Spotlight "induction heads" Papers
2 papers found
From Shortcut to Induction Head: How Data Diversity Shapes Algorithm Selection in Transformers
Ryotaro Kawata, Yujin Song, Alberto Bietti et al.
NeurIPS 2025spotlightarXiv:2512.18634
1
citations
What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains
Chanakya Ekbote, Ashok Vardhan Makkuva, Marco Bondaschi et al.
NeurIPS 2025spotlightarXiv:2508.07208