# Multimodal Continual Learning with MLLMs from Multi-scenario Perspectives

arXiv: https://arxiv.org/abs/2511.18507 · HTML: https://mlsanity.com/paper/2511.18507/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models.
- First posted on arXiv 23 Nov 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Prompt learning and adaptation of CLIP](https://mlsanity.com/mllm/prompt-learning-and-adaptation-of-clip/)

## Built on by (most cited first, 4 of 4)

- [CRL-VLA: Continual Vision-Language-Action Learning](https://mlsanity.com/paper/2602.03445/) (2026)
- [Latent Noise Mask for Reducing Visual Redundancy in Multimodal Large Language Models](https://mlsanity.com/paper/2606.30168/) (2026)
- [Miles: Metric Learning with Expandable Subspace for Pre-Trained Model-Based Class-Incremental Learning](https://mlsanity.com/paper/2607.17593/) (2026)
- [Mitigating Visual Degradation in MLLMs via Spatial-Spectral Visual Anchor Learning](https://mlsanity.com/paper/2608.01635/) (2026)

## Abstract (arXiv)

Multimodal large language models (MLLMs) deployed on devices must adapt to continuously changing visual scenarios such as variations in background and perspective, to effectively perform complex visual tasks. To investigate catastrophic forgetting under real-world scenario shifts, we construct a multimodal visual understanding dataset (MSVQA), covering four distinct scenarios and perspectives: high-altitude, underwater, low-altitude, and indoor environments. Furthermore, we propose UNIFIER (mUltimodal coNtInual learning with MLLMs From multi-scenarIo pERspectives), a continual learning (CL) framework designed to address visual discrepancies while learning different scenarios. Compared to existing CL methods, UNIFIER enables knowledge accumulation within the same scenario and mutual enhancement across different scenarios via Vision Representation Expansion (VRE) and Vision Consistency Constraint (VCC). Experimental results show that UNIFIER improves the last-step VQA scores by 2.70%~10.62% and the last-step F1 scores by 3.40%~7.69% compared to the state-of-the-art method, QUAD, in 20-step cross-scenario continual learning tasks. MSVQA dataset is available at https://huggingface.co/datasets/Kaij00/MSVQA.