← back to paper

Review history

arxiv: 2605.07333 · 2 revisions

Beyond Linear Attention: Softmax Transformers Implement In-Context Reinforcement Learning

1. 2026-05-20 UNVERDICTED LOW v0.9.0 novelty 8.0
   41138 ms 5725 in 1320 out 2026-05-20T23:21:50.884774+00:00
2. 2026-05-11 UNVERDICTED LOW v0.9.0 novelty 7.0
   33517 ms 5494 in 1371 out 2026-05-11T01:09:34.720802+00:00