Beyond What Seems Necessary: Hidden Gains from Scaling Training-Time Reasoning Length under Outcome Supervision

Yihao Xue, Allan Zhang, Jianhao Huang, Amit Sahai, Baharan Mirzasoleiman

NeurIPS 2026Under review

20/20 Vision Language Models: A Prescription for Better VLMs through Data Curation Alone

Datology AI

Technical report