Zekun Blog

Building and evaluating AI-powered products, agent systems, and local-first developer tools.

Slides Thief 2.0: From Rectangle Heuristics to Evidence-Aware Review

A browser-local redesign of boundary detection, confidence, and batch geometry.

What Changed in Slides Thief 2.0? Slides Thief 2.0 replaces a single rectangle heuristic with an evidence-aware detection pipeline. Instead of trusting the first plausible boundary, several detec...

Posted by Zekun Wang on August 1, 2026

Designing Memory That Can Safely Forget

Persistent project memory is trustworthy only when forgetting is explicit, previewable, and bounded.

What Makes Agent Memory Safe to Forget? Safe forgetting makes deletion intent explicit, previews the complete semantic effect before writing, and plans every affected file as one mutation. It remo...

Posted by Zekun Wang on July 21, 2026

Why Project Memory Should Be Plain Text and Repo-Native

Durable coding-agent memory should live with the code, survive the tool, and load only when relevant.

Why Use Plain Text for Project Memory? Plain-text, repo-native memory remains readable without the original tool, travels with the code, participates in ordinary review, and works across agent pla...

Posted by Zekun Wang on July 20, 2026

Slides Thief - Turn Photographed Presentation Slides into Clean PDFs

Just take photos of the slides—they are yours now.

We have all done it: sitting at an angle in a classroom, academic talk, tech sharing session, or trade show, quickly taking photos of presentation slides before they disappear. The problem comes l...

Posted by Zekun Wang on July 13, 2026

MemoryCustodian: Durable Project Memory for Coding Agents

Memory can grow; context must stay small.

What Is MemoryCustodian? MemoryCustodian is a repo-native memory protocol and CLI for coding agents. It stores durable project decisions and constraints in plain Markdown, keeps their history in G...

Posted by Zekun Wang on July 1, 2026

Social inequality and cultural factors impact the awareness and reaction during the cryptic transmission period of the pandemic

PNAS Nexus

The World Health Organization (WHO) declared the COVID-19 outbreak a Public Health Emergency of International Concern on January 31, 2020. However, rumors of a “mysterious virus” had already been c...

Posted by Zhuoren Jiang, Xiaozhong Liu, Yangyang Kang, Changlong Sun, Yong-Yeol Ahn, Johan Bollen on February 1, 2025

Characterizing browser-based medical imaging AI with serverless edge computing: towards addressing clinical data security constraints

SPIE Medical Imaging, 2023

The deployment of deep learning algorithms in clinical practice faces challenges in data privacy and local hardware constraints. This work presents the tools and design choices of a browser-based e...

Posted by Chenxi Dong, Thomas Z. Li, Kaiwen Xu, Zekun Wang, Fabien Maldonado, Kim Sandler, Bennett A. Landman, Yuankai Huo on April 10, 2023

WearMask: Fast in-browser face mask detection with serverless edge computing for COVID-19

Electronic Imaging

The COVID-19 epidemic has been a significant healthcare challenge in the United States. COVID-19 is transmitted predominantly by respiratory droplets generated when people breathe, talk, cough, or ...

Posted by Zekun Wang, Pengwei Wang, Peter C. Louis, Lee E. Wheless, Yuankai Huo on January 1, 2023

K-Means-Based Anomalous Email Detection in PySpark

Anomaly detection for emails based on MinHash and K-Means, implemented with PySpark and Colab

Reading tip. Intermediate Spark .show() / cell outputs are folded in the bordered blocks below. Click Click to expand to reveal a horizontally scrollable monospace dump; the Python steps stay vi...

Posted by Zekun Wang on May 5, 2021

WearMask - Face Mask Detection Project Details

Low-cost solution for small businesses and public places

The paper has been published in Electronic Imaging (2023): WearMask: Fast in-browser face mask detection with serverless edge computing for COVID-19. A preprint is also available on arXiv. Source c...

Posted by Zekun Wang on December 1, 2020

Topics

About

Building AI agent systems that can be evaluated, improved, and trusted.

zekun.wang.us@gmail.com