# Stitchable Neural Networks

arXiv: https://arxiv.org/abs/2302.06586 · HTML: https://mlsanity.com/paper/2302.06586/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 63 of its 72 references that are in the map.
- First posted on arXiv 13 Feb 2023.

## Builds on (most cited first, 30 of 63)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [Segmenter: Transformer for Semantic Segmentation](https://mlsanity.com/paper/2105.05633/) (2021)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [Efficient Neural Architecture Search via Parameter Sharing](https://mlsanity.com/paper/1802.03268/) (2018)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)

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

- [T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching](https://mlsanity.com/paper/2402.14167/) (2024)
- [Training-Free Pretrained Model Merging](https://mlsanity.com/paper/2403.01753/) (2024)
- [Towards Personalized Federated Learning via Heterogeneous Model Reassembly](https://mlsanity.com/paper/2308.08643/) (2023)
- [Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator](https://mlsanity.com/paper/2510.13454/) (2025)
- [Conditional computation in neural networks: principles and research trends](https://mlsanity.com/paper/2403.07965/) (2024)
- [Stitched ViTs are Flexible Vision Backbones](https://mlsanity.com/paper/2307.00154/) (2023)
- [Knowledge Fusion of Large Language Models Via Modular SkillPacks](https://mlsanity.com/paper/2505.18502/) (2025)
- [R-Stitch: Dynamic Trajectory Stitching for Efficient Reasoning](https://mlsanity.com/paper/2507.17307/) (2025)
- [Slicing Vision Transformer for Flexible Inference](https://mlsanity.com/paper/2412.04786/) (2024)
- [Efficient Multiuser AI Downloading via Reusable Knowledge Broadcasting](https://mlsanity.com/paper/2307.15316/) (2023)
- [BlockLLM: Multi-tenant Finer-grained Serving for Large Language Models](https://mlsanity.com/paper/2404.18322/) (2024)
- [Latent Space Alignment for AI-Native MIMO Semantic Communications](https://mlsanity.com/paper/2507.16680/) (2025)
- [Efficient Stitchable Task Adaptation](https://mlsanity.com/paper/2311.17352/) (2023)
- [Elastic ViTs from Pretrained Models without Retraining](https://mlsanity.com/paper/2510.17700/) (2025)
- [Optimizing Time Series Forecasting Architectures: A Hierarchical Neural Architecture Search Approach](https://mlsanity.com/paper/2406.05088/) (2024)
- [Bridging Functional and Representational Similarity via Usable Information](https://mlsanity.com/paper/2601.21568/) (2026)
- [Revisiting Model Stitching In the Foundation Model Era](https://mlsanity.com/paper/2603.12433/) (2026)
- [Stitched Value Model for Diffusion Alignment](https://mlsanity.com/paper/2605.19804/) (2026)
- [Cooperative Learning for Cost-Adaptive Inference](https://mlsanity.com/paper/2312.08532/) (2023)
- [BioX-Bridge: Model Bridging for Unsupervised Cross-Modal Knowledge Transfer across Biosignals](https://mlsanity.com/paper/2510.02276/) (2025)
- [Keys in the Weights: Transformer Authentication Using Model-Bound Latent Representations](https://mlsanity.com/paper/2511.00973/) (2025)
- [KLAS: Using Similarity to Stitch Neural Networks for Improved Accuracy-Efficiency Tradeoffs](https://mlsanity.com/paper/2605.29259/) (2026)
- [No Re-Train, More Gain: Upgrading Backbones with Diffusion model for Pixel-Wise and Weakly-Supervised Few-Shot Segmentation](https://mlsanity.com/paper/2407.16182/) (2024)
- [ReStNet: A Reusable & Stitchable Network for Dynamic Adaptation on IoT Devices](https://mlsanity.com/paper/2506.09066/) (2025)
- [Sharing Knowledge without Sharing Data: Stitches can improve ensembles of disjointly trained models](https://mlsanity.com/paper/2512.17592/) (2025)
- [ABRA: Teleporting Fine-Tuned Knowledge Across Domains for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2603.12409/) (2026)

## Abstract (arXiv)

The public model zoo containing enormous powerful pretrained model families (e.g., ResNet/DeiT) has reached an unprecedented scope than ever, which significantly contributes to the success of deep learning. As each model family consists of pretrained models with diverse scales (e.g., DeiT-Ti/S/B), it naturally arises a fundamental question of how to efficiently assemble these readily available models in a family for dynamic accuracy-efficiency trade-offs at runtime. To this end, we present Stitchable Neural Networks (SN-Net), a novel scalable and efficient framework for model deployment. It cheaply produces numerous networks with different complexity and performance trade-offs given a family of pretrained neural networks, which we call anchors. Specifically, SN-Net splits the anchors across the blocks/layers and then stitches them together with simple stitching layers to map the activations from one anchor to another. With only a few epochs of training, SN-Net effectively interpolates between the performance of anchors with varying scales. At runtime, SN-Net can instantly adapt to dynamic resource constraints by switching the stitching positions. Extensive experiments on ImageNet classification demonstrate that SN-Net can obtain on-par or even better performance than many individually trained networks while supporting diverse deployment scenarios. For example, by stitching Swin Transformers, we challenge hundreds of models in Timm model zoo with a single network. We believe this new elastic model framework can serve as a strong baseline for further research in wider communities.