OPD-Aha: From Linguistic Momentum to Visual Reflection in Multimodal On-Policy Distillation
OPD-Aha is introduced, which reconstructs the distillation target directly from this isolated visual preference rather than relying on the fragile teacher-student discrepancy, yielding broad and consistent improvements across diverse fine-grained perception and complex multimodal reasoning benchmarks.
Chen-Hao Qiu, Da-Wei Li, Ye-Chao Zhang et al.
· 0 citations