<feed xmlns="http://www.w3.org/2005/Atom"> <id>/</id><title>Yuan Fang</title><subtitle></subtitle> <updated>2025-07-17T14:45:06+00:00</updated> <author> <name>Yuan Fang</name> <uri>/</uri> </author><link rel="self" type="application/atom+xml" href="/feed.xml"/><link rel="alternate" type="text/html" hreflang="en" href="/"/> <generator uri="https://jekyllrb.com/" version="4.4.1">Jekyll</generator> <rights> © 2025 Yuan Fang </rights> <icon>/assets/img/favicons/favicon.ico</icon> <logo>/assets/img/favicons/favicon-96x96.png</logo> <entry><title>Mani-GPT</title><link href="/posts/manigpt/" rel="alternate" type="text/html" title="Mani-GPT" /><published>2024-09-24T00:00:00+00:00</published> <updated>2024-09-24T00:00:00+00:00</updated> <id>/posts/manigpt/</id> <content type="text/html" src="/posts/manigpt/" /> <author> <name>Yuan Fang</name> </author> <category term="Project" /> <summary>Repository Link: https://github.com/FangYzzz/manigpt 1 Introduction In an ideal scenario, interactive robots should possess the ability to engage in smooth, natural conversations with humans, as well as to flexibly execute tasks related to their operations. When it comes to conversation, human interactions are often multi-turn, involving progressively deeper discussions, ambiguous instruct...</summary> </entry> </feed>
