OPLD: On-Policy Latent Distillation for Multimodal Reasoning 文章

ArXiv CS.CV2026-07-31PAPERen作者: Shoutai Zhu, Tianyang Xu, Bin Sun, Mingyuan Xu, Yu Liu, Qinzhen Guo

OPLD: On-Policy Latent Distillation for Multimodal Reasoning · 相关公司

A
ATHCOMPANY