works on
benchmark 1evaluation metrics 1evolving contexts 1keyframe conditioning 1large language models 1multimodal models 1on-policy distillation 1open-ended tasks 1reverse kl 1video generation 1

From the 2 of 18 linked papers with an AI index.

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

Flux-OPD: On-Policy Distillation with Evolving Contexts

Yuran Wang, Zekun Wang, Bohan Zeng +10

The paper introduces Flux-OPD, a method for training large language models by distilling knowledge from teachers while using evolving contexts as supervision, and stabilizes the pr…