← back to paper

Review history

arxiv: 2608.06792 · 2 revisions

Progressive Alignment of Recommender Foundation Model through Multi-Phase Post-Training

1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
   149041 ms 3391 in 4108 out 2026-08-15T14:29:57.865285+00:00
2. 2026-08-10 CONDITIONAL MODERATE v1.4.0-daily-deepseek-medium novelty 5.0
   154509 ms 11434 in 17444 out 2026-08-10T20:45:42.096470+00:00