<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>News |</title><link>https://lhk6666.github.io/tags/news/</link><atom:link href="https://lhk6666.github.io/tags/news/index.xml" rel="self" type="application/rss+xml"/><description>News</description><generator>HugoBlox Kit (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Mon, 07 Sep 2026 00:00:00 +0000</lastBuildDate><image><url>https://lhk6666.github.io/media/icon_hu_eee4a95885829ab2.png</url><title>News</title><link>https://lhk6666.github.io/tags/news/</link></image><item><title>🎉 CoFL-S accepted to CoRL 2026</title><link>https://lhk6666.github.io/blog/cofl-s-accepted-corl-2026/</link><pubDate>Mon, 07 Sep 2026 00:00:00 +0000</pubDate><guid>https://lhk6666.github.io/blog/cofl-s-accepted-corl-2026/</guid><description>&lt;p&gt;Our paper &lt;strong&gt;CoFL-S: Spatially Queryable Sector Flow Fields for Local
Language-Conditioned Navigation&lt;/strong&gt; has been accepted to the
!&lt;/p&gt;
&lt;p&gt;CoFL-S is a low-level vision-language-action framework that predicts a
language-conditioned flow field over the robot&amp;rsquo;s local visible sector and
rolls it out into continuous trajectories. It is trained with frame-level
local supervision distilled from VLN-CE episodes.&lt;/p&gt;
&lt;ul&gt;
&lt;li&gt;Paper page:
&lt;/li&gt;
&lt;li&gt;arXiv:
&lt;/li&gt;
&lt;li&gt;Video:
&lt;/li&gt;
&lt;/ul&gt;
&lt;p&gt;Many thanks to all my co-authors and to my advisor Moju Zhao. See you at CoRL!&lt;/p&gt;</description></item><item><title>🎉 Website launched</title><link>https://lhk6666.github.io/blog/website-launched/</link><pubDate>Mon, 13 Jul 2026 00:00:00 +0000</pubDate><guid>https://lhk6666.github.io/blog/website-launched/</guid><description>&lt;p&gt;Welcome to my new personal homepage! Here I will share news about my
research on vision-language-action models and robotics.&lt;/p&gt;</description></item></channel></rss>