# DeLo: Dual Decomposed Low-Rank Experts Collaboration for Continual Missing Modality Learning

arXiv: https://arxiv.org/abs/2603.01632 · HTML: https://mlsanity.com/paper/2603.01632/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 31 of its 50 references that are in the map.
- First posted on arXiv 2 Mar 2026.

## Placed in

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

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence](https://mlsanity.com/paper/1801.10112/) (2018)
- [Overcoming catastrophic forgetting with hard attention to the task](https://mlsanity.com/paper/1801.01423/) (2018)
- [Online Continual Learning with Maximally Interfered Retrieval](https://mlsanity.com/paper/1908.04742/) (2019)
- [Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting](https://mlsanity.com/paper/1904.00310/) (2019)
- [Gated Multimodal Units for Information Fusion](https://mlsanity.com/paper/1702.01992/) (2017)
- [S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning](https://mlsanity.com/paper/2207.12819/) (2022)
- [SMIL: Multimodal Learning with Severely Missing Modality](https://mlsanity.com/paper/2103.05677/) (2021)
- [Co2L: Contrastive Continual Learning](https://mlsanity.com/paper/2106.14413/) (2021)
- [Compacting, Picking and Growing for Unforgetting Continual Learning](https://mlsanity.com/paper/1910.06562/) (2019)
- [InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning](https://mlsanity.com/paper/2404.00228/) (2024)
- [Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalities](https://mlsanity.com/paper/1812.07809/) (2018)
- [Adversarial Continual Learning](https://mlsanity.com/paper/2003.09553/) (2020)
- [Multimodal Prompting with Missing Modalities for Visual Recognition](https://mlsanity.com/paper/2303.03369/) (2023)
- [Continual Learning with Node-Importance based Adaptive Group Sparse Regularization](https://mlsanity.com/paper/2003.13726/) (2020)
- [Towards Good Practices for Missing Modality Robust Action Recognition](https://mlsanity.com/paper/2211.13916/) (2022)
- [Introducing Language Guidance in Prompt-based Continual Learning](https://mlsanity.com/paper/2308.15827/) (2023)
- [Unified Multi-Modal Image Synthesis for Missing Modality Imputation](https://mlsanity.com/paper/2304.05340/) (2023)
- [Multimodal Instruction Tuning with Conditional Mixture of LoRA](https://mlsanity.com/paper/2402.15896/) (2024)
- [Knowledge Bridger: Towards Training-free Missing Modality Completion](https://mlsanity.com/paper/2502.19834/) (2025)
- [Efficient Prompting for Continual Adaptation to Missing Modalities](https://mlsanity.com/paper/2503.00528/) (2025)
- [Reconstruct before Query: Continual Missing Modality Learning with Decomposed Prompt Collaboration](https://mlsanity.com/paper/2403.11373/) (2024)

## Abstract (arXiv)

Adapting Large Multimodal Models (LMMs) to real-world scenarios poses the dual challenges of learning from sequential data streams while handling frequent modality incompleteness, a task known as Continual Missing Modality Learning (CMML). However, existing works on CMML have predominantly relied on prompt tuning, a technique that struggles with this task due to cross-task interference between its learnable prompts in their shared embedding space. A naive application of Low-Rank Adaptation (LoRA) with modality-shared module will also suffer modality interference from competing gradients. To this end, we propose DeLo, the first framework to leverage a novel dual-decomposed low-rank expert architecture for CMML. Specifically, this architecture resolves modality interference through decomposed LoRA expert, dynamically composing LoRA update matrix with rank-one factors from disentangled modality-specific factor pools. Embedded within a task-partitioned framework that structurally prevents catastrophic forgetting, this expert system is supported by two key mechanisms: a Cross-Modal Guided Routing strategy to handle incomplete data and a Task-Key Memory for efficient, task-agnostic inference. Extensive experiments on established CMML benchmarks demonstrate that our method significantly outperforms state-of-the-art approaches. This highlights the value of a principled, architecturally-aware LoRA design for real-world multimodal challenges.