M
MODELYST
AI research terminal
●
live · verified Jul 13
Search
⌘K
Frontier
Models
Compare
Leaderboards
Changes
Media
Benchmarks
Papers
Pick
Discover
Ask
Frontier
Models
Compare
Leaderboards
Changes
Media
Benchmarks
Papers
Pick
Discover
Ask
People
/
Christoph H. Lampert
PPL
Christoph H. Lampert
☆ Watch
Papers (3)
From Privacy to Generalization: Linear Max-Information Bounds for DP-SGD
Beyond Square Roots: Explicit Memory-Efficient Factorization for Multi-Epoch Private Learning
Sink vs. diagonal patterns as mechanisms for attention switch and oversmoothing prevention