← back to paper

Review history

arxiv: 2602.04872 · 2 revisions

Multi-layer Cross-attention is Provably Optimal for Multi-modal In-context Learning

1. 2026-05-21 UNVERDICTED LOW v0.9.0 novelty 8.0
   50405 ms 5722 in 1391 out 2026-05-21T13:33:31.044248+00:00
2. 2026-05-16 UNVERDICTED LOW v0.9.0 novelty 6.0
   32457 ms 5491 in 1142 out 2026-05-16T06:36:47.408720+00:00