# Superpose Task-specific Features for Model Merging

arXiv: https://arxiv.org/abs/2502.10698 · HTML: https://mlsanity.com/paper/2502.10698/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 62 references that are in the map.
- First posted on arXiv 15 Feb 2025.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (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)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [Remote Sensing Image Scene Classification: Benchmark and State of the Art](https://mlsanity.com/paper/1703.00121/) (2017)
- [Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch](https://mlsanity.com/paper/2311.03099/) (2023)
- [Merging Models with Fisher-Weighted Averaging](https://mlsanity.com/paper/2111.09832/) (2021)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [Word Translation Without Parallel Data](https://mlsanity.com/paper/1710.04087/) (2017)
- [CMMLU: Measuring massive multitask language understanding in Chinese](https://mlsanity.com/paper/2306.09212/) (2023)
- [PAWS: Paraphrase Adversaries from Word Scrambling](https://mlsanity.com/paper/1904.01130/) (2019)
- [Dataless Knowledge Fusion by Merging Weights of Language Models](https://mlsanity.com/paper/2212.09849/) (2022)
- [WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations](https://mlsanity.com/paper/1808.09121/) (2018)
- [LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition](https://mlsanity.com/paper/2307.13269/) (2023)
- [In-Context Learning Creates Task Vectors](https://mlsanity.com/paper/2310.15916/) (2023)
- [PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts](https://mlsanity.com/paper/2202.01279/) (2022)
- [Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning](https://mlsanity.com/paper/1909.00277/) (2019)
- [The E2E Dataset: New Challenges For End-to-End Generation](https://mlsanity.com/paper/1706.09254/) (2017)
- [QASC: A Dataset for Question Answering via Sentence Composition](https://mlsanity.com/paper/1910.11473/) (2019)
- [Composing Parameter-Efficient Modules with Arithmetic Operations](https://mlsanity.com/paper/2306.14870/) (2023)
- [Localizing Task Information for Improved Model Merging and Compression](https://mlsanity.com/paper/2405.07813/) (2024)

## Built on by (most cited first, 5 of 5)

- [DiMtextsuperscript3: Bridging Multilingual and Multimodal Models via Direction- and Magnitude-Aware Merging](https://mlsanity.com/paper/2605.12960/) (2026)
- [Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts](https://mlsanity.com/paper/2607.00666/) (2026)
- [Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach](https://mlsanity.com/paper/2607.15661/) (2026)
- [Hierarchical Wasserstein Merging for Multi-Domain Multi-Task Learning: From Specialists to a Generalist](https://mlsanity.com/paper/2609.06406/) (2026)
- [A Survey on the Linear Representation Hypothesis](https://mlsanity.com/paper/2609.22695/) (2026)

## Abstract (arXiv)

Model merging enables powerful capabilities in neural networks without requiring additional training. In this paper, we introduce a novel perspective on model merging by leveraging the fundamental mechanisms of neural network representation. Our approach is motivated by the linear representation hypothesis, which states that neural networks encode information through linear combinations of feature vectors. We propose a method that superposes task-specific features from individual models into a merged model. Our approach specifically targets linear transformation matrices, which are crucial for feature activation and extraction in deep networks. By formulating the merging process as a linear system, we can preserve task-specific features from individual models and create merged models that effectively maintain multi-task capabilities compared to existing methods. Extensive experiments across diverse benchmarks and models demonstrate that our method outperforms existing techniques. Code is available at https://github.com/LARS-research/STF.