Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Denser Better: Limits of On-Policy Self-Distillation for Continual Post-Training
Meng Wang, Haohan Zhao, Wenzhuo Liu +7
Continual post-training enables foundation models to acquire new knowledge while preserving existing capabilities. Recent work suggests that on-policy learning can mitigate forgett…
cs.LG2025
Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training
Song Lai, Haohan Zhao, Rong Feng +9
Continual post-training (CPT) is a popular and effective technique for adapting foundation models like multimodal large language models to ever-evolving downstream tasks. While exi…