Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes
On-policy self-distillation has recently emerged as an effective approach for improving language-model reasoning by supervising students with a frozen or EMA version of themselves that receives privileged information. Its application to multimodal large language models (MLLMs), however, remains largely unexplored. Rece...
Sophia Sirko-Galouchenko, M. Wysoczańska, Andrei Bursuc et al.
· 0 citations