Skip to content
View Mixriaoliao's full-sized avatar
  • Fuzhou University of International Studies and Trade
  • Fuzhou, China

Block or report Mixriaoliao

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.

Content in all repositories owned by your account will be closed.
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
Mixriaoliao/README.md

Leo / 李奥

Artificial Intelligence undergraduate focused on building verifiable AI systems, reproducible LLM evaluation, local-first software, and practical AI applications.

What I build and study

  • AI systems and agent workflows with explicit validation boundaries
  • Reproducible evaluation of LLM agent reliability and feedback adaptation
  • Local-first applications that keep users in control of their data
  • Practical and industrial AI prototypes with limitations stated clearly

Selected work

A local-first Windows sticky-note application built with Tauri, Rust, React, TypeScript, and SQLite. It includes a mobile web companion, self-hosted synchronization, automated tests, CI, and a downloadable Windows release.

The current MVP is designed for personal use and trusted local networks; its documentation explicitly covers the absence of end-to-end encryption and other production security boundaries.

An industrial AI prototype and case study for exploring image-derived heuristic features, material matching, and visualization. It is a demonstration system, not a production-validated waste-steel grading model.

Current research

Reproducible evaluation of LLM agent reliability and feedback adaptation, with engineering verification kept separate from research-hypothesis evidence.

Technical focus

Python · TypeScript · React · Rust · SQLite · Tauri · LLM evaluation · testing · reproducible experiments

Working style

Evidence before claims. Reproducibility where results matter. AI-assisted engineering with human review, tests, and explicit product and research boundaries.

Popular repositories Loading

  1. waste-steel-ai waste-steel-ai Public

    Industrial AI prototype exploring deterministic image-derived heuristics and weighted nearest-center matching.

    Python 2

  2. ZFCheckScores ZFCheckScores Public

    Forked from NianBroken/ZFCheckScores

    正方教务管理系统每隔 30 分钟自动检测一次成绩是否有更新,若有更新,将通过微信推送及时通知用户。| 正方教务系统 | 成绩推送 | 成绩通知 | 成绩更新 | 显示成绩提交时间 | 显示成绩提交人姓名 | 成绩信息按时间降序排序 | 计算 GPA | 计算百分制 GPA | 显示未公布成绩的课程

    Python 1

  3. pinboard-local-notes pinboard-local-notes Public

    本地优先的 Windows 悬浮便签,配套手机网页与自托管同步服务。

    TypeScript 1

  4. Mixriaoliao Mixriaoliao Public

    AI student developer focused on verifiable AI systems, reproducible LLM evaluation, and local-first software.

  5. AI-Competition-PPT-Agent AI-Competition-PPT-Agent Public archive

    AI Agent concept for turning competition materials into editable PPTX, pitch logic and Q&A.