作者位次 #5/10ICML 2026Poster
Annotations Mitigate Post-Training Mode Collapse
Jacob Mitchell Springer · Madhu Advani · Lukas Aichberger · Arwen Bradley · Eran Malach · Omid Saremi · Sinead Williamson · Preetum Nakkiran · Etai Littwin · Aditi Raghunathan
强化学习与后训练OpenReview