Research Questions: How can we design computing platforms that are more efficient for data processing workloads? What are the architectures that maximize throughput, energy efficiency and minimizes latency for data processing? What does the future of compute infrastructure for distributed data processing look like, and how should we balance specialization versus general-purpose? Are GPUs and AI accelerators evolving into the general-purpose data parallel processing hardware of the future?
Yannis Chronis
Assistant Professor
chronis [at] ethz.ch
Dept. of Computer Science
ETH Zurich
About Me
I am an assistant professor of Computer Science
at ETH Zurich, and a Visiting Faculty at
Google. I am a member of the
Systems Group where I lead the Data, Intelligence and Architecture Lab (DIAL),
and a faculty member at the ETH AI Center. I work on making
access to data efficient, and the systems that provide it efficient, robust and easy to use. My research interests
span database systems, computer architecture, AI and their interesection.
Before joining ETH, I spent 3 years at the Systems Research Group at Google. I received my Ph.D. in Computer
Science from the University of Wisconsin-Madison, advised by Prof. Jignesh Patel.
My PhD focused on HW-SW codesign for making data processing efficient. My work was generously
supported by a Facebook
Fellowship. I earned a Bachelor's and a Master's Degree on Computer Science from the
University of Athens, Greece, advised by Prof. Yannis Ioannidis.
Active research areas
Hardware–Software Co-Design for Data Processing +Research Questions: What core operations should a next-generation data management system support to increase data retrieval quality and overall efficiency? How can database systems serve as the central source of data for multi-step AI-driven and semantic data search pipelines?
Research Questions: What data structures and algorithms can enable efficient search across both structured and unstructured data? How do we design efficient and easy to use systems for semantic queries?
For positions in DIAL, please visit our website.
Publications
VADER: Filtered Vector Search with Declarative Recall
Manos Chatzakis, Duo Lu, Helena Caminal, Yannis Chronis, Fatma Özcan, Yannis Papakonstantinou, Timofey Asyrkin, Sebastian Infante Murguia, Itai Rosenblatt, Themis Palpanas
arXiv 2026 arXiv
Over the Memory Wall, Into the Instruction Wall: The New Bottleneck in GPU Data Processing
Sven Hepkema, Bowen Wu, Christos Kozyrakis, Yannis Chronis, Gustavo Alonso
arXiv 2026 arXiv
An In-Depth Study of Filter-Agnostic Vector Search on a PostgreSQL Database System
Duo Lu, Helena Caminal, Manos Chatzakis, Yannis Papakonstantinou, Yannis Chronis, Vaibhav Jain, Fatma Ozcan
SIGMOD 2026 (To appear) arXiv
To GPU or Not to GPU: Vector Search in Relational Engines
Vasilis Mageirakos, Joel André, Marko Kabic, Bowen Wu, Yannis Chronis, Gustavo Alonso
arXiv 2026 arXiv
Is it Bigger than a Breadbox: Efficient Cardinality Estimation for Real World Workloads
Zixuan Yi, Sami Abu-El-Haija, Yawen Wang, Teja Vemparala, Yannis Chronis, Yu Gan, Michael Burrows, Carsten Binnig, Bryan Perozzi, Ryan Marcus, Fatma Özcan
arXiv 2025 arXiv
Filtered Vector Search: State-of-the-art and Research Challenges
Yannis Chronis, Helena Caminal, Yannis Papakonstantinou, Fatma Özcan, Anastasia Ailamaki
VLDB 2025 Tutorial PDF
LLMs and Databases: A Synergistic Approach to Data Utilization
Fatma Ozcan, Yeounoh Chung, Yannis Chronis, Yu Gan, Yawen Wang, Carsten Binnig, Johannes Wehrstein, Gaurav Tarlok Kakkar, Sami Abu-el-haija
IEEE Data Eng. Bull. 2025 Link
Databases in the Era of Memory-Centric Computing
Yannis Chronis, Anastasia Ailamaki, Lawrence Benson, Helena Caminal, Jana Giceva, Dave Patterson, Eric Sedlar, Lisa Wu Wills
CIDR 2025 PDF
CardBench: A Benchmark for Learned Cardinality Estimation in Relational Databases
Yannis Chronis, Yawen Yang, Yu Gan, Sami Abu-El-Haija, Chelsea Lin, Carsten Binnig, Fatma Ozcan
arXiv 2024 PDF arXiv Code
Simple Adaptive Query Processing vs. Learned Query Optimizers: Observations and Analysis
Yunjia Zhang, Yannis Chronis, Jignesh Patel, Theodoros Rekatsinas
VLDB 2023 PDF 
PVLDB 2025 PDF
SPA: Economical and Workload-Driven Indexing for Data Analytics in the Cloud
Peter Boncz, Yannis Chronis, Jan Finis, Stefan Halfpap, Viktor Leis, Thomas Neumann, Anisoara Nica, Caetano Sauer, Knut Stolze, Marcin Zukowski
ICDE 2023 PDF
Accelerating Database Analytical Query Workloads using an Associative Processor
Helena Caminal*, Yannis Chronis*, Tianshu Wu, Jignesh M. Patel, José F. Martínez
ISCA 2022 PDF
How good is my HTAP system?
Elena Milkai, Yannis Chronis, Kevin Gaffney, Zhihan Guo, Jignesh M. Patel, Xiangyao Yu
SIGMOD 2022 PDF
Can Transfer Learning be used to build a Query Optimizer?
Yunjia Zhang, Yannis Chronis, Jignesh Patel, Theodoros Rekatsinas
CIDR 2022 PDF
External Merge Sort for Top-K Queries: Eager input filtering guided by histograms
Yannis Chronis, Thanh Do, Goetz Graefe, Keith Peters
SIGMOD 2020 PDF
Efficiently Searching In-Memory Sorted Arrays: Revenge of the Interpolation Search?
Peter VanSandt, Yannis Chronis, Jignesh M. Patel
SIGMOD 2019 PDF Code 
Fairness in dataflow scheduling in the cloud
Ilia Pietri, Yannis Chronis, Yannis Ioannidis
Information Systems 2019 PDF
Multi-objective optimization of scheduling dataflows on heterogeneous cloud resources
Ilia Pietri, Yannis Chronis, Yannis Ioannidis
IEEE Big Data 2017 PDF
Teaching
ETH Zurich
[Autumn 2026] Data Management Systems
[Spring 2026] Data Modeling and Databases
[Autumn 2025] Vector Search in Databases for AI Seminar
Universtiy of Wisconsin-Madison
[Spring 2022] CS 564 - Database Management Systems: Design and Implementation
Experience and Awards
Systems Researcher, SRG @
Google, Sunnyvale, USA
2022-2025
Facebook Fellowship Recipient, Blog
Post
2020-2022
Intern, Microsoft
Research and Google
Summer 2017, Summer 2018, Summer 2020
Service
PCSIGMOD, VLDB, VLDBJ, CIDR, DaMoN, MICRO, SOCC
CIDR Proceedings Chair