Publications
- 2026Recovering Graph ANN Search on Attention-Derived Workloads via a Query-Agnostic Spherical Transformationto appear
David Procházka, Vlastislav Dohnal, and Martin Aumüller
Conference on Information and Knowledge Management (CIKM 2026) · Rome, Italy
- 2026Learned k-NN Graph Construction and Spherical Indexing for MIPS
David Procházka, Emma Sommerová, Jan Mach, and Vlastislav Dohnal
Similarity Search and Applications (SISAP 2026) · Brno, Czechia
- 2026Capacity-Aware Cluster Rebalancing for Efficient R-Tree Indexing
David Procházka, Mirjam Bayer, Daniyal Kazempour, Maximilian Verwiebe, Peer Kröger, and Vlastislav Dohnal
Similarity Search and Applications (SISAP 2026) · Brno, Czechia
- 2026AlphaFind v2: similarity search in AlphaFold DB and TED domains across structural contexts
Terézia Slanináková, Adrián Rošinec, Jakub Čillík, Aleš Křenek, Katarína Grešová, Jana Porubská, Eva Maršálková, Jaroslav Olha, David Procházka, Lukáš Hejtmánek, Vlastislav Dohnal, Karel Berka, Radka Svobodová, and Matej Antol
- 2025On the Costs and Benefits of Learned Indexing for Dynamic High-Dimensional Data
Terézia Slanináková, Jaroslav Olha, David Procházka, Matej Antol, and Vlastislav Dohnal
Big Data Analytics and Knowledge Discovery (DaWaK 2025) · Bangkok, Thailand
- 2024Scaling Learned Metric Index to 100M Datasets
David Procházka, Terézia Slanináková, Jozef Čerňanský, Jaroslav Olha, Matej Antol, and Vlastislav Dohnal
Similarity Search and Applications (SISAP 2024) · Providence, RI, USA
- 2024AlphaFind: discover structure similarity across the proteome in AlphaFold DB
David Procházka*, Terézia Slanináková*, Jaroslav Olha, Adrián Rošinec, Katarína Grešová, Miriama Jánošová, Jakub Čillík, Jana Porubská, Radka Svobodová, Vlastislav Dohnal, and Matej Antol · *equal contribution
- 2023SISAP 2023 Indexing Challenge – Learned Metric Index
Terézia Slanináková, David Procházka, Matej Antol, Jaroslav Olha, and Vlastislav Dohnal
Similarity Search and Applications (SISAP 2023) · A Coruña, Spain
- 2021Organizing Similarity Spaces Using Metric Hulls
Miriama Jánošová, David Procházka, and Vlastislav Dohnal
Similarity Search and Applications (SISAP 2021) · Dortmund, Germany (virtual)
Experience
- 2024–
nowResearch SpecialistLeading the Information and Data Platform team of CESMOD.cz.
Dept. of Computer Systems and Communications, Masaryk University
- 2024–
nowResearch SpecialistResearching indexes for vector search over data that keeps changing, while designing public tools such as AlphaFind and DreaMS Search.
Dept. of Machine Learning and Data Processing, Masaryk University
Projects
- 2026–
2029Artificial Intelligence-Based Quality Control System for Decorative VeneersTeam member
Ministry of Industry and Trade of the Czech Republic
CZ.01.01.01/01/25_067/0009890
- 2025–
2027Software Tool for Annotating Protein Structural Data Based on Structural SimilarityTeam member
MUNI/92/13289/2025
- 2024–
2025
Show 2 more ↓ Show less ↑
- 2024–
2029 - 2023–
2026
Research stays
- 2025IT University of Copenhagen
Algorithms and Complexity group · hosted by Assoc. Prof. Martin Aumüller
Copenhagen, Denmark · September – October 2025
- 2024Technical University of Dortmund
Data Mining Research Group · hosted by Prof. Dr. Erich Schubert
Dortmund, Germany · March 2024
Talks
- 2026DreaMS Search: vector search over 200+ million tandem mass spectra
Invited talk.
SITOLA laboratory seminar, Masaryk University · September 2026
- 2026Vector Search at Scale
Guest lecture in PV211 Introduction to Information Retrieval.
Masaryk University · Spring 2026
- 2024Complex Data Management in the Age of AI
Invited talk.
SITOLA laboratory seminar (SitSem) · Telč · September 2024
Academic service
- 2026Similarity Search and Applications (SISAP 2026)
Program committee member and session chair.
Brno, Czechia
- 2025–
2026ACM MultimediaReviewer.
Theses
- 2026Scalable Learned Indexing for Complex Data
David Procházka · supervisor Vlastislav Dohnal
Advanced Master's thesis (RNDr.), Masaryk University
- 2023Advancing Motion Words for Human Motion Classification
David Procházka · supervisor Vlastislav Dohnal
Master's thesis, Masaryk University
- 2021Indexing Structure Based on Metric Hulls
David Procházka · supervisor Vlastislav Dohnal
Bachelor's thesis, Masaryk University
Teaching
- 2024–
nowPA152 Efficient Use of Database SystemsTeaching assistant.
- 2023–
nowPA036 Database System ProjectTeaching assistant.
- 2022–
nowPA220 Database Systems for Data AnalyticsTeaching assistant.
Show 1 more ↓ Show less ↑
- 2024
Thesis supervision
- 2026Nearest Neighbor Ordering Under Dimensionality Reduction Techniques
Filip Balko
Bachelor's thesis, Masaryk University
- 2026
- 2026Continually Learned Index for Dynamic Approximate Nearest Neighbor Search
Michal Jakubík
Master's thesis, Masaryk University
Show 9 more ↓ Show less ↑
- 2026
- 2026Dynamic Space-Partitioning Indexes for High-Dimensional Data
Boris Lukačovič
Bachelor's thesis, Masaryk University
- 2026A High-Performance Dynamic Learned Index for Complex Data in Rust
Šimon Plhák
Master's thesis, Masaryk University
- 2026
- 2026Dynamic Properties of the Hierarchical Navigable Small World Index
Adéla Návratová
Bachelor's thesis, Masaryk University
- 2025Implications of the Curse of Dimensionality for High-Dimensional Indexing
Maroš Pavlík
Bachelor's thesis, Masaryk University
- 2025
- 2025Enhancing Performance of Learned Metric Index for Indexing Large Datasets
Jozef Čerňanský
Bachelor's thesis, Masaryk University
- 2024Implementing Filtering Techniques in Learned Metric Index for Indexing Large Datasets
Jan Mach, with Terézia Slanináková consulting
Bachelor's thesis, Masaryk University
Thesis consultation
- 2026Analysis and Visualization of Data Flows via Data Lineage
Peter Ilaš
Bachelor's thesis, Masaryk University
- 2026Extending a Data Platform with Data from the Information System for Research, Development, and Innovation
Samuel Hudák
Bachelor's thesis, Masaryk University
- 2026Dynamic Learned Indexing for Vector Data Using Continual Learning
Filip Forgáč
Master's thesis, Masaryk University
Show 1 more ↓ Show less ↑
- 2026Automated Homework Submission and Evaluation Framework
Jan Švestka
Master's thesis, Masaryk University