# Multimodal Instruction Tuning with Conditional Mixture of LoRA

arXiv: https://arxiv.org/abs/2402.15896 · HTML: https://mlsanity.com/paper/2402.15896/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 34 of its 48 references that are in the map.
- First posted on arXiv 24 Feb 2024.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks](https://mlsanity.com/paper/1711.02257/) (2017)
- [Multi-Task Learning as Multi-Objective Optimization](https://mlsanity.com/paper/1810.04650/) (2018)
- [End-to-End Multi-Task Learning with Attention](https://mlsanity.com/paper/1803.10704/) (2018)
- [Compacter: Efficient Low-Rank Hypercomplex Adapter Layers](https://mlsanity.com/paper/2106.04647/) (2021)
- [Conflict-Averse Gradient Descent for Multi-task Learning](https://mlsanity.com/paper/2110.14048/) (2021)
- [Multi-Task Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2009.09796/) (2020)
- [Parameter-Efficient Transfer Learning with Diff Pruning](https://mlsanity.com/paper/2012.07463/) (2020)
- [Scene Text Visual Question Answering](https://mlsanity.com/paper/1905.13648/) (2019)
- [Visual Entailment: A Novel Task for Fine-Grained Image Understanding](https://mlsanity.com/paper/1901.06706/) (2019)
- [Multi-Task Learning as a Bargaining Game](https://mlsanity.com/paper/2202.01017/) (2022)
- [LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark](https://mlsanity.com/paper/2306.06687/) (2023)
- [SVIT: Scaling up Visual Instruction Tuning](https://mlsanity.com/paper/2307.04087/) (2023)
- [Attentive Single-Tasking of Multiple Tasks](https://mlsanity.com/paper/1904.08918/) (2019)
- [What Would Elsa Do? Freezing Layers During Transformer Fine-Tuning](https://mlsanity.com/paper/1911.03090/) (2019)

## Built on by (most cited first, 30 of 36)

- [A Survey on LoRA of Large Language Models](https://mlsanity.com/paper/2407.11046/) (2024)
- [MoME: Mixture of Multimodal Experts for Generalist Multimodal Large Language Models](https://mlsanity.com/paper/2407.12709/) (2024)
- [ModalPrompt: Towards Efficient Multimodal Continual Instruction Tuning with Dual-Modality Guided Prompt](https://mlsanity.com/paper/2410.05849/) (2024)
- [Dynamic Mixture of Curriculum LoRA Experts for Continual Multimodal Instruction Tuning](https://mlsanity.com/paper/2506.11672/) (2025)
- [SMoLoRA: Exploring and Defying Dual Catastrophic Forgetting in Continual Visual Instruction Tuning](https://mlsanity.com/paper/2411.13949/) (2024)
- [Plug-and-Play Grounding of Reasoning in Multimodal Large Language Models](https://mlsanity.com/paper/2403.19322/) (2024)
- [M2PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning](https://mlsanity.com/paper/2409.15657/) (2024)
- [Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model](https://mlsanity.com/paper/2503.04543/) (2025)
- [LLMs Can Evolve Continually on Modality for X-Modal Reasoning](https://mlsanity.com/paper/2410.20178/) (2024)
- [LoRASculpt: Sculpting LoRA for Harmonizing General and Specialized Knowledge in Multimodal Large Language Models](https://mlsanity.com/paper/2503.16843/) (2025)
- [UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter-Efficient Fine-Tuning of Large Models](https://mlsanity.com/paper/2505.20154/) (2025)
- [Modality-Specialized Synergizers for Interleaved Vision-Language Generalists](https://mlsanity.com/paper/2407.03604/) (2024)
- [Re-Imagining Multimodal Instruction Tuning: A Representation View](https://mlsanity.com/paper/2503.00723/) (2025)
- [VisNec: Measuring and Leveraging Visual Necessity for Multimodal Instruction Tuning](https://mlsanity.com/paper/2603.01195/) (2026)
- [Advancing Chart Question Answering with Robust Chart Component Recognition](https://mlsanity.com/paper/2407.21038/) (2024)
- [Pisces: An Auto-regressive Foundation Model for Image Understanding and Generation](https://mlsanity.com/paper/2506.10395/) (2025)
- [Large Multimodal Models for Low-Resource Languages: A Survey](https://mlsanity.com/paper/2502.05568/) (2025)
- [A Shared Low-Rank Adaptation Approach to Personalized RLHF](https://mlsanity.com/paper/2503.19201/) (2025)
- [MoRA: Missing Modality Low-Rank Adaptation for Visual Recognition](https://mlsanity.com/paper/2511.06225/) (2025)
- [ThanoRA: Task Heterogeneity-Aware Multi-Task Low-Rank Adaptation](https://mlsanity.com/paper/2505.18640/) (2025)
- [GLAD: Generalizable Tuning for Vision-Language Models](https://mlsanity.com/paper/2507.13089/) (2025)
- [AdaptGCD: Multi-Expert Adapter Tuning for Generalized Category Discovery](https://mlsanity.com/paper/2410.21705/) (2024)
- [Error-driven Data-efficient Large Multimodal Model Tuning](https://mlsanity.com/paper/2412.15652/) (2024)
- [Bridging Human Oversight and Black-box Driver Assistance: Vision-Language Models for Predictive Alerting in Lane Keeping Assist Systems](https://mlsanity.com/paper/2505.11535/) (2025)
- [Mixture-of-Experts for Personalized and Semantic-Aware Next Location Prediction](https://mlsanity.com/paper/2505.24597/) (2025)
- [MINT: Multimodal Instruction Tuning with Multimodal Interaction Grouping](https://mlsanity.com/paper/2506.02308/) (2025)
- [MNAFT: modality neuron-aware fine-tuning of multimodal large language models for image translation](https://mlsanity.com/paper/2604.16943/) (2026)
- [NoEsis: Differentially Private Knowledge Transfer in Modular LLM Adaptation](https://mlsanity.com/paper/2504.18147/) (2025)
- [AuRA: Internalizing Audio Understanding into LLMs as LoRA](https://mlsanity.com/paper/2606.11033/) (2026)
- [AWARe: Mitigating Catastrophic Forgetting via Activation-Weighted Adaptive REtention](https://mlsanity.com/paper/2608.11758/) (2026)

## Abstract (arXiv)

Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in diverse tasks across different domains, with an increasing focus on improving their zero-shot generalization capabilities for unseen multimodal tasks. Multimodal instruction tuning has emerged as a successful strategy for achieving zero-shot generalization by fine-tuning pre-trained models on diverse multimodal tasks through instructions. As MLLMs grow in complexity and size, the need for parameter-efficient fine-tuning methods like Low-Rank Adaption (LoRA), which fine-tunes with a minimal set of parameters, becomes essential. However, applying LoRA in multimodal instruction tuning presents the challenge of task interference, which leads to performance degradation, especially when dealing with a broad array of multimodal tasks. To address this, this paper introduces a novel approach that integrates multimodal instruction tuning with Conditional Mixture-of-LoRA (MixLoRA). It innovates upon LoRA by dynamically constructing low-rank adaptation matrices tailored to the unique demands of each input instance, aiming to mitigate task interference. Experimental results on various multimodal evaluation datasets indicate that MixLoRA not only outperforms the conventional LoRA with the same or even higher ranks, demonstrating its efficacy and adaptability in diverse multimodal tasks.