← back to paper

Review history

arxiv: 2608.04496 · 2 revisions

DIVE: Dynamic Iterative Visual Evidence Construction for Efficient Vision-Language Models

1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
   131836 ms 25719 in 17015 out 2026-08-15T14:38:44.774992+00:00
2. 2026-08-06 CONDITIONAL MODERATE v1.4.0-daily-deepseek-medium novelty 6.0
   142518 ms 25776 in 13878 out 2026-08-06T23:15:09.471777+00:00