Towards Granular-Aware MLLM with Diverse Reasoning Capability: Technical Challenges and Open Questions

Speaker: Dr. Yi R. (May) Fung
Assistant Professor
Department of Computer Science and Engineering
Hong Kong University of Science and Technology

Title: Towards Granular-Aware MLLM with Diverse Reasoning Capability: Technical Challenges and Open Questions

Date: Monday, 1 September 2025

Time: 4:00pm - 5:00pm

Venue: Lecture Theater F
(Leung Yat Sing Lecture Theater), near lift 25/26, HKUST

Abstract:

In recent years, multimodal large language models have achieved remarkable progress, excelling across diverse tasks and demonstrating impressive few-shot learning capabilities. However, ensuring these models align with principles of trustworthiness, robustness, and human-centric reasoning remains an open challenge. In this talk, we present a roadmap for enhancing foundation models’ reasoning capabilities, with a focus on diagnosing and improving their reasoning robustness, knowledge boundary awareness, and perspective diversity. We then conclude with a discussion on scalable approaches and emerging research directions that promise to make foundation models more interpretable, advanced, and aligned with human cognitive reasoning, paving the path towards AI agents that operate reliably in dynamic, real-world environments.

Biography:

Yi R. (May) Fung is an Assistant Professor at the Department of Computer Science and Engineering (CSE), Hong Kong University of Science and Technology (HKUST). She received her Ph.D. from the University of Illinois, after which she spent time visiting MIT as a postdoctoral researcher. May drives cutting-edge research in the domain of human-centric trustworthy AI/NLP model reasoning, with cognitively grounded scalable alignment principles and a focus on advancing robust multimodal knowledge awareness mechanisms. In particular, she has published over 30 papers at top-tier machine learning venues along the topics of agentic frameworks, retrieval-augmented generation, and multi-lingual sociocultural-adaptive situation understanding for diverse real-world applications (e.g., business, software, healthcare, education, media communication). Her stellar research has received many prestigious recognition internationally, including the ACL '24 Outstanding Paper Award, NAACL '24 Outstanding Paper Award, and NAACL '21 Best Demo Paper Award. In addition, she serves on the organizing committee for IJCAI, as Area Chair for ACL/EMNLP/ACL-RR, and as Program Chair for ACM Multimedia System (MMSys). She leads a young, energetic, and growing research lab.