← back to paper

Review history

arxiv: 2607.04683 · 3 revisions

Failing to See or Failing to Know? Attributing Errors in Vision-Language Models

1. 2026-08-04 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 6.0
   145494 ms 26320 in 16403 out 2026-08-04T04:27:20.325947+00:00
2. 2026-07-13 CONDITIONAL MODERATE v1.1.0-grok45 novelty 6.0
   32864 ms 30973 in 3711 out 2026-07-13T06:56:45.837972+00:00
3. 2026-07-11 CONDITIONAL MODERATE v1.1.0-grok45 novelty 6.5
   24781 ms 30992 in 3341 out 2026-07-11T15:13:42.885507+00:00