Projects

• DB-BERT: the database tuning tool that “reads” the manual.
• UDO: the “Swiss Army Knife” of database tuning tools.
• SkinnerDB: adaptive query processing with reinforcement learning.
• NaturalMiner: automate exploratory data analysis via LLMs.
• CodexDB: synthesize Python code for data processing via LLMs.
• CiceroDB: efficient and effective voice query interfaces.
• Scrutinizer: fact-checking natural language claims from data.
• GenesisDB: generate personalized DBMS components (WIP).

Publications

2025

• SIGMOD 2025 Demonstrating CEDAR: A System for Cost-Efficient Data-Driven Claim Verification. Tharushi Jayasekara, Immanuel Trummer.
• SIGMOD 2025 Demonstrating SQLBarber: Leveraging Large Language Models to Generate Customized, Constraint-aware, and Realistic SQL. Jiale Lao, Immanuel Trummer.
• SIGMOD 2025 SwellDB: Dynamic Query-Driven Table Generation with Large Language Models. Victor Giannakouris, Immanuel Trummer.
• SIGMOD 2025 λ-Tune: Harnessing Large Language Models for Automated Database System Tuning. Victor Giannakouris, Immanuel Trummer.
  [Paper]
• SIGMOD 2025 SpareLLM: Automatically Selecting Task-Specific Minimum-Cost Large Language Models under Equivalence Constraint. Saehan Jo, Immanuel Trummer.
• VLDBJ 2025 Best of VLDB Generating Highly Customizable Python Code for Data Processing with Large Language Models. Immanuel Trummer.
  [Paper]
• Data Engineering Bulleting 2025 Customizing Operator Implementations for SQL Processing via Large Language Models. Immanuel Trummer.
  [Paper]

2024

• SIGMOD 2024 ThalamusDB: Approximate Query Processing on Multi-Modal Data. Saehan Jo, Immanuel Trummer.
  [Paper]
• SIGMOD 2024 ROME: Robust Query Optimization via Parallel Multi-Plan Execution. Ziyun Wei, Immanuel Trummer.
  [Paper]
• SIGMOD 2024 Demonstrating λ-Tune: Exploiting Large Language Models for Workload-Adaptive Database System Tuning. Victor Giannakouris, Immanuel Trummer.
  [Paper]
• ICDE 2024 Tutorial on Large Language Models: Principles and Practice. Immanuel Trummer.
  [Paper]
• VLDB 2024 Can Large Language Models Predict Data Correlations from Column Names? Immanuel Trummer.
  [Paper Code]
• VLDB 2024 Generating Succinct Descriptions of Database Schemata for Cost-Efficient Prompting of Large Language Models. Immanuel Trummer.
  [Paper]
• VLDB 2024 Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes. Simran Arora, Brandon Yang, Sabri Eyuboglu, Avanika Narayan, Andrew Hojel, Immanuel Trummer, Christopher Re.
  [Paper Code]
• VLDB 2024 DBG-TP: A Large Language Model Assisted Query Performance Regression Debugger. Victor Giannakouris, Immanuel Trummer.
  [Paper]
• VLDB 2024 Quantum-Inspired Digital Annealing for Join Ordering. Manuel Schönberger, Immanuel Trummer, Wolfgang Mauerer.
  [Paper]
• Q-DATA 2024 Leveraging Quantum Computing for Database Index Selection. Immanuel Trummer, Davide Venturelli.
  [Paper]
• Q-DATA 2024 Towards Out-of-Core Simulators for Quantum Computing. Immanuel Trummer.
  [Paper]
• Q-DATA 2024 First Workshop on Quantum Computing and Quantum-Inspired Technology for Data-Intensive Systems and Applications. Ibrahim Sabek, Immanuel Trummer, Stefan Prestel.
• RLC 2024 JoinGym: An Efficient Join Order Selection Environment. Junxiong Wang, Kaiwen Wang, Yueying Li, Nathan Kallus, Immanuel Trummer, Wen Sun.

2023

• MEAP Book AI-Assisted Data Science: Large Language Models for Multimodal Data Analysis. Immanuel Trummer.
  [Book]
• VLDBJ 2023 DB-BERT: Making Database Tuning Tools “Read” the Manual. Immanuel Trummer.
  [Paper]
• PVLDB 2023 ADOPT: Adaptively Optimizing Attribute Orders for Worst-Case Optimal Join Algorithms via Reinforcement Learning. Junxiong Wang, Immanuel Trummer, Ahmet Kara, Dan Olteanu.
  [Paper Code]
• PVLDB 2023 Demonstrating ADOPT: Adaptively Optimizing Attribute Orders for Worst-Case Optimal Joins via Reinforcement Learning. Junxiong Wang, Immanuel Trummer, Ahmet Kara, Dan Olteanu.
  [Code]
• PVLDB 2023 Demonstrating GPT-DB: Generating Query-Specific and Customizable Code for SQL Processing with GPT-4. Immanuel Trummer.
  [Code]
• SIGMOD 2023 Best Demo Runner Up Demonstrating NaturalMiner: Searching Large Data Sets for Abstract Patterns Described in Natural Language. Immanuel Trummer.
  [Paper Code Talk]
• SIGMOD 2023 Demonstration of ThalamusDB: Answering Complex SQL Queries with Natural Language Predicates on Multi-Modal Data. Saehan Jo, Immanuel Trummer.
  [Paper Talk]
• VLDB 2023 QDSM Quantum Optimisation of General Join Trees. Manuel Schönberger, Immanuel Trummer, Wolfgang Mauerer.
  [Paper]

