← back to paper

Review history

arxiv: 2606.02564 · 2 revisions

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization

1. 2026-06-30 UNVERDICTED LOW v0.9.1-grok novelty 7.0
   45146 ms 5840 in 1375 out 2026-06-30T10:35:52.409054+00:00
2. 2026-06-28 UNVERDICTED LOW v0.9.1-grok novelty 7.0
   23051 ms 5840 in 1234 out 2026-06-28T15:24:31.457851+00:00