2 papers
cs.LG2026
What Will Post-Training Fix? Per-Problem Gains Are Shared Across Independent RL Runs, and Existing Checkpoints Predict Them Better Than A Priori Signals
Xiaoxian Duan
Data selection, curricula and the evaluation of post-training recipes all assume that we can tell, before training, which problems a model will improve on. We test this assumption…
cs.AI2026
VeriGeo: Controllable Geometry Question Generation with Numerical and Analytical Verification
Xiaoxian Duan, Zequn Liu, Yingce Xia
Geometry problem generation is useful for AI-assisted education and multimodal mathematical reasoning, but reliable synthesis remains difficult because the problem statement, diagr…