Anton Korznikov

AntonKorznikov

AI & ML interests

None yet

Recent Activity

upvoted a paper 10 days ago

E-MoE: Enhanced Mixture-of-Experts for Non-Factorized Diffusion Language Models

authored a paper 17 days ago

The Rogue Scalpel: Activation Steering Compromises LLM Safety

upvoted a paper 17 days ago

Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs

View all activity

Organizations

None yet

AntonKorznikov 's datasets 1

AntonKorznikov/feature_stories

Viewer • Updated Jul 15 • 1.04M • 188 • 2