Commit Graph

3 Commits

Author SHA1 Message Date
8x54zj-m
a0e8501d11 Add independent DreamWaQ stair capability benchmark 2026-07-22 16:31:09 +08:00
8x54zj-m
3648551043 Backup DreamWaQ rslrl stability fixes 2026-07-22 02:17:01 +08:00
8x54zj-m
3038aa7ac7 fix: critic called once (was 3x), adaptive KL schedule restored, upgrade 3m 2026-07-01 15:05:50 +08:00