Stone Tao

@Stone_Tao

simulation & research @physical_int

stoneztao.com

Joined January 2013

Pinned
Stone Tao
@Stone_Tao
Jul 31
Just over a month later, I have now joined @physical_int full time! Wrote a bit about why I'm excited to research simulation at Pi stoneztao.substack.com/joining-physic…
Stone Tao
@Stone_Tao
Jun 16
just arrived in SF and excited to begin my research internship at physical intelligence @physical_int working on simulation!
Stone Tao
@Stone_Tao
20h
love that after all these years maniskill is still supporting all kinds of RL research!
Alexandre Brown 🇨🇦
@AlexandreBrown0
Aug 17
I'm at the Reinforcement Learning Conference (RLC) 2026 presenting SegDAC: Visual Generalization in Reinforcement Learning via Dynamic Object Tokens, joint work with @GlenBerseth . SegDAC reasons over objects instead of pixels and uses dynamic object tokens to obtain a robust
Stone Tao
@Stone_Tao
Aug 16
literally getting lunch outside and table next to me is talking about matic and saying it works so well incredible release, looking forward to what you all are up to next!
Mehul
@mehul
Aug 15
Matic Cues live demo!!
Stone Tao
@Stone_Tao
Aug 10
same energy
Alps
@alpaysh
Aug 8
Fortune favors the bald btw
Stone Tao
@Stone_Tao
Jul 23
easy to miss detail and pretty neat: you can just modify the UMI style data collection devices to use different tools
02:09
Generalist
@GeneralistAI
Jul 23
Why create robot intelligence for just one hand, when we could have it learn from many? GEN-1, our latest embodied foundation model, now supports a broad range of end effectors from 5-finger hands, to specialized tools, and everything in between.