Edit, Don't Imitate: Minimal-Edit On-Policy Distillation for Multimodal Reasoning
This work proposes minimal-edit corrective on-policy distillation, a method that preserves on-policy supervision while avoiding full-response imitation, and improves perception-oriented performance, particularly low-level geometric perception, and transfers to external mathematics and perception benchmarks.
Wen Ye, Ai-Lin Deng, Zi-Rui Wang et al.
· 0 citations