S-OPD is a simple multimodal on-policy distillation framework that explicitly strengthens student perceptual learning through two objectives: Teacher-calibrated Policy Contrast separates student policies under original and masked images with teacher-based token-level gating, strengthening the student's reliance on visu...
Unified large multimodal models, capable of both understanding and generation, face significant challenges during continued training without access to original pre-training data. This post-pre-training task, critical for enhancing core foundational capabilities, is plagued by catastrophic forgetting and compounded by t...
Yue Duan, Yi-Xuan Shi, Zheng Yuan et al.· Proceedings of the 34th ACM...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.