<feed xmlns="http://www.w3.org/2005/Atom"> <id>https://jinnessism.github.io/</id><title>Jeongmin Park</title><subtitle>jinnessism.github.io is the personal website of Jeongmin Park, a M.S. student at KAIST. It is built with Jekyll and the Chirpy theme.</subtitle> <updated>2026-09-06T18:17:49+09:00</updated> <author> <name>Jeongmin Park</name> <uri>https://jinnessism.github.io/</uri> </author><link rel="self" type="application/atom+xml" href="https://jinnessism.github.io/feed.xml"/><link rel="alternate" type="text/html" hreflang="en" href="https://jinnessism.github.io/"/> <generator uri="https://jekyllrb.com/" version="4.4.1">Jekyll</generator> <rights> © 2026 Jeongmin Park </rights> <icon>/assets/img/favicons/favicon.ico</icon> <logo>/assets/img/favicons/favicon-96x96.png</logo> <entry><title>[CS588] Lecture PR: Retrieval-Augmented 3D Generation</title><link href="https://jinnessism.github.io/posts/CS588-Lecture-PR/" rel="alternate" type="text/html" title="[CS588] Lecture PR: Retrieval-Augmented 3D Generation" /><published>2026-04-02T21:33:00+09:00</published> <updated>2026-04-02T21:33:00+09:00</updated> <id>https://jinnessism.github.io/posts/CS588-Lecture-PR/</id> <content type="text/html" src="https://jinnessism.github.io/posts/CS588-Lecture-PR/" /> <author> <name>Jeongmin Park</name> </author> <summary>This post summarizes a lecture survey on Retrieval-Augmented 3D Generation presented at KAIST CS588. The survey explores how external 3D contexts can assist neural networks in generating 3D content more efficiently. Survey Overview The core objective of this survey is to address how to prevent hallucinations and incorporate up-to-date information without constantly updating model parameters. ...</summary> </entry> <entry><title>3rd Data Science Contest, with LG Electronics</title><link href="https://jinnessism.github.io/posts/LG-contest/" rel="alternate" type="text/html" title="3rd Data Science Contest, with LG Electronics" /><published>2024-01-27T18:00:00+09:00</published> <updated>2026-03-30T21:47:27+09:00</updated> <id>https://jinnessism.github.io/posts/LG-contest/</id> <content type="text/html" src="https://jinnessism.github.io/posts/LG-contest/" /> <author> <name>Jeongmin Park</name> </author> <summary>This post archives our work in the 3rd Data Science Contest with LG Electronics. I participated with three teammates: Dayoon, Juhee, and Donghwan. Contest Task Summary Given 130 weeks of historical component demand data, the contest involved two tasks: demand forecasting and inventory optimisation. For forecasting, the objective was to minimise Relative Mean Absolute Error (RMAE) between pred...</summary> </entry> </feed>
