Conveying Complex Information in Multi-modal Dialogue Generation through Event, Knowledge and Reasoning

The School of EECS is hosting the following PhD progress review 1:

Conveying Complex Information in Multi-modal Dialogue Generation through Event, Knowledge and Reasoning

Speaker: Fenghua Cheng
Host: Dr Xin Yu

Abstract: To Build conversational agents’ abilities to interact with human and specific environment by not only natural language but also perceiving the physical world using all senses is one of long-term goals of Artificial Intelligence (AI). With success achieved from Large Language Model (LLM), recent works raised increasing interest in developing a multi-modal conversational agent with visual ability. However, Understanding complex information from non-linguistic modalities, associating to external knowledge and generating response in a clear point of view are still unexplored in today's multi-modal dialogue research. Therefore, we target conveying more complex information into multi-modal dialogue generation with events, knowledge and reasoning. 

Biography: Fenghua Cheng is a Ph.D. student at the school of EECS in the University of Queensland, under the supervision of Prof. Xue Li and Prof. Helen Huang. He obtained his Bachelor of Computer Science from both Shandong University, China and Australian National University. He completed his Master of Computing at Australian National University. His research interests include multi-modal machine learning and vision-language learning.