α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Daniil Gavrilov
Daniil Gavrilov
1
Affiliations
Affiliations
Tinkoff Research
5
papers
80
total citations
papers (5)
Learn Your Reference Model for Real Good Alignment
ICLR 2025
arXiv
50
citations
Mechanistic Permutability: Match Features Across Layers
ICLR 2025
arXiv
14
citations
PALBERT: Teaching ALBERT to Ponder
NEURIPS 2022
arXiv
9
citations
Analyze Feature Flow to Enhance Interpretation and Steering in Language Models
ICML 2025
arXiv
6
citations
Teach Old SAEs New Domain Tricks with Boosting
COLM 2025
arXiv
1
citations