Skip to content
conftrace_

on-policy distillation

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

cold-start alignment (1) reasoning transfer (1) group relative policy optimization (1) vision-language model (1) reinforcement learning (1)

Papers

VOLD: Reasoning Transfer from LLMs to Vision-Language Models via On-Policy Distillation CVPR 2026