Trustworthy multimodal foundation models — fusion, faithfulness & reasoning.
I am a second-year third-year Ph.D. student in the Joint Programme between the
Institute of Intelligent Machines,
Hefei Institute of Physical Science, CAS, and
USTC. I am fortunate to be advised by Prof.
Yining Sun
and Prof. Zenghui Ding. Previously I received my M.Sc. in
Data Science and Analytics from
The Hong Kong Polytechnic University.
My research centers on the trustworthy deployment of agents built on large foundation models (LLMs, LVLMs). Currently I focus on efficient multimodal fusion (image–text, video–text) — improving fairness, mitigating hallucinations, and strengthening reasoning.
AI Research Intern
Ant Group
AI Research Intern
Squirrel AI LearningResearch on adaptive learning and large-model methods for intelligent education systems.
Ph.D. Student · Artificial Intelligence
CAS (IIM) × USTC — Joint ProgrammeAdvised by Prof. Yining Sun & Prof. Zenghui Ding. Multimodal fusion, hallucination mitigation, and reasoning in foundation models.
M.Sc. · Data Science and Analytics
The Hong Kong Polytechnic UniversityFoundations in statistical learning, data analytics, and machine learning that seeded my move into multimodal research.
Preprint In Submission, 2025 BibTeX
ICCV 2025 International Conference on Computer Vision
ICCV 2025 International Conference on Computer Vision
ACL 2025 Annual Meeting of the ACL (Findings)