Loading activity…
@runchu_tian
UNC PhD @unc_ai_group advised by @mohitban47 | Prev UIUC MS @siebelschool advised by @JiaweiHan | THU Undergrad @TsinghuaNLP advised by @zibuyu9
AI
MiRL’s researchers say training starts where recurring errors occur, rewarding runs only if they pass tests and avoid the error.
