Excited to share that the full programme for the 2025 UCL NeuroAI Annual Conference is now live! 🧠🤖 @ucl-neuroai.bsky.social

Spaces are limited, so register soon:
lnkd.in/ehiKrSaf

Full programme here:
lnkd.in/e8cV3mAZ

4. Pre-training ICL models on linear regression tasks changed this outcome. These models then succeeded at transitive inference and didn't rely on induction circuits.

3. Mechanistic analysis revealed why: ICL models developed induction circuits - specialized attention patterns that implement match-and-copy operations rather than encoding hierarchical relationships.

2. In-context learning models failed to generalize transitively. Despite perfect performance on training pairs, they couldn't infer relationships between non-adjacent items.

1. In-weights learning model developed transitive inference despite only seeing adjacent pairs during training. They also showed behavioral patterns consistent with human and animal performance on these tasks.