← back to paper
Review history
arxiv:
2608.03294
· 2 revisions
Provably Learning Multi-Head Attention with Queries
-
2026-08-10
ACCEPT
MODERATE
v1.4.0-alltime-deepseek-medium
novelty 7.0
202425 ms
41461 in
19810 out
2026-08-10T04:27:08.022460+00:00
-
2026-08-05
ACCEPT
MODERATE
v1.4.0-daily-deepseek-medium
novelty 8.0
338298 ms
41434 in
30302 out
2026-08-05T21:34:21.485070+00:00