When Good Verifiers Go Bad: Silent Negative Transfer in Verifier-Guided VLM Training.

arXiv:2606.14629v3 Announce Type: replace-cross Abstract: Verifier reliability is not portable across tasks. A verifier-guided self-DPO pipeline with genuine held-out gains on MathVista (+9.6 points on self-training data, +8.0 held out) can be harmful on MMMU.