α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Michael Gastpar
Michael Gastpar
4
papers
42
total citations
papers (4)
Attention with Markov: A Curious Case of Single-layer Transformers
ICLR 2025
arXiv
39
citations
Leveraging Sparsity for Sample-Efficient Preference Learning: A Theoretical Perspective
ICML 2025
arXiv
2
citations
What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains
NEURIPS 2025
arXiv
1
citations
Which Algorithms Have Tight Generalization Bounds?
NEURIPS 2025
arXiv
0
citations