# Beimingwu: A Learnware Dock System

arXiv: https://arxiv.org/abs/2401.14427 · HTML: https://mlsanity.com/paper/2401.14427/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 43 references that are in the map.
- First posted on arXiv 24 Jan 2024.

## Builds on (most cited first, 16 of 16)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Neural Tangent Kernel: Convergence and Generalization in Neural Networks](https://mlsanity.com/paper/1806.07572/) (2018)
- [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://mlsanity.com/paper/2303.17580/) (2023)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [LEEP: A New Measure to Evaluate Transferability of Learned Representations](https://mlsanity.com/paper/2002.12462/) (2020)
- [Deep Convolutional Networks as shallow Gaussian Processes](https://mlsanity.com/paper/1808.05587/) (2018)
- [TransTab: Learning Transferable Tabular Transformers Across Tables](https://mlsanity.com/paper/2205.09328/) (2022)
- [Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation](https://mlsanity.com/paper/2205.04183/) (2022)
- [Fast Finite Width Neural Tangent Kernel](https://mlsanity.com/paper/2206.08720/) (2022)
- [Model Spider: Learning to Rank Pre-Trained Models Efficiently](https://mlsanity.com/paper/2306.03900/) (2023)
- [Ranking and Tuning Pre-trained Models: A New Paradigm for Exploiting Model Hubs](https://mlsanity.com/paper/2110.10545/) (2021)
- [Learnware: Small Models Do Big](https://mlsanity.com/paper/2210.03647/) (2022)
- [Handling Concept Drift via Model Reuse](https://mlsanity.com/paper/1809.02804/) (2018)
- [Model Reuse with Reduced Kernel Mean Embedding Specification](https://mlsanity.com/paper/2001.07135/) (2020)
- [Packaging and Sharing Machine Learning Models via the Acumos AI Open Platform](https://mlsanity.com/paper/1810.07159/) (2018)

## Built on by (most cited first, 8 of 8)

- [Wings: Learning Multimodal LLMs without Text-only Forgetting](https://mlsanity.com/paper/2406.03496/) (2024)
- [LLMEmbed: Rethinking Lightweight LLM's Genuine Function in Text Classification](https://mlsanity.com/paper/2406.03725/) (2024)
- [SeqFusion: Sequential Fusion of Pre-Trained Models for Zero-Shot Time-Series Forecasting](https://mlsanity.com/paper/2503.02836/) (2025)
- [Learnware of Language Models: Specialized Small Language Models Can Do Big](https://mlsanity.com/paper/2505.13425/) (2025)
- [Hierarchical and Decoupled BEV Perception Learning Framework for Autonomous Driving](https://mlsanity.com/paper/2407.12491/) (2024)
- [RouteJudge: An Open Platform for Reproducible and Preference-Aware LLM Routing](https://mlsanity.com/paper/2606.18774/) (2026)
- [Learnware for CSI Feedback: Scene-specific Small Models Can Do Big](https://mlsanity.com/paper/2608.17760/) (2026)
- [Learnware and AI Model Management System](https://mlsanity.com/paper/2609.11656/) (2026)

## Abstract (arXiv)

The learnware paradigm proposed by Zhou [2016] aims to enable users to reuse numerous existing well-trained models instead of building machine learning models from scratch, with the hope of solving new user tasks even beyond models' original purposes. In this paradigm, developers worldwide can submit their high-performing models spontaneously to the learnware dock system (formerly known as learnware market) without revealing their training data. Once the dock system accepts the model, it assigns a specification and accommodates the model. This specification allows the model to be adequately identified and assembled to reuse according to future users' needs, even if they have no prior knowledge of the model. This paradigm greatly differs from the current big model direction and it is expected that a learnware dock system housing millions or more high-performing models could offer excellent capabilities for both planned tasks where big models are applicable; and unplanned, specialized, data-sensitive scenarios where big models are not present or applicable. This paper describes Beimingwu, the first open-source learnware dock system providing foundational support for future research of learnware paradigm.The system significantly streamlines the model development for new user tasks, thanks to its integrated architecture and engine design, extensive engineering implementations and optimizations, and the integration of various algorithms for learnware identification and reuse. Notably, this is possible even for users with limited data and minimal expertise in machine learning, without compromising the raw data's security. Beimingwu supports the entire process of learnware paradigm. The system lays the foundation for future research in learnware-related algorithms and systems, and prepares the ground for hosting a vast array of learnwares and establishing a learnware ecosystem.