mlsanityData to 14 Oct 2026

Multimodal Continual Learning with MLLMs from Multi-scenario Perspectives

arXiv 2511.18507 ↗First posted 23 Nov 2025cs.CV cs.AIcited by 4

On the map: Multimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP

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.

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.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026CRL-VLA: Continual Vision-Language-Action Learningcited by 7
  2. 2026Latent Noise Mask for Reducing Visual Redundancy in Multimodal Large Language Modelscited by 0
  3. 2026Miles: Metric Learning with Expandable Subspace for Pre-Trained Model-Based Class-Incremental Learningcited by 0
  4. 2026Mitigating Visual Degradation in MLLMs via Spatial-Spectral Visual Anchor Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025MLLM-CL: Continual Learning for Multimodal Large Language Models
  2. 2025Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting
  3. 2025When Continue Learning Meets Multimodal Large Language Model: A Survey
  4. 2024Multi-Stage Knowledge Integration of Vision-Language Models for Continual Learning
  5. 2024Improving Multimodal Large Language Models Using Continual Learning
  6. 2026Black-Box Continual Learning for Vision-Language Models
  7. 2026Is Our Benchmark Enough? An Analysis of Continual Learning for MLLMs
  8. 2023Continual Instruction Tuning for Large Multimodal Models