# RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness

arXiv: https://arxiv.org/abs/2502.17159 · HTML: https://mlsanity.com/paper/2502.17159/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 69 references that are in the map.
- First posted on arXiv 24 Feb 2025.

## Builds on (most cited first, 30 of 54)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [VizWiz Grand Challenge: Answering Visual Questions from Blind People](https://mlsanity.com/paper/1802.08218/) (2018)
- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [Remote Sensing Image Scene Classification: Benchmark and State of the Art](https://mlsanity.com/paper/1703.00121/) (2017)
- [DoRA: Weight-Decomposed Low-Rank Adaptation](https://mlsanity.com/paper/2402.09353/) (2024)
- [A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge](https://mlsanity.com/paper/2206.01718/) (2022)
- [Scaling Vision Transformers to 22 Billion Parameters](https://mlsanity.com/paper/2302.05442/) (2023)
- [Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch](https://mlsanity.com/paper/2311.03099/) (2023)
- [MaPLe: Multi-modal Prompt Learning](https://mlsanity.com/paper/2210.03117/) (2022)
- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [Merging Models with Fisher-Weighted Averaging](https://mlsanity.com/paper/2111.09832/) (2021)

## Built on by (most cited first, 26 of 26)

- [HiDe-LLaVA: Hierarchical Decoupling for Continual Instruction Tuning of Multimodal Large Language Model](https://mlsanity.com/paper/2503.12941/) (2025)
- [Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging](https://mlsanity.com/paper/2505.15875/) (2025)
- [MergeVLA: Cross-Skill Model Merging Toward a Generalist Vision-Language-Action Agent](https://mlsanity.com/paper/2511.18810/) (2025)
- [Token Transforming: A Unified and Training-Free Token Compression Framework for Vision Transformer Acceleration](https://mlsanity.com/paper/2506.05709/) (2025)
- [DC-Merge: Improving Model Merging with Directional Consistency](https://mlsanity.com/paper/2603.06242/) (2026)
- [Fine-Grained Post-Training Quantization for Large Vision Language Models with Quantization-Aware Integrated Gradients](https://mlsanity.com/paper/2603.17809/) (2026)
- [Spectral Imbalance Causes Forgetting in Low-Rank Continual Adaptation](https://mlsanity.com/paper/2602.00722/) (2026)
- [ThanoRA: Task Heterogeneity-Aware Multi-Task Low-Rank Adaptation](https://mlsanity.com/paper/2505.18640/) (2025)
- [Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging](https://mlsanity.com/paper/2512.01461/) (2025)
- [PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging](https://mlsanity.com/paper/2604.22823/) (2026)
- [Sparsity Curse: Understanding RLVR Model Parameter Space from Model Merging](https://mlsanity.com/paper/2606.18521/) (2026)
- [SSR-Merge: Subspace Signal Routing for Training-Free LoRA Merging in Diffusion Models](https://mlsanity.com/paper/2606.10617/) (2026)
- [Unified Prediction and Planning via Conflict-Aware Disjoint Parameter Training](https://mlsanity.com/paper/2607.19971/) (2026)
- [From Parameters to Behaviors: A Survey of Model Fusion for Large Language Models](https://mlsanity.com/paper/2609.19553/) (2026)
- [CAMFT: Conflict-Aware Mergeable Fine-Tuning for Large Language Models](https://mlsanity.com/paper/2609.22253/) (2026)
- [Beyond Parameter Arithmetic: Sparse Complementary Fusion for Distribution-Aware Model Merging](https://mlsanity.com/paper/2602.11717/) (2026)
- [ES-Merging: Biological MLLM Merging via Embedding Space Signals](https://mlsanity.com/paper/2603.14405/) (2026)
- [Decoupling Endpoint and Semantic Transition Learning for Zero-Shot Composed Image Retrieval](https://mlsanity.com/paper/2605.08389/) (2026)
- [Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach](https://mlsanity.com/paper/2607.15661/) (2026)
- [CT-Merging: Consensus Directions and Task-Specific Scaling for LoRA Adapter Merging](https://mlsanity.com/paper/2607.20561/) (2026)
- [Understanding Knowledge Transfer Mechanism in Heterogeneous MLLM Fusion: A Simple Linear Approach](https://mlsanity.com/paper/2607.26608/) (2026)
- [AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models](https://mlsanity.com/paper/2608.06699/) (2026)
- [HyperFix: Combinatorial Nonlinear Correction for Task Vector Merging](https://mlsanity.com/paper/2608.11499/) (2026)
- [Tracing and Coordinating Cross-Layer Influence for Multimodal Model Merging](https://mlsanity.com/paper/2609.12897/) (2026)
- [Beyond Uniform Subspaces: Spectrum-Aware and Depth-Adaptive Fusion for Multi-Task Model Merging](https://mlsanity.com/paper/2609.24612/) (2026)
- [PaLoRA: Paced Low-Rank Adaptation for Continual Learning](https://mlsanity.com/paper/2610.04226/) (2026)

## Abstract (arXiv)

Fine-tuning pre-trained models with custom data leads to numerous expert models on specific tasks. Merging models into one universal model to empower multi-task ability refraining from data leakage has gained popularity. With the expansion in data and model size, parameter-efficient tuning becomes the common practice for obtaining task-specific models efficiently. However, few methods are dedicated to efficient merging, and existing methods designed for full fine-tuning merging fail under efficient merging. To address the issue, we analyze from low-rank decomposition and reveal that direction robustness during merging is crucial for merging efficient modules. We furthermore uncover that compensating for the gap between stark singular values contributes to direction robustness. Therefore, we propose RobustMerge, a training-free parameter-efficient merging method with complementary parameter adaptation to maintain direction robustness. Specifically, we (1) prune parameters and scale coefficients from inter-parameter relation for singular values to maintain direction stability away from task interference, and (2) perform cross-task normalization to enhance unseen task generalization. We establish a benchmark consisting of diverse multimodal tasks, on which we conduct experiments to certify the outstanding performance and generalizability of our method. Additional studies and extensive analyses further showcase the effectiveness. Code is available at https://github.com/AuroraZengfh/RobustMerge.