Announcement_23

🔔 Check out our two papers accepted at the Conference on Robot Learning (CoRL 2026), Austin, Texas US 🇺🇸:

• (i) PAINT — a training-free method for asynchronous execution via Initial Noise Selection with backward Euler inversion
• (ii) PGPG — an unsupervised preference alignment framework for generative control policies without human annotations or manual reward functions, via ordered coverage alignment relative to a few expert demonstrations

Congratulations to the team! 🎉