Aleksandra Piktus
- Artificial Intelligence top 10%
- Computer Vision and Pattern Recognition
- Information Systems
- Sociology and Political Science
- Communication
- Co-authors
- Sebastian RiedelFabio PetroniÉdouard GraveFabrizio SilvestriPatrick LewisPiotr BojanowskiXilun ChenVladimir Karpukhin
- Topics
- Natural Language Processing Techniques (10 papers)Topic Modeling (9 papers)Multimodal Machine Learning Applications (4 papers)
- Journals
- NatureNature Machine IntelligenceIRIS Research product catalog (Sapienza University of Rome)
- Partner nations
- GermanyIsraelUnited Kingdom
In The Last Decade
Aleksandra Piktus
10 papers receiving 116 citations
Peers
Comparison fields: 5 of 22
- Artificial Intelligence 115
- Computer Vision and Pattern Recognition 30
- Information Systems 22
- Sociology and Political Science 14
- Communication 8
Countries citing papers authored by Aleksandra Piktus
This map shows the geographic impact of Aleksandra Piktus's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Aleksandra Piktus with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Aleksandra Piktus more than expected).
Fields of papers citing papers by Aleksandra Piktus
This network shows the impact of papers produced by Aleksandra Piktus. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Aleksandra Piktus. The network helps show where Aleksandra Piktus may publish in the future.
Co-authorship network of co-authors of Aleksandra Piktus
This figure shows the co-authorship network connecting the top 25 collaborators of Aleksandra Piktus. A scholar is included among the top collaborators of Aleksandra Piktus based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Aleksandra Piktus. Aleksandra Piktus is excluded from the visualization to improve readability, since they are connected to all nodes in the network.
All Works
| # | Work | Indexed citations |
|---|---|---|
| 1 | 0 | |
| 2 | 10 | |
| 3 | 1 | |
| 4 | 12 | |
| 5 | 2 | |
| 6 | 2 | |
| 7 | 30 | |
| 8 | How Context Affects Language Models' Factual Predictions | 16 |
| 9 | Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks | 2 |
| 10 | 21 | |
| 11 | 27 |
About Aleksandra Piktus
Aleksandra Piktus is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Communication, having authored 11 papers that have together received 123 indexed citations. Recurring topics across this work include Natural Language Processing Techniques (10 papers), Topic Modeling (9 papers) and Multimodal Machine Learning Applications (4 papers). The work is most often cited by research in Artificial Intelligence (115 citations), Health Informatics (4 citations) and Computer Vision and Pattern Recognition (30 citations). Aleksandra Piktus has collaborated with scholars based in Germany, Israel and United Kingdom. Frequent co-authors include Sebastian Riedel, Fabio Petroni, Édouard Grave, Fabrizio Silvestri, Patrick Lewis, Piotr Bojanowski, Xilun Chen, Vladimir Karpukhin, Sonal Gupta and Kushal Lakhotia. Their work appears in journals such as Nature, Nature Machine Intelligence and IRIS Research product catalog (Sapienza University of Rome).
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.