Roozbeh Mottaghi (@roozbehmottaghi) 's Twitter Profile
Roozbeh Mottaghi

@roozbehmottaghi

AI Researcher; FAIR Robotics Leadership, @AIatMeta; Affiliate Prof @uwcse; Ex Research Manager @allen_ai; post-doc @Stanford and CS PhD @UCLA

ID: 1138872700376571905

linkhttp://roozbehm.info calendar_today12-06-2019 18:16:25

329 Tweet

3,3K Followers

228 Following

Roozbeh Mottaghi (@roozbehmottaghi) 's Twitter Profile Photo

Excited to open-source our latest work in advancing robot planning and reasoning within dynamic environments. Stay tuned for more information.

Zhao-Heng Yin (@zhaohengyin) 's Twitter Profile Photo

We introduce Dexterity Gen (DexGen), a foundation controller that enables unprecedented dexterous manipulation capabilities. For the first time, it allows human teleoperation of tasks such as using a pen, screwdriver, and syringe. Developed by @berkeley_AI and @MetaAI. A Thread.

Dhruv Batra (@dhruvbatradb) 's Twitter Profile Photo

Robots are going to operate in human environments and need to re-plan in their presence. This is one of the last projects I supported during my time at FAIR and combines many ingredients close to my heart — large-scale simulation, sim2real transfer, human-AI coordination via

Xavier Puig @ ICLR (@xavierpuigf) 's Twitter Profile Photo

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

Meta (@meta) 's Twitter Profile Photo

Chores? No problem. Understanding multiple languages? Easy. Spatial awareness? Simple. Our fundamental AI research team is working on some fun things—watch this space for more.

AI at Meta (@aiatmeta) 's Twitter Profile Photo

By sharing some of the insights and challenges in developing the Meta PARTNR demo, we hope to contribute to the development of the next wave of innovation in human-robot collaboration. Research paper ➡️ go.fb.me/prlg14  Dataset and code ➡️ go.fb.me/k9dzc0

Roozbeh Mottaghi (@roozbehmottaghi) 's Twitter Profile Photo

- A novel method for training agents in scenarios where collecting human demonstrations or reward engineering is hard/infeasible. - The first demonstration that MLLMs can be adapted as VLA agents for embodied tasks using synthetic rewards with online RL.

Yann LeCun (@ylecun) 's Twitter Profile Photo

Rob Fergus is the new head of Meta-FAIR! FAIR is refocusing on Advanced Machine Intelligence: what others would call human-level AI or AGI. linkedin.com/posts/rob-ferg…

Yiming Wang (@yimingwang107) 's Twitter Profile Photo

ICRA just wrapped up, next up: #IROS2025 🚀🚀 Don’t miss our upcoming workshop on human-aware embodied AI IROS 2025 with an amazing line-up of speakers. 📰Consider to submit your works if on relevant topics! 📢Stay tuned for further updates! #EmbodiedAI #Workshops #Call4papers

ICRA just wrapped up, next up: #IROS2025 🚀🚀

Don’t miss our upcoming workshop on human-aware embodied AI <a href="/IROS2025/">IROS 2025</a> with an amazing line-up of speakers.

đź“°Consider to submit your works if on relevant topics!
📢Stay tuned for further updates!
#EmbodiedAI #Workshops #Call4papers
Kwan-Yee Lin (@ky_lin0305) 's Twitter Profile Photo

🚀Join our #CVPR2025 2nd POETs Workshop --Embodied "Humans": Symbiotic Intelligence Between Virtual Humans and Humanoid Robots We have super cool live demo sessions, and awesome lineup of speakers Unitree Gerard Pons-Moll, Deepak Pathak, Karen Liu, Chelsea Finn Shunsuke Saito

🚀Join our #CVPR2025  2nd POETs Workshop --Embodied "Humans": Symbiotic Intelligence Between Virtual Humans and Humanoid Robots

We have super cool live demo sessions, and awesome lineup of speakers <a href="/UnitreeRobotics/">Unitree</a> <a href="/GerardPonsMoll1/">Gerard Pons-Moll</a>, <a href="/pathak2206/">Deepak Pathak</a>, Karen Liu, <a href="/chelseabfinn/">Chelsea Finn</a> <a href="/psyth91/">Shunsuke Saito</a>
Xavier Puig @ ICLR (@xavierpuigf) 's Twitter Profile Photo

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

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