paper-with-me

Papers

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

2026-05-10 · Meng Lou, Hanzhong Guo, Linwei Chen, Yizhou Yu arxiv

Recent studies suggest that Reinforcement Fine-Tuning (RFT) is inherently more resilient to catastrophic forgetting than Supervised Fine-Tuning (SFT). However, whether RFT (e.g., GRPO) can effectively overcome forgetting in challenging visual continual learning settings, such as class-incremental learning (CIL) and domain-incremental learning (DIL), remains an open problem. Through a pilot study, we confirm that while RFT consistently outperforms SFT, it still suffers from non-negligible forgetting. We empirically trace this bottleneck to Trajectory-level Drift Agnosticism: among candidate rollouts achieving identical task rewards, the KL divergence from the preceding-task policy varies substantially, which strongly correlates with catastrophic forgetting across sequential tasks. Motivated by this insight, we propose Retention-aware Policy Optimization (RaPO), a simple yet effective RFT method that explicitly mitigates forgetting through trajectory-level reward shaping. Specifically, RaPO comprises two core components: (1) Retention Reward that converts trajectory-level distribution drift into a continuous reward signal, preferentially reinforcing knowledge-preserving rollouts within each group; (2) Cross-Task Advantage Normalization (CTAN), which maintains a persistent exponential moving average of reward statistics across task boundaries to stabilize the optimization progress during continual learning. Leveraging the free-form textual generalization of MLLMs, we comprehensively evaluate RaPO across five visual continual learning settings. Extensive experiments demonstrate that RaPO achieves leading performance, substantially reducing catastrophic forgetting while preserving strong plasticity. To the best of our knowledge, this work represents the first systematic exploration of RFT in visual continual learning, offering insights that we hope will inspire future research.

📄 PDF Abstract BibTeX arXiv:2605.09640

Code (0)

등록된 구현이 없습니다.

Tasks

class-incremental learningContinual Learning

Similar Papers 제목 키워드 기반

Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting

2019-03-31 · Xilai Li, Yingbo Zhou, Tianfu Wu, Richard Socher 외

Addressing catastrophic forgetting is one of the key challenges in continual learning where machine learning systems are trained with sequential or streaming tasks. Despite recent remarkable progress in state-of-the-art …

Continual LearningNeural Architecture Searchparameter estimationPermuted-MNIST

ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think

2025-01-02 · Tao Feng, Wei Li, Didi Zhu, Hangjie Yuan 외

Backpropagation provides a generalized configuration for overcoming catastrophic forgetting. Like, SGD and Adam are commonly used for weight updates in continual learning and continual pre-training. In practice, permissi…

Continual Learning

Overcoming Catastrophic Forgetting by XAI

2022-11-25 · Giang Nguyen

Explaining the behaviors of deep neural networks, usually considered as black boxes, is critical especially when they are now being adopted over diverse aspects of human life. Taking the advantages of interpretable machi…

Continual LearningExplainable Artificial Intelligence (XAI)Interpretable Machine Learning

Overcoming Catastrophic Forgetting in Massively Multilingual Continual Learning

2023-05-25 · Genta Indra Winata, Lingjue Xie, Karthik Radhakrishnan, Shijie Wu 외

Real-life multilingual systems should be able to efficiently incorporate new languages as data distributions fed to the system evolve and shift over time. To do this, systems need to handle the issue of catastrophic forg…

Continual LearningScheduling

Quantum Continual Learning Overcoming Catastrophic Forgetting

2021-08-05 · Wenjie Jiang, Zhide Lu, Dong-Ling Deng

Catastrophic forgetting describes the fact that machine learning models will likely forget the knowledge of previously learned tasks after the learning process of a new one. It is a vital problem in the continual learnin…

BIG-bench Machine LearningContinual LearningIncremental LearningQuantum Machine Learning