← back to paper

Review history

arxiv: 2507.19437 · 2 revisions

Observations Meet Actions: Learning Control-Sufficient Representations for Robust Policy Generalization

1. 2026-08-15 REJECT MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
   228271 ms 27165 in 24521 out 2026-08-15T17:54:31.095094+00:00
2. 2026-08-06 REJECT MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
   241489 ms 27481 in 23262 out 2026-08-06T14:19:41.967666+00:00