M.Sc. in AI and Entrepreneurship — HKUST (2026–2028) B.Eng. in Computer Science and Technology — ECUST (2022–2026)
I build LLM and agent systems, and the evaluation harnesses that keep them honest. My work sits between applied AI engineering and measurement: retrieval-augmented pipelines, structured outputs and tool calling, and benchmarks that test whether a model actually understands a situation rather than pattern-matching it.
vlm-world-knowledge-benchmark A counterfactual image-understanding benchmark for vision-language models. It separates "the model recognises the picture" from "the model can reason about what would happen if one variable changed", using paired relevant / irrelevant knowledge conditions to isolate where accuracy gains actually come from.
ai-work-order-system Natural-language maintenance ticket triage: unstructured repair reports become categorised, geocoded, worker-assigned work orders. A pure-LLM pipeline was not reliable enough, so the LLM is constrained by a rule engine at every step. Dockerised FastAPI backend, Vue front end, public demo.
Contact — cyuanam@connect.ust.hk