arXiv2
Search
Dark
/ Date
/ Name
Aa
W
/ Date
/ Name
"au:"Jason D. Lee"" — arXiv2 Search
Showing 1–2 of 2 results
/ Date
/ Name
Aug 10, 2025
What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains
Jul 5, 2023
Scaling In-Context Demonstrations with Structured Attention