# CoRe-MoE: Compact Reusable MoE for Continual Multimodal Instruction Tuning

arXiv: https://arxiv.org/abs/2608.27867 · HTML: https://mlsanity.com/paper/2608.27867/

## 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 21 of its 29 references that are in the map.
- First posted on arXiv 28 Aug 2026.

## Placed in

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

## Builds on (most cited first, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [VizWiz Grand Challenge: Answering Visual Questions from Blind People](https://mlsanity.com/paper/1802.08218/) (2018)
- [IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning](https://mlsanity.com/paper/2110.13214/) (2021)
- [CLEVR-Math: A Dataset for Compositional Language, Visual and Mathematical Reasoning](https://mlsanity.com/paper/2208.05358/) (2022)
- [No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces](https://mlsanity.com/paper/2502.04959/) (2025)
- [Continual Instruction Tuning for Large Multimodal Models](https://mlsanity.com/paper/2311.16206/) (2023)
- [SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuning](https://mlsanity.com/paper/2505.02486/) (2025)
- [HiDe-LLaVA: Hierarchical Decoupling for Continual Instruction Tuning of Multimodal Large Language Model](https://mlsanity.com/paper/2503.12941/) (2025)
- [ModalPrompt: Towards Efficient Multimodal Continual Instruction Tuning with Dual-Modality Guided Prompt](https://mlsanity.com/paper/2410.05849/) (2024)
- [Accurate and Efficient Low-Rank Model Merging in Core Space](https://mlsanity.com/paper/2509.17786/) (2025)
- [KeepLoRA: Continual Learning with Residual Gradient Adaptation](https://mlsanity.com/paper/2601.19659/) (2026)
- [Continual Learning for Generative AI: From LLMs to MLLMs and Beyond](https://mlsanity.com/paper/2506.13045/) (2025)
- [DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-Experts](https://mlsanity.com/paper/2506.09351/) (2025)

## Abstract (arXiv)

Continual multimodal instruction tuning requires multimodal large language models to acquire new task abilities sequentially while preserving previously learned knowledge. LoRA-MoE provides a promising solution by introducing expert-based capacity, but repeatedly learning and maintaining full LoRA experts leads to substantial parameter overhead. This raises a natural question: is full expert expansion necessary for every new task? To answer it, we analyze the SVD of task-specific LoRA updates and observe substantial overlap in their input- and output-side LoRA direction subspaces, with task-specific adaptation largely captured by lightweight coordinates over these subspaces. Motivated by this observation, we propose CoRe-MoE, a Compact Reusable MoE framework for parameter-efficient continual multimodal instruction tuning. CoRe-MoE extracts reusable input- and output-side direction bases from an initial expert bank, and for subsequent tasks trains only compact coordinate experts together with task-specific low-rank routers. Experiments on two representative MLLMs show that CoRe-MoE improves final average performance over the strongest competing baseline by up to 5.90 points, while using less than 1% of the trainable parameters required by sequential LoRA for later tasks. The code is publicly available at https://github.com/runzezz/CoRe-MoE.