Wentao Zhu

Join us tomorrow for the 1st Workshop on Humanoid Agents! We have an exciting lineup: @xiaolonw @xavierpuigf @GuanyaShi @GerardPonsMoll1 @blacksquirrel__ @tianminshu @petitegeek @xbpeng4 📍 Room 101 D, Music City Center 🔗 humanoid-agents.github.io @CVPR #CVPR2025

I'll talk about human-object/scene interactions, capture and synthesis: Today at 11.30 📍 Room 101 D, Music City Center 🔗 humanoid-agents.github.io Workshop will be stream vía zoom on cvpr official link.

✈️Off to #CVPR2025! Posters: InterAct: Fri 14-16(#162) sirui-xu.github.io/InterAct InterMimic(highlight): Sat 10:30-12:30(#155) sirui-xu.github.io/InterMimic Talks: Humanoid Agents: Wed 10:30 Agents in Interaction: Thu 14:45 Excited to catch up with friends—old and new—and chat!🚀

I will be talking at the #CVPR2025 workshop on Humanoid Agents, tomorrow June 11th at 9:30 am. I will discuss how humanoid agents can help us improve human-robot collaboration. See you there! humanoid-agents.github.io

✈️to #CVPR2025 to give three workshop/tutorial talks about learning humanoid whole-body control and loco-manipulation: - Wed 8:30am @ 3D Scene Understanding, 106C - Wed 10am @ Humanoid Agent, 101D - Thu 11am @ Robotics 101 tutorial, 202B Excited to meet old & new friends!

Angjoo Kanazawa @akanazawa and I taught CS 280, graduate computer vision, this semester at UC Berkeley. We found a combination of classical and modern CV material that worked well, and are happy to share our lecture material from the class. cs280-berkeley.github.io Enjoy!

📅 Submission deadline is next week (Apr 29)! We welcome new work and recent published papers (e.g., ICLR, CVPR, RSS, ICRA)! Non-archival, interdisciplinary, and exciting. 🦾 🔗 Submit & join the discussion: humanoid-agents.github.io #CVPR2025 @CVPR

Join us at the 1st Workshop on Humanoid Agents @CVPR! #CVPR2025 Speakers in CV, CG, Robotics & CogSci will share insights on building virtual & physical human-like AI agents. 💃🤖🦾 📢 Submit your work & spark interdisciplinary discussions! 🔗 Details: humanoid-agents.github.io

We released PARTNR, the largest benchmark to study human-robot collaboration in households, with +100K natural language tasks! PARTNR tests agents in key capabilities including: 🔍 Perceiving dynamic environments 🎯 Task planning and skill execution 🤝 Coordination with humans

Join us with inspiring talks at the 5th #CV4Animals Workshop at #CVPR2025 @CVPR 🦒🦍🐒🐳🐆🐎🐈‍⬛🐁🐕🪼🦋 Don’t miss the chance to submit your work by March 28: cv4animals.com🌟

Excited to announce our new work, FreeCloth! Our hybrid framework combines LBS-based deformation with free-form generation, achieving SOTA performance in challenging clothed human modeling with superior visual fidelity and realism. Check it out here: alvinyh.github.io/FreeCloth/

I wonder what went on in her head when making that slide. The student’s nationality is irrelevant, she still puts it there, she *knows* it’s wrong so writes the hedge in green instead of just… not mentioning the nationality…? Props to the person who confronted her on the spot!

Stoked to have presented our #ECCV2024 paper "Real-time Holistic Robot Pose Estimation with Unknown States" @eccvconf. We estimate camera-to-robot pose without known GT joint states as additional inputs. Instead, we estimate both robot pose and joint states holistically (p1).

Just updated my Tips for CS Faculty Applications. Best of luck to everyone applying! yisongyue.medium.com/checklist-of-t…

Can LLMs represent their own and others' beliefs? If so, can manipulating these representations impact their social reasoning abilities? Our new #ICML2024 study says yes! Paper: arxiv.org/pdf/2402.18496 Code: walter0807.github.io/RepBelief/ Poster: Thu 1:30 PM, Hall C 4-9 #707

🚨CVPR 2024 Paper Alert 🚨 ➡️Paper Title: ScoreHypo: Probabilistic Human Mesh Estimation with Hypothesis Scoring 🌟Few pointers from the paper 🎯Monocular 3D human mesh estimation is an ill-posed problem characterized by inherent ambiguity and occlusion. While recent…