← back to paper

Review history

arxiv: 2607.19033 · 2 revisions

Content is What Remains: Invariant Speech Tokenization from Parallel Utterances

1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
   119531 ms 10656 in 13763 out 2026-08-15T15:31:42.935026+00:00
2. 2026-08-01 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 6.0
   210209 ms 10610 in 21284 out 2026-08-01T13:39:00.968027+00:00