← back to paper

Review history

arxiv: 2602.22918 · 2 revisions

Where Vision Becomes Text: Locating the OCR Routing Bottleneck in Vision-Language Models

1. 2026-05-21 UNVERDICTED LOW v0.9.0 novelty 6.0
   53690 ms 5742 in 1214 out 2026-05-21T12:36:33.812425+00:00
2. 2026-05-15 UNVERDICTED LOW v0.9.0 novelty 7.0
   24333 ms 5509 in 1149 out 2026-05-15T18:48:50.193091+00:00