Hong-Xing "Koven" Yu (@koven_yu) 's Twitter Profile
Hong-Xing "Koven" Yu

@koven_yu

AI PhD at @StanfordAILab @StanfordSVL, working on understanding and generating the physical world.

ID: 1417003475167178754

linkhttps://kovenyu.com/ calendar_today19-07-2021 06:08:55

72 Tweet

1,1K Takipçi

273 Takip Edilen

Fei-Fei Li (@drfeifei) 's Twitter Profile Photo
Fei-Fei Li
@drfeifei

8 months ago

Check out our newly released WorldScore, by our Stanford Vision and Learning Lab team on benchmarking world models!!❤️‍🔥🌎🏆

Hong-Xing "Koven" Yu (@koven_yu) 's Twitter Profile Photo
Hong-Xing "Koven" Yu
@koven_yu

6 months ago

[🚨 #CVPR2025 Oral 🚨] 🤩 Our code, data, and pretrained models of FluidNexus are released! github.com/ueoo/FluidNexus See you at #CVPR Tennessee!

Nate Gillman @ICLR'25 (@gillmanlab) 's Twitter Profile Photo
Nate Gillman @ICLR'25
@gillmanlab

6 months ago

Ever wish you could turn your video generator into a controllable physics simulator? We're thrilled to introduce Force Prompting! Animate any image with physical forces and get fine-grained control, without needing any physics simulator or 3D assets at inference. 🧵(1/n)

Ziwei Liu (@liuziwei7) 's Twitter Profile Photo
Ziwei Liu
@liuziwei7

6 months ago

🎬#CVPR2025 𝐓𝐮𝐭𝐨𝐫𝐢𝐚𝐥 🗺️𝑭𝒓𝒐𝒎 𝑽𝒊𝒅𝒆𝒐 𝑮𝒆𝒏𝒆𝒓𝒂𝒕𝒊𝒐𝒏 𝒕𝒐 𝑾𝒐𝒓𝒍𝒅 𝑴𝒐𝒅𝒆𝒍 #CVPR2025 🔗world-model-tutorial.github.io 📅June 11 🚀Hosted by MMLab@NTU x Kling AI 🧠Incredible lineup of speakers: Jack Parker-Holder Hong-Xing "Koven" Yu Jiaming Song Pengfei Wan Angjoo Kanazawa Sherry Yang

🎬#CVPR2025 𝐓𝐮𝐭𝐨𝐫𝐢𝐚𝐥 🗺️𝑭𝒓𝒐𝒎 𝑽𝒊𝒅𝒆𝒐 𝑮𝒆𝒏𝒆𝒓𝒂𝒕𝒊𝒐𝒏 𝒕𝒐 𝑾𝒐𝒓𝒍𝒅 𝑴𝒐𝒅𝒆𝒍 <a href="/CVPR/">#CVPR2025</a> 🔗world-model-tutorial.github.io 📅June 11 🚀Hosted by <a href="/MMLabNTU/">MMLab@NTU</a> x <a href="/Kling_ai/">Kling AI</a> 🧠Incredible lineup of speakers: <a href="/jparkerholder/">Jack Parker-Holder</a> <a href="/Koven_Yu/">Hong-Xing "Koven" Yu</a> <a href="/baaadas/">Jiaming Song</a> <a href="/wanfufeng/">Pengfei Wan</a> <a href="/akanazawa/">Angjoo Kanazawa</a> <a href="/sherryyangML/">Sherry Yang</a>
Zhao Dong (@flycooler_zd) 's Twitter Profile Photo
Zhao Dong
@flycooler_zd

6 months ago

🚀 Excited to announce our CVPR 2025 Workshop: 3D Digital Twin: Progress, Challenges, and Future Directions 🗓 June 12, 2025 · 9:00 AM–5:00 PM 📢 Incredible lineup: Richard Newcombe, Andrea Vedaldi Visual Geometry Group (VGG),Hao (Richard) Zhang,Qianqian Wang,Dr. Xiaoshuai Zhang Hillbot,

🚀 Excited to announce our CVPR 2025 Workshop: 3D Digital Twin: Progress, Challenges, and Future Directions 🗓 June 12, 2025 · 9:00 AM–5:00 PM 📢 Incredible lineup: <a href="/rapideRobot/">Richard Newcombe</a>, Andrea Vedaldi <a href="/Oxford_VGG/">Visual Geometry Group (VGG)</a>,<a href="/richardzhangsfu/">Hao (Richard) Zhang</a>,<a href="/QianqianWang5/">Qianqian Wang</a>,Dr. Xiaoshuai Zhang <a href="/Hillbot_AI/">Hillbot</a>,
Zizhang Li (@zizhang_li) 's Twitter Profile Photo
Zizhang Li
@zizhang_li

5 months ago

In our #ICCV2025 WonderPlay, we study how to combine physical simulation and video generative prior to enable 3D action interaction with the world from a single image! Check the 🧵for more details!

Hong-Xing "Koven" Yu (@koven_yu) 's Twitter Profile Photo
Hong-Xing "Koven" Yu
@koven_yu

5 months ago

🤩 WorldScore is accepted to #ICCV2025. Benchmark your 3D/4D/video world models with WorldScore!

Hong-Xing "Koven" Yu (@koven_yu) 's Twitter Profile Photo
Hong-Xing "Koven" Yu
@koven_yu

5 months ago

Very insightful post explaining and envisioning world models!!