作者位次 #9/9ICLR 2026Poster· Applications / Everything Else
Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction
Yusong Wu · Stephen Brade · Teng Ma · Tia-Jane Fowler · Enning Yang · Berker Banar · Aaron Courville · Natasha Jaques · Anna Huang