Jadelynn Dao retweeted
During long-horizon task planning, a robot must decide what to do, while ensuring each action is geometrically feasible.
To this end, we propose ๐ฝ๐น๐ฎ๐ป๐ป๐ถ๐ป๐ด ๐๐ถ๐๐ต ๐ถ๐ป๐๐ฒ๐ฟ๐น๐ฒ๐ฎ๐๐ฒ๐ฑ ๐๐ถ๐๐ถ๐ผ๐ป-๐น๐ฎ๐ป๐ด๐๐ฎ๐ด๐ฒ ๐๐ต๐ผ๐๐ด๐ต๐๐.
Jadelynn Dao retweeted
๐ค Can VLA models teach themselves the best way to reason?
We introduce R&B-EnCoRe which is a self-improving pretraining cycle for reasoning VLAs to propose and self-discover what embodiment-specific reasoning looks like.
๐ milanganai.github.io/rnb-encโฆ
๐ arxiv.org/pdf/2602.08167
test-time compute [ttc] in robotics isn't free & isn't always worth it. smart allocation of ttc recovers frontier-level planning at a fraction of the cost!
coauthor @milanganai
w/ Yasmina @ajaysridhar0 Mozghan @katielulula Clark Barrett @jiajunwu_cs @chelseabfinn @drmapavone ๐งต โ at Stanford, CA
4/4 we are incredibly excited about this line of work!! feel free to reach out to us ๐
๐ arxiv.org/abs/2606.12402
๐ jadee-dao.github.io/direct/
๐ค jadee-dao.github.io/direct/vโฆ
