← back to paper

Review history

arxiv: 2507.18433 · 2 revisions

DiagR1: A Vision-Language Model Trained via Reinforcement Learning for Digestive Pathology Diagnosis

1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
   134031 ms 15380 in 14699 out 2026-08-15T18:12:10.254594+00:00
2. 2026-08-06 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 5.0
   149611 ms 15399 in 14939 out 2026-08-06T14:32:46.420277+00:00