<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Genai on Jungbae Park</title><link>https://jungbaepark.github.io/blog/tags/genai/</link><description>Recent content in Genai on Jungbae Park</description><generator>Hugo -- 0.152.2</generator><language>en-us</language><lastBuildDate>Thu, 01 Jan 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://jungbaepark.github.io/blog/tags/genai/index.xml" rel="self" type="application/rss+xml"/><item><title>Scene-to-Products Retrieval for Digital Twin (Image-to-3D)</title><link>https://jungbaepark.github.io/blog/projects/digital-twin-scene-retrieval/</link><pubDate>Thu, 01 Jan 2026 00:00:00 +0000</pubDate><guid>https://jungbaepark.github.io/blog/projects/digital-twin-scene-retrieval/</guid><description>Built an end-to-end scene-to-products retrieval pipeline for Digital Twin at Bucketplace, achieving 13x recall improvement, 6,000x cost reduction in 3D collaboration, and scaling the catalog from 30K to 400K+ products.</description></item><item><title>OHouseAI GenAI Workflow Systematization</title><link>https://jungbaepark.github.io/blog/projects/ohouseai-genai-workflow/</link><pubDate>Sat, 15 Nov 2025 00:00:00 +0000</pubDate><guid>https://jungbaepark.github.io/blog/projects/ohouseai-genai-workflow/</guid><description>Led systematization of OHouseAI&amp;rsquo;s GenAI interior design service at Bucketplace, achieving +253% net satisfaction, 2x latency reduction, and outperforming GPT-IMAGE-1.5 and Gemini Nano. Reached Korea #8 in Graphics/Design.</description></item></channel></rss>