"induction heads" Papers

6 papers found

Filters:induction headsClear all

Conference

AAAI 2025 (3,028)COLM 2025 (418)CVPR 2025 (2,873)ICCV 2025 (2,701)ICLR 2025 (3,827)ICML 2025 (3,340)ISMAR 2025 (229)NEURIPS 2025 (5,858)AAAI 2024 (2,289)CVPR 2024 (2,716)ECCV 2024 (2,387)ICLR 2024 (2,297)ICML 2024 (2,635)

Paper Type

poster (24,624)paper (8,558)oral (1,594)spotlight (1,421)highlight (975)

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

Selective induction Heads: How Transformers Select Causal Structures in Context

Francesco D'Angelo, francesco croce, Nicolas Flammarion

ICLR 2025arXiv:2509.08184
6
citations

The Dual-Route Model of Induction

Sheridan Feucht, Eric Todd, Byron C Wallace et al.

COLM 2025paperarXiv:2504.03022
15
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
1
citations

Better & Faster Large Language Models via Multi-token Prediction

Fabian Gloeckle, Badr Youbi Idrissi, Baptiste Roziere et al.

ICML 2024arXiv:2404.19737
232
citations

How Transformers Learn Causal Structure with Gradient Descent

Eshaan Nichani, Alex Damian, Jason Lee

ICML 2024arXiv:2402.14735
102
citations