MorphingDB: A Task-Centric AI-Native DBMS for Model Management and Inference
Summary: MorphingDB embeds task-centric model management into PostgreSQL with tensor types and a two‑phase transfer-learning selector (offline transferability subspace, online feature-aware projection). Pre‑embedding/vector sharing and DAG batch pipelines with cost‑aware scheduling boost inference, improving throughput and accuracy/resource/time tradeoffs over AI‑DBMS and AutoML baselines. (summarized by gpt-5-mini on Feb 11 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Sai Wu (Zhejiang University)
- 2. Ruichen Xia (Zhejiang University)
- 3. Dingyu Yang (Zhejiang University)
- 4. Rui Wang (Zhejiang University)
- 5. Huihang Lai (Zhejiang University)
- 6. Jiarui Guan (Zhejiang University)
- 7. Jiameng Bai (Zhejiang University)
- 8. Dongxiang Zhang (Zhejiang University)
- 9. Xiu Tang (Zhejiang University)
- 10. Zhongle Xie (Zhejiang University)
- 11. Peng Lu (Zhejiang University)
- 12. Gang Chen (Zhejiang University)
BibTeX Citation
@inproceedings{wu_sigmod26,
title = {{MorphingDB: A Task-Centric AI-Native DBMS for Model Management and Inference}},
author = {Wu, Sai and Xia, Ruichen and Yang, Dingyu and Wang, Rui and Lai, Huihang and Guan, Jiarui and Bai, Jiameng and Zhang, Dongxiang and Tang, Xiu and Xie, Zhongle and Lu, Peng and Chen, Gang},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3769844},
url = {https://dl.acm.org/doi/10.1145/3769844},
year = {2026}
}
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 11 of 11 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,120 | KathDB: Explainable Multimodal Database Management System with Human-AI Collaboration | 2026 | CIDR |
| 2 | 11,548 | DeepO: A Learned Query Optimizer | 2022 | SIGMOD |
| 3 | 2,888 | AI Meets Database: AI4DB and DB4AI | 2021 | SIGMOD |
| 4 | 5,456 | InferDB: In-Database Machine Learning Inference Using Indexes | 2024 | VLDB |
| 5 | 9,470 | Powering In-Database Dynamic Model Slicing for Structured Data Analytics | 2024 | VLDB |
| 6 | 3,961 | MB2: Decomposed Behavior Modeling for Self-Driving Database Management Systems | 2021 | SIGMOD |
| 7 | 2,175 | From Natural Language Processing to Neural Databases | 2021 | VLDB |
| 8 | 5,953 | The Tensor Data Platform: Towards an AI-centric Database System | 2023 | CIDR |
| 9 | 6,357 | A Unified Transferable Model for ML-Enhanced DBMS | 2022 | CIDR |
| 10 | 8,221 | NeurDB: On the Design and Implementation of an AI-powered Autonomous Database | 2025 | CIDR |