<?xml version="1.0" encoding="utf-8"?><feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en"><generator uri="https://jekyllrb.com/" version="4.4.1">Jekyll</generator><link href="https://wozengyi.github.io/feed.xml" rel="self" type="application/atom+xml"/><link href="https://wozengyi.github.io/" rel="alternate" type="text/html" hreflang="en"/><updated>2026-09-26T04:00:58+00:00</updated><id>https://wozengyi.github.io/feed.xml</id><title type="html">blank</title><subtitle>Zengyi Wo is a joint Ph.D. student at Nanjing University and the Institute of Automation, Chinese Academy of Sciences (CASIA), affiliated with PRLab and focusing on VLM agents, post-training, and Embodied AI. His previous work includes multimodal LLM post-training, graph machine learning, and data mining. </subtitle></feed>