Book
Open access
Nov 2026
OP-CL: On-Policy Guided Continual Post-training for Multimodal Large Language Models
OP-CL is proposed, a two-stage on-policy guided framework for continual post-training in MLLMs that achieves a better balance between new task adaptation and old task retention than representative SFT- and RL-based baselines.
Xing-Yue Guo, Jia-He Wu, Xu-Hui Sui et al.
· Proceedings of the 34th ACM... · 0 citations