Tony Dong

[Tony Dong @TonyDong050519]

Thank you William Baron and @chen_hongyi_ for your help, and @UksangYoo, @jeff_ichnowski, and Weiming Zhi for advising, as well as the support from @CMU_Robotics and CMU Office of Undergraduate Research and Scholar Development (Summer Undergraduate Research Fellowship).

🧵[8/8]

[Tony Dong @TonyDong050519]

Can robot learn manipulation skill with one object and perform it on a completely different one without any new demonstrations?

Excited to introduce SemAnCorr, a framework for dense correspondence and manipulation skill transfer across diverse objects.

https://t.co/p2cLar5vLq

[Tony Dong @TonyDong050519]

Together, SemAnCorr provides a manipulation-oriented representation that bridges visual demonstrations and robot actions, enabling reliable manipulation skill transfer.

Feedback and questions are welcomed!
Website: https://t.co/p2cLar5vLq
Arxiv: https://t.co/dfHGuGjCka

🧵[7/8]