Yang Yue (@YYang9923) profile picture

CS PhD @ UNC Chapel Hill ๐Ÿค– | Robot Learning, Long-Horizon Manipulation, Imitation & RL, Real-to-Sim | Prev. Meta Reality Labs, MERL | MSCS @ Georgia Tech

Chapel Hill
Joined November 2022
Photo by Yang Yue (@YYang9923)
Landed in Austin for #CoRL2026! Can't wait to see old friends and meet new ones. Find me Thu (11/12) morning at two workshop posters: โœ‹ GNR (done at Meta Reality Labs) @ Scaling H2R ๐ŸŽ› EGR (done at MERL) @ Beneath the Policy DMs open, always up for coffee! Details ๐Ÿ‘‡
2
21
419
๐Ÿฆพ Scaling dexterous robot demonstrations from human data! ๐Ÿš€ Excited to share Generative Neural Retargeting (GNR) from Meta Reality Labs! ๐Ÿ”ฅ 223k robot demos across 3.3k objects, with dense contact force labels! ๐ŸŒ yy-gx.github.io/GNR/ ๐Ÿ“„ arxiv.org/abs/2610.12440
2
5
94
4,564
๐Ÿ“– Why Generative? GNR learns a distribution of physically feasible robot trajectories, enabling test-time sampling to explore multiple solutions and improve retargeting success. Huge thanks to our amazing team at Meta Reality Labs Research! ๐Ÿ™Œ @DechenGao @ewhitmire
1
127
๐Ÿค– GNR scales data along two axes: ๐ŸŒ Diversity: Large-scale, contact-rich demonstrations generated with high-fidelity physics simulation using SuperDex (projectsuperdex.com/). ๐ŸŽฏ Difficulty: High-precision, long-horizon manipulation, including NIST assembly and ShapeFilter.
2
221