improve the communication efficiency of model transmissions from clients in federated multilingual NLP.

Yun-Wei Chu PhD student, Purdue University Joined November 2021

Jan 15, 2024 · View a PDF of the paper titled Only Send What You Need: Learning to Communicate Efficiently in Federated Multilingual Machine Translation, by Yun-Wei Chu and 2 other authors

Yun-Wei Chu received the B.S. degree in electrical engineering from National Chi Nan University, Puli, Taiwan, in 2015 and the M.S. degree in electrical control engineering from National Chiao Tung University, Hsinchu, Taiwan, in 2017.

Aug 2, 2022 · View a PDF of the paper titled Mitigating Biases in Student Performance Prediction via Attention-Based Personalized Federated Learning, by Yun-Wei Chu and 6 other authors