Second-year Undergraduate
Hongyi Honor Class of Computer Science, Wuhan University
Sep. 2024 - Jun. 2028
Supervised by Prof. Mang Ye
I am a second-year undergraduate student in the Hongyi Honor Class of Computer Science at Wuhan University. I am interested in large language models, AI for education, multimodal learning, and agentic systems. I enjoy building research prototypes that turn AI capabilities into useful learning and reasoning tools.
I work to understand how models work internally, and to turn that understanding into a bridge — making AI more aligned with people, more trustworthy, and better able to augment human capabilities. Whether it's making a model's competence legible and correctable, or helping AI genuinely support how people learn and grow.
Selected publications and preprints.
Proposes Semantic Consistency Learning for animal re-identification across species, improving cross-species generalization under diverse morphologies and ecological domains.
Introduces OmniManim, a render-feedback-aware framework for generating educational animations with explicit visual planning, structured diagnostics, and localized repair.
Co-building an AI learning workspace that decomposes problems, explains reasoning paths, and helps students connect worked examples to notes, plans, and follow-up practice.
Participating in the Microsoft Research Asia Star of Tomorrow Internship Program, working on language models and model alignment.
Coursework and project work across language models, educational AI, multimodal systems, and agentic tools.
Co-leading product design and prototyping for AI-assisted learning workflows and educational content generation.
Threshold-Stable Selective Classification for Freedom of Information Act Privilege Review
I am open to research collaboration and academic conversations in LLMs, AI for education, multimodal learning, and agentic systems.
Email: 2024302111194@whu.edu.cn