OBSR: Open Benchmark for spatial representations
Julia A. Moska, Oleksii Furman, Piotr Ł Gramacki, Piotr Szymański, Kacper Kozaczko, Szymon Leszkiewicz, Jakub Polczyk
ACM
2025
Profile
Piotr Gramacki
PhD Student
Piotr is a PhD student working on Geospatial task-solving with the help of Large Language Models (LLMs). Apart from that, he is interested in representation learning from geospatial data and natural language processing. He is a member of the Kraina.AI research group, where he works with spatial data and urban-related tasks, and develops an open-source library for geospatial data processing.
Research interests
- Geospatial Data
- Urban Data Science
- Natural Language Processing
- Representation Learning
Research groups
Education
- 2020
BSc in Computer Science
Wrocław University of Science and Technology
- 2021
MSc in Data Science
Wrocław University of Science and Technology
Publications8
Evaluation of code LLMs on geospatial code generation
Piotr Ł. Gramacki, Piotr Szymański, Bruno Martins
ACM
2024
Massively Multilingual Corpus of Sentiment Datasets and Multi-faceted Sentiment Classification Benchmark
Łukasz M. Augustyniak, Szymon Woźniak, Marcin Gruza, Piotr Ł Gramacki, Krzysztof Rajda, Tomasz Kajdanowicz, Mikołaj Morzy
Neural Information Processing Systems Foundation
2023
Utilizing OSM data in geospatial representation learning
Piotr Ł. Gramacki, Kacper Leśniara, Kamil Raczycki, Szymon Woźniak, Piotr Szymański
W: Proceedings of the OSM Science at State of the Map Europe 2023, Antwerp, Belgium, 10-12 November 2023 / eds. Minghini, M. [i in.]. [B.w. : b.m., 2023]
2023
SRAI: Towards standardization of geospatial AI
Piotr Ł. Gramacki, Kacper Leśniara, Kamil Raczycki, Szymon Woźniak, Marcin Przymus, Piotr Szymański
Proceedings of the 6th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery
2023
Resources and few-shot learners for in-context learning in slavic languages
Piotr Ł Gramacki, Michal Štefánik, Marek Kaldcík, Petr Sojka
Association for Computational Linguistics
2023
Assessment of Massively Multilingual Sentiment Classifiers
Krzysztof Rajda, Łukasz M Augustyniak, Piotr Ł Gramacki, Marcin Gruza, Szymon Woźniak, Tomasz Kajdanowicz
Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis
2022
gtfs2vec: learning GTFS embeddings for comparing public transport offer in microregions
Piotr Ł. Gramacki, Szymon Woźniak, Piotr Szymański
ACM
2021