Skip to content
View ZikunFu's full-sized avatar
2 followers · 0 following

Highlights

  • Pro

Block or report ZikunFu

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ZikunFu/README.md

Hi, I'm Zikun

MSc Computer Science graduate (Ontario Tech University, 2026) worked on language models and structured data includes ML/NLP, AI automation, and data systems.

  • My thesis, Database Entity Recognition using Language Models, reached 93.2% F1 grounding natural language questions to database schemas; published at IEEE IRI 2025.
  • I build grounded LLM systems: hermes-clinic-analytics is an AI analytics assistant that structurally cannot hallucinate: Using read-only DuckDB, SQL allowlist, and provenance on every answer; 100% grounding / 0% hallucination on an oracle-backed harness.
  • I also build AI automation with real world guardrails: an LLM exam grading pipeline (~70 handwritten finals for ~$10, with human review) and an automated web presence audit pipeline.

More: zikunfu.github.io · LinkedIn · Resume (PDF)

Pinned Loading

  1. hermes-clinic-analytics hermes-clinic-analytics Public

    LLM analytics assistant over structured business data.

    Python

  2. miners miners Public

    Forked from gentaiscool/miners

    Extending in-context learning and DPR experiments (OTU CSCI 6720)

    Python

  3. PEDFE-EmoAnalysis PEDFE-EmoAnalysis Public

    Analysis of Elicited and Acted Emotional Expressions in PEDFE

    Jupyter Notebook 1 1

  4. DBER DBER Public

    Database Entity Recognition: grounding natural-language questions to database tables, columns, and values. Code, trained-model artifacts, and results for the DB-ER benchmark (IEEE IRI 2025); datase…

    Python