https://hackerpaper.kaipfister.de/p/2602.20092/Collected HN comments and submissions linking this paper.enSun, 08 Nov 2026 05:37:00 GMThttps://news.ycombinator.com/item?id=50405190urn:hackerpapers:mention:2602.20092:50405190Sat, 07 Nov 2026 15:08:30 GMT<p>You can look at the CFP for the most recent BabyLM https://arxiv.org/html/2602.20092v2 : &quot;This year, we have merged the Multimodal and Interaction tracks into the Strict and Strict-small tracks. This is for two primary reasons: Firstly, there were insufficient submissions to warrant standalone tracks. Secondly, none of the submissions in the Interaction track outperformed models submitted to the Strict track, and *none of the submissions from Multimodal outperformed our baselines*. We will still allow participants to use multimodal data or interactive training procedures if they choose, but…</p><p><a href="https://hackerpaper.kaipfister.de/p/2602.20092/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL