retention-aware-policy-optimization

Tag

Cards List
#retention-aware-policy-optimization

Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning

Hugging Face Daily Papers · 2026-05-10 Cached

This paper introduces Retention-aware Policy Optimization (RaPO) to mitigate catastrophic forgetting in visual continual learning using reinforcement fine-tuning. RaPO uses trajectory-level reward shaping and cross-task advantage normalization to close the gap between reinforcement and supervised fine-tuning in class- and domain-incremental learning.

0 favorites 0 likes
← Back to home

Submit Feedback