← back
arXivZhenglin Wan, Jingxuan Wu, Xingrui Yu, Chubin Zhang, Mingcong Lei, Bo An, Ivor W. Tsang, Yang YouTue, May 26, 2026, 7:38 AM PDT
score 16.4

Robot learning from videos without live expert feedback

Original: Adversarial Dual On-Policy Distillation from Expressive Flow-based Teacher

Source: arxiv.org

Writing ELI5 summary…