<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"><channel><description>Ph.D. Student @ UMich EECS. Multimodal learning, audio-visual learning and computer vision. &#xA;Prev research Intern @Adobe and @Meta&#xA;&#xA;https://ificl.github.io/</description><link>https://bsky.app/profile/czyang.bsky.social</link><title>@czyang.bsky.social - Ziyang Chen</title><item><link>https://bsky.app/profile/czyang.bsky.social/post/3lbvklevtbk27</link><description>🎥 Introducing MultiFoley, a video-aware audio generation method with multimodal controls! 🔊&#xA;We can&#xA;⌨️Make a typewriter sound like a piano 🎹&#xA;🐱Make a cat meow like a lion roars! 🦁&#xA;⏱️Perfectly time existing SFX 💥 to a video.&#xA;&#xA;arXiv: arxiv.org/abs/2411.17698&#xA;website: ificl.github.io/MultiFoley/</description><pubDate>27 Nov 2024 02:58 +0000</pubDate><guid isPermaLink="false">at://did:plc:of7tyzi5arweotwpry5pkzrf/app.bsky.feed.post/3lbvklevtbk27</guid></item></channel></rss>