arxiv:2509.24510
Patrik Wolf
patrikwolf
ยท
AI & ML interests
Test-time training, preference learning, alignment, theory
Recent Activity
liked
a dataset
13 days ago
proj-persona/PersonaHub
upvoted
a
paper
about 1 month ago
Reasoning with Sampling: Your Base Model is Smarter Than You Think
upvoted
a
paper
about 2 months ago
Language Models are Injective and Hence Invertible
Organizations
