mlsanityData to 7 Oct 2026

Beimingwu: A Learnware Dock System

arXiv 2401.14427 ↗First posted 24 Jan 2024cs.SE cs.CR cs.LGcited by 8

Not on the map. Why?

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.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 16 of its 43 references that are in the map. First posted on arXiv 24 Jan 2024.

Builds on

16 of 43 references.

References · 16

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
  4. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,173
  5. 2019A Comprehensive Survey on Transfer Learningcited by 1,154
  6. 2020LEEP: A New Measure to Evaluate Transferability of Learned Representationscited by 182
  7. 2018Deep Convolutional Networks as shallow Gaussian Processescited by 137
  8. 2022TransTab: Learning Transferable Tabular Transformers Across Tablescited by 132
  9. 2022Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptationcited by 93
  10. 2022Fast Finite Width Neural Tangent Kernelcited by 62
  11. 2023Model Spider: Learning to Rank Pre-Trained Models Efficientlycited by 32
  12. 2021Ranking and Tuning Pre-trained Models: A New Paradigm for Exploiting Model Hubscited by 28
4 more
  1. 2022Learnware: Small Models Do Bigcited by 16
  2. 2018Handling Concept Drift via Model Reusecited by 15
  3. 2020Model Reuse with Reduced Kernel Mean Embedding Specificationcited by 14
  4. 2018Packaging and Sharing Machine Learning Models via the Acumos AI Open Platformcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 2; 2026: 3.

8 papers.

  1. 2024Wings: Learning Multimodal LLMs without Text-only Forgettingcited by 23
  2. 2024LLMEmbed: Rethinking Lightweight LLM's Genuine Function in Text Classificationcited by 3
  3. 2025SeqFusion: Sequential Fusion of Pre-Trained Models for Zero-Shot Time-Series Forecastingcited by 3
  4. 2025Learnware of Language Models: Specialized Small Language Models Can Do Bigcited by 3
  5. 2024Hierarchical and Decoupled BEV Perception Learning Framework for Autonomous Drivingcited by 2
  6. 2026RouteJudge: An Open Platform for Reproducible and Preference-Aware LLM Routingcited by 1
  7. 2026Learnware for CSI Feedback: Scene-specific Small Models Can Do Bigcited by 0
  8. 2026Learnware and AI Model Management Systemcited by 0