default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDLukas Galke Poech
Lukas Galke – Lukas Paul Achatius Galke
Person information
- affiliation: University of Southern Denmark, Department of Mathematics and Computer Science, Odense, Denmark
- affiliation: Max Planck Institute for Psycholinguistics, Nijmegen, The Netherlands
- affiliation: ZBW - Leibniz Information Centre for Economics, Kiel, Germany
- affiliation: University of Kiel, Germany
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2026
[c29]Mogens Henrik From, Jacob Nielsen, Lukas Galke, Peter Schneider-Kamp:
DeToNATION: Decoupled Torch Network-Aware Training on Interlinked Online Nodes. AAAI 2026: 21128-21135- [i38]Jacob Nielsen, Stine Lyngsø Beltoft, Peter Schneider-Kamp, Lukas Galke Poech:
SDUs DAISY: A Benchmark for Danish Culture. CoRR abs/2601.19930 (2026) - [i37]Annemette Brok Pirchert, Jacob Nielsen, Mogens Henrik From, Lukas Galke Poech, Peter Schneider-Kamp:
FlexMoRE: A Flexible Mixture of Rank-heterogeneous Experts for Efficient Federatedly-trained Large Language Models. CoRR abs/2602.08818 (2026) - [i36]William Brach, Tomas Bedej, Jacob Nielsen, Jacob Pichna, Juraj Bedej, Eemeli Saarensilta, Julie Dupouy, Gianluca Barmina, Andrea Blasi Núñez, Peter Schneider-Kamp, Kristián Kostál, Michal Ries, Lukas Galke Poech:
SommBench: Assessing Sommelier Expertise of Language Models. CoRR abs/2603.12117 (2026) - 2025
- [c28]Jacob Nielsen, Peter Schneider-Kamp, Lukas Galke:
Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models? ACL (Findings) 2025: 13483-13493 - [c27]Marcel Hoffmann
, Lukas Galke, Ansgar Scherp:
Gumbel-MPNN: Graph Rewiring with Gumbel-Softmax. ECAI 2025: 2442-2449 - [c26]Richard Sléher, William Brach, Tibor Sloboda, Kristián Kostál, Lukas Galke:
Guarded Query Routing for Large Language Models. ECAI 2025: 4129-4136 - [c25]Jacob Nielsen, Lukas Galke, Peter Schneider-Kamp:
When Are 1.58 Bits Enough? A Bottom-up Exploration of Quantization-Aware Training with Ternary Weights. ICAART (3) 2025: 1440-1449 - [c24]Andor Diera, Lukas Galke, Fabian Karl, Ansgar Scherp:
Efficient Continual Learning for Small Language Models with a Discrete Key-Value Bottleneck. ICNLSP 2025: 162-176 - [c23]Thao Anh Dang, Limor Raviv, Lukas Galke:
Tokenization and Morphology in Multilingual Language Models: A Comparative Analysis of mT5 and ByT5. ICNLSP 2025: 242-257 - [c22]Danial Namazifard, Lukas Galke Poech:
Isolating Culture Neurons in Multilingual Large Language Models. IJCNLP-AACL (Findings) 2025: 768-785 - [c21]Andrea Blasi Núñez, Lukas Paul Achatius Galke, Peter Schneider-Kamp:
MLDataForge: Accelerating Large-Scale Dataset Preprocessing and Access for Multimodal Foundation Model Training. RANLP 2025: 175-183 - [e1]Mourad Abbas, Tariq Yousef, Lukas Galke:
Proceedings of the 8th International Conference on Natural Language and Speech Processing, ICNLSP 2025, Southern Denmark University, Odense, Denmark, August 25-27, 2025. Association for Computational Linguistics 2025, ISBN 979-8-89176-297-8 [contents] - [i35]Yousef Younes, Lukas Galke, Ansgar Scherp:
A Transformer-based Autoregressive Decoder Architecture for Hierarchical Text Classification. CoRR abs/2501.13598 (2025) - [i34]Mogens Henrik From, Jacob Nielsen, Lukas Galke, Peter Schneider-Kamp:
FlexDeMo: Decoupled Momentum Optimization for Fully and Hybrid Sharded Training. CoRR abs/2502.06728 (2025) - [i33]Jacob Nielsen, Peter Schneider-Kamp, Lukas