Aryabhata: An exam-focused language model for JEE Math Paper โข 2508.08665 โข Published 5 days ago โข 16
RLPR: Extrapolating RLVR to General Domains without Verifiers Paper โข 2506.18254 โข Published Jun 23 โข 32 โข 8
RLPR: Extrapolating RLVR to General Domains without Verifiers Paper โข 2506.18254 โข Published Jun 23 โข 32 โข 8