Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Yuyang, Hong, Qiuhe, Huang, Linlan, Gomez-Villa, Alexandra, Goswami, Dipam, Liu, Xialei, van de Weijer, Joost, Tian, Yonghong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911689526476800
author Liu, Yuyang
Hong, Qiuhe
Huang, Linlan
Gomez-Villa, Alexandra
Goswami, Dipam
Liu, Xialei
van de Weijer, Joost
Tian, Yonghong
author_facet Liu, Yuyang
Hong, Qiuhe
Huang, Linlan
Gomez-Villa, Alexandra
Goswami, Dipam
Liu, Xialei
van de Weijer, Joost
Tian, Yonghong
contents Vision-language models (VLMs) and the recent surge of Multimodal Large Language Models (MLLMs) have revolutionized artificial intelligence with unprecedented cross-modal alignment and zero-shot generalization. However, enabling them to learn continually from non-stationary data remains a major challenge, as their cross-modal alignment and generalization capabilities are particularly vulnerable to catastrophic forgetting. Unlike traditional unimodal continual learning (CL), VLMs face unique challenges such as cross-modal feature drift, parameter interference due to shared architectures, and zero-shot capability erosion. Furthermore, generative MLLMs exhibit a unique ``alignment tax,'' where catastrophic forgetting manifests not merely as factual amnesia, but as a systemic collapse of deep Chain-of-Thought (CoT) reasoning. This survey presents the first comprehensive, diagnostic review bridging continual learning for both predictive VLMs and generative MLLMs. We systematically deconstruct the aforementioned failure modes and propose a challenge-driven taxonomy comprising four core paradigms: (1) Multi-Modal Replay Strategies addressing explicit and implicit memory drift; (2) Cross-Modal Regularization enforcing topological and geometric alignment; (3) Parameter-Efficient Adaptation} utilizing dynamic routing and subspace projections; and the emerging (4) Model Fusion and Decoupling paradigms. We critically analyze the evolution of evaluation protocols, highlighting the essential shift toward dual-track benchmarks (Domain vs. Ability CL) and micro-diagnostic CoT evaluations. Finally, we chart a roadmap for future research, emphasizing compositional zero-shot learning, embodied AI with sensor fusion, and autonomous agentic ecosystems. All resources are available at: https://github.com/YuyangSunshine/Awesome-Continual-learning-of-Vision-Language-Models.
format Preprint
id arxiv_https___arxiv_org_abs_2508_04227
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting
Liu, Yuyang
Hong, Qiuhe
Huang, Linlan
Gomez-Villa, Alexandra
Goswami, Dipam
Liu, Xialei
van de Weijer, Joost
Tian, Yonghong
Computer Vision and Pattern Recognition
Machine Learning
Vision-language models (VLMs) and the recent surge of Multimodal Large Language Models (MLLMs) have revolutionized artificial intelligence with unprecedented cross-modal alignment and zero-shot generalization. However, enabling them to learn continually from non-stationary data remains a major challenge, as their cross-modal alignment and generalization capabilities are particularly vulnerable to catastrophic forgetting. Unlike traditional unimodal continual learning (CL), VLMs face unique challenges such as cross-modal feature drift, parameter interference due to shared architectures, and zero-shot capability erosion. Furthermore, generative MLLMs exhibit a unique ``alignment tax,'' where catastrophic forgetting manifests not merely as factual amnesia, but as a systemic collapse of deep Chain-of-Thought (CoT) reasoning. This survey presents the first comprehensive, diagnostic review bridging continual learning for both predictive VLMs and generative MLLMs. We systematically deconstruct the aforementioned failure modes and propose a challenge-driven taxonomy comprising four core paradigms: (1) Multi-Modal Replay Strategies addressing explicit and implicit memory drift; (2) Cross-Modal Regularization enforcing topological and geometric alignment; (3) Parameter-Efficient Adaptation} utilizing dynamic routing and subspace projections; and the emerging (4) Model Fusion and Decoupling paradigms. We critically analyze the evolution of evaluation protocols, highlighting the essential shift toward dual-track benchmarks (Domain vs. Ability CL) and micro-diagnostic CoT evaluations. Finally, we chart a roadmap for future research, emphasizing compositional zero-shot learning, embodied AI with sensor fusion, and autonomous agentic ecosystems. All resources are available at: https://github.com/YuyangSunshine/Awesome-Continual-learning-of-Vision-Language-Models.
title Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2508.04227