Titile: From Learning through Labels to Learning through Language
Date: 2024-08-22 13:30-14:30
Location: CSIE R104
Speaker: Prof. Kai-Wei Chang, UCLA
Host: Prof. Vivian Yun-Nung Chen
Abstract:
Over the past few decades, machine learning has predominantly relied on labeled data. Achieving high performance has depended on the availability of vast, high-quality annotated training data, as well as the assumption that the test conditions are identical to the training conditions. However, it's noteworthy that humans don't learn from hundreds of thousands of annotated samples, but often learn from conceptual explanations, instructions, and contextual understanding. With the advancement of large language models, AI agents can now understand descriptions and follow instructions. Therefore, we investigate how to empower AI agents to learn from natural language narratives and multimodal interactions with humans, making them more adaptable to rapidly changing environments.
In this talk, I will showcase our journey of developing object recognition models that can absorb knowledge from rich natural language descriptions to recognize new objects. I will further discuss how to use language to steer language models and text-to-image models, enhancing their inclusivity and robustness. Finally, I will conclude the talk by discussing future directions and potential challenges in empowering models to learn through language.
Biography:
Kai-Wei Chang is an Associate Professor in the Department of Computer Science at the University of California Los Angeles and an Amazon Scholar at Amazon AGI. His research interests include designing trustworthy natural language processing systems and developing multimodal models for vision-language applications. Kai-Wei has published broadly in NLP, AI, and ML. His awards include the Sloan Fellow (2021), AAAI Senior Member (2023), EMNLP Best Long Paper Award (2017), and KDD Best Paper Award (2010). He is elected as an officer of SIGDAT, the organizer running EMNLP. Kai-Wei obtained his Ph.D. from the University of Illinois at Urbana-Champaign in 2015 and was a post-doctoral researcher at Microsoft Research in 2016. Additional information is available at http://kwchang.net