2022

• PVLDB 2022 CodexDB: Synthesizing Code for Query Processing from Natural Language Instructions Using GPT-3 Codex. Immanuel Trummer.
  [Paper Code Talk]
• PVLDB 2022 BABOONS: Black-Box Optimization of Data Summaries in Natural Language. Immanuel Trummer.
  [Paper Code]
• PVLDB 2022 From BERT to GPT-3 Codex: Harnessing the Potential of Very Large Language Models for Data Management. Immanuel Trummer.
  [Paper Talk]
• PVLDB 2022 UDO: Universal Database Optimization Using Reinforcement Learning. Junxiong Wang, Immanuel Trummer, Debabrota Basu.
  [Paper Code Talk]
• PVLDB 2022 SkinnerMT: Parallelizing for Efficiency and Robustness in Adaptive Query Processing on Multicore Platforms. Ziyun Wei, Immanuel Trummer.
  [Paper]
• VLDB 2022, PhD Workshop Building Learned Federated Query Optimizers. Victor Giannakouris, Immanuel Trummer.
  [Paper]
• SIGMOD 2022 Demonstrating DB-BERT: a Database Tuning Tool that “Reads the Manual”. Immanuel Trummer.
  [Paper Code Talk]
• AAAI 2022 Procrastinated Tree Search: Black-Box Optimization with Delayed, Noisy, and Multi-Fidelity Feedback. Junxiong Wang, Debabrota Basu, Immanuel Trummer.
  [Paper Code]
• SIGMOD 2022 DB-BERT: a Database Tuning Tool that “Reads the Manual”. Immanuel Trummer.
  [Paper Code Talk]
• CIDR 2022 Towards NLP-Enhanced Data Profiling Tools. (Abstract) Immanuel Trummer.
  [Paper Code Talk]

2021

• TODS 2021 “Best of SIGMOD” Edition SkinnerDB: Regret-Bounded Query Evaluation via Reinforcement Learning. Immanuel Trummer, Junxiong Wang, Ziyun Wei, Deepak Maram, Samuel Moseley, Saehan Jo, Joseph Antonakakis
  [Paper Code Talk]
• PVLDB 2021 The Case for NLP-Enhanced Database Tuning: Towards Tuning Tools that Read the Manual. Immanuel Trummer.
  [Paper Talk]
• PVLDB 2021 Robust Voice Querying with MUVE: Optimally Visualizing Results of Phonetically Similar Queries. Ziyun Wei, Immanuel Trummer, Connor Anderson.
  [Paper]
• IEEE Data Engineering Bulletin WebChecker: Towards an Infrastructure for Efficient Misinformation Detection at Web Scale. Immanuel Trummer.
  [Paper Code]
• SIGMOD Record 2021 Database Tuning Using Natural Language Processing. Immanuel Trummer.
  [Paper]
• SIGMOD 2021 Demonstrating UDO: a Unified Approach for Optimizing Transaction Code, Physical Design, and System Parameters via Reinforcement Learning. Junxiong Wang, Immanuel Trummer, Debabrota Basu.
  [Paper Code]
• SIGMOD 2021 Demonstrating Robust Voice Querying with MUVE: Optimally Visualizing Results of Phonetically Similar Queries. Ziyun Wei, Immanuel Trummer, Connor Anderson.
  [Paper]
• ICDE 2021 Optimally Summarizing Data by Small Fact Sets for Concise Answers to Voice Queries. Immanuel Trummer, Connor Anderson.
  [Paper Code Talk]

