← back to paper

Review history

arxiv: 2605.21854 · 2 revisions

CrossVLA: Cross-Paradigm Post-Training and Inference Optimization for Vision-Language-Action Models

1. 2026-06-30 UNVERDICTED LOW v0.9.1-grok novelty 7.0
   53550 ms 5876 in 1415 out 2026-06-30T17:45:28.189157+00:00
2. 2026-05-22 CONDITIONAL LOW v0.9.0 novelty 7.0
   43971 ms 5876 in 1562 out 2026-05-22T08:04:38.850127+00:00