🚀 We had a fantastic time at 𝗖𝗼𝗥𝗟 𝟮𝟬𝟮𝟱 (Seoul)—presenting our paper 𝗘𝗻𝗱𝗼𝗩𝗟𝗔: 𝗗𝘂𝗮𝗹-𝗣𝗵𝗮𝘀𝗲 𝗩𝗶𝘀𝗶𝗼𝗻-𝗟𝗮𝗻𝗴𝘂𝗮𝗴𝗲-𝗔𝗰𝘁𝗶𝗼𝗻 𝗳𝗼𝗿 𝗣𝗿𝗲𝗰𝗶𝘀𝗲 𝗔𝘂𝘁𝗼𝗻𝗼𝗺𝗼𝘂𝘀 𝗧𝗿𝗮𝗰𝗸𝗶𝗻𝗴 𝗶𝗻 𝗘𝗻𝗱𝗼𝘀𝗰𝗼𝗽𝘆 and catching up with friends in the robot-learning community.

The work couples a VLM backbone with a dual-phase training recipe (SFT → RFT) to turn language prompts into robust tracking and motor commands for a continuum endoscope.

A highlight was a meeting with Prof. Ken Goldberg—especially meaningful since Prof. Ren previously served as a postdoc at UC Berkeley, keeping our CUHK↔︎UCB connection strong.

🤝 Huge thanks to collaborators and everyone who stopped by the poster!

Authors: Chi Kit Ng*, Long Bai*, Guankun Wang*, Yupeng Wang, Huxin Gao, Kun Yuan, Chenhan Jin, Tieyong Zeng, Hongliang Ren
Affiliations: CUHK, TUM