2020

• BDA 2020 Best Demonstration Award Scrutinizer: a System for Checking Statistical Claims. Georgios Karagiannis, Mohammed Saeed, Paolo Papotti, Immanuel Trummer.
  [Paper]
• PVLDB 2020 Scrutinizer: A Mixed-Initiative Approach to Large-Scale, Data-Driven Claim Verification. George Karagiannis, Mohammed Saeed, Paolo Papotti, Immanuel Trummer.
  [Paper Code]
• PVLDB 2020 Mining an “Anti-Knowledge Base” from Wikipedia Updates with Applications to Fact Checking and Beyond. Georgios Karagiannis, Immanuel Trummer, Saehan Jo, Shubham Khandelwal, Xuezhi Wang, Cong Yu.
  [Paper Data]
• PVLDB 2020 Demonstration of ScroogeDB: Getting More Bang for the Buck with Deterministic Approximation in the Cloud. Saehan Jo, Jialing Pei, Immanuel Trummer.
  [Paper]
• PVLDB 2020 Demonstrating the Voice-Based Exploration of Large Data Sets with CiceroDB-Zero. Immanuel Trummer.
  [Paper Code]
• PVLDB 2020 Scrutinizer: Fact Checking Statistical Claims. George Karagiannis, Mohammed Saeed, Paolo Papotti, Immanuel Trummer.
  [Paper Code]
• SIGMOD 2020 Demonstration of BitGourmet: Data Analysis via Deterministic Approximation. Saehan Jo, Immanuel Trummer.
  [Paper]
• CIDR 2020 BitGourmet: Deterministic Approximation via Optimized Bit Selections. Saehan Jo, Immanuel Trummer.
  [Paper Talk]

2019

• SIGMOD 2019 Selected for “Best of SIGMOD” SkinnerDB: Regret-bounded Query Evaluation via Reinforcement Learning. Immanuel Trummer, Junxiong Wang, Deepak Maram, Samuel Moseley, Saehan Jo, Joseph Antonakakis.
  [Paper Talk]
• SIGMOD 2019 A Holistic Approach for Query Evaluation and Result Vocalization in Voice-Based OLAP. Immanuel Trummer, Yicheng Wang, Saketh Mahankali.
  [Paper Talk]
• SIGMOD 2019 Exact Cardinality Query Optimization with Bounded Execution Cost. Immanuel Trummer.
  [Paper Code Talk]
• SIGMOD 2019 Verifying Text Summaries of Relational Data Sets. Saehan Jo, Immanuel Trummer, Weicheng Yu, Xuezhi Wang, Cong Yu, Daniel Liu, Niyati Mehta.
  [Paper Talk]
• PVLDB 2019 AggChecker: a Fact-Checking System for Text Summaries of Relational Data Sets. Saehan Jo, Immanuel Trummer, Weicheng Yu, Xuezhi Wang, Cong Yu, Daniel Liy Niyati Mehta.
  [Paper Demo]
• CIDR 2019 Data Vocalization with CiceroDB. Immanuel Trummer.
  [Paper Talk]

2018

• PVLDB 2018 SkinnerDB: Regret-Bounded Query Evaluation via Reinforcement Learning. Immanuel Trummer, Samuel Moseley, Joseph Antonakakis, Saehan Jo.
  [Paper Code]
• PVLDB 2018 Vocalizing Large Time Series Efficiently. Immanuel Trummer, Mark Bryan, Ramya Narasimha.
  [Paper Talk]

2017

• CACM 2017 Multi-Objective Parametric Query Optimization. Immanuel Trummer, Christoph Koch.
  [Paper]
• PVLDB 2017 Data Vocalization: Optimizing Voice Output of Relational Data. Immanuel Trummer, Jiancheng Zhu, Mark Bryan.
  [Paper Talk]
• SIGMOD 2017 Solving the Join Ordering Problem via Mixed Integer Linear Programming. Immanuel Trummer, Christoph Koch.
  [Paper Code]

Funding

External

• NSF 2239326: CAREER: Mining Hints from Text Documents to Guide Automated Database Performance Tuning (2023-2028).
• NSF 1910830: III: Small: Regret-Bounded Query Evaluation via Reinforcement Learning (2019-2022).
• Google AI-Powered Immediate Response to Pandemics Initiative: Data-Driven Automatic Fact Checking of Coronavirus Claims (2020).
• Fact-Checking Development Grant (IFCN & YouTube): Automatic Fact-Checking of Coronavirus Claims (2020).
• Google Faculty Research Award: Mining an “Anti-Knowledge Base” for Fact Checking from Wikipedia Updates (2018).
• Google Faculty Research Award: Optimizing Voice-Based Output of Relational Data (2016).

Internal

• CIDA RIF Seed Grant: Co-Creating a Human-Machine Interface Better Adapted for On-Farm Data Recording, Curation, Management, and Use (2021-2023).
• Huawei Research Initiative: Deterministic Approximation via BitGourmet (2019).

Students

• Junxiong Wang (Last paper)
• Saehan Jo (Last paper)
• Victor Giannakouris (Last paper)
• Ziyun Wei (Last paper)

Teaching

Cornell Courses

• CS 4320: Introduction to database systems.
• CS 4321: Practicum in database systems.
• CS 6320: Advanced database systems.
• CS 7390: Seminar in database systems.

Online Courses

• Introductory database lecture (over 1M views!)
• Tutorial on large language models

Hosted on GitHub Pages — Theme by orderedlist