All projects Model Lake
Amalur
Amalur explores the convergence of data integration and machine learning — automating how scattered training data across silos is integrated for downstream models. It is the foundation of the group’s Model Lake vision, where heterogeneous data and rich model zoos meet in one place.
Related publications
- Harpoon: Generalised Manifold Guidance for Conditional Tabular Diffusion · arXiv 2026
- Accelerating machine learning queries with linear algebra query processing · DAPD 2025
- Database as Runtime: Compiling LLMs to SQL for In-database Model Serving · SIGMOD 2025
- Database is All You Need: Serving LLMs with Relational Queries · EDBT 2025
- Ilargi: A GPU Compatible Factorized ML Model Training Framework · WISE 2025
- IMLP: An Energy-Efficient Continual Learning Method for Tabular Data Streams · arXiv 2025
- Share Secrets for Privacy: Confidential Forecasting with Vertical Federated Learning · ARES 2025
- TranSQL +: Serving Large Language Models with SQL on Low-Resource Hardware · SIGMOD 2025
- WaveStitch: Flexible and Fast Conditional Time Series Generation With Diffusion Models · SIGMOD 2025
- Amalur: The Convergence of Data Integration and Machine Learning · IEEE TKDE 2024
- AutoFeat: Transitive Feature Discovery over Join Paths · ICDE 2024
- CEBench: A Benchmarking Toolkit for the Cost-Effectiveness of LLM Pipelines · arXiv 2024
- Cross-Source ML Model Training · ICDE 2024
- Human-in-the-Loop Feature Discovery for Tabular Data · CIKM 2024
- LLM-PQA: LLM-enhanced Prediction Query Answering · CIKM 2024
- Model Selection with Model Zoo via Graph Learning · ICDE 2024
- SiloFuse: Cross-silo Synthetic Data Generation with Latent Tabular Diffusion Models · ICDE 2024
- Will Sharing Metadata Leak Privacy? · ICDEW 2024
- Amalur: Data Integration Meets Machine Learning · ICDE 2023
- Data Lakes: A Survey of Functions and Systems · IEEE TKDE 2023
- Macaroni: Crawling and Enriching Metadata from Public Model Zoos · ICWE 2023
- Metadata Representations for Queryable Repositories of Machine Learning Models · IEEE Access 2023
- Optimizing ML Inference Queries Under Constraints · ICWE 2023
- Amalur: Next-generation Data Integration in Data Lakes · CIDR 2022