-
The Path Not Taken: RLVR Provably Learns Off the Principals
Paper • 2511.08567 • Published • 34 -
Reasoning with Sampling: Your Base Model is Smarter Than You Think
Paper • 2510.14901 • Published • 48 -
When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA
Paper • 2510.04849 • Published • 115
Mayssa Hajj Hassan
Mayssa-03
AI & ML interests
None yet
Organizations
None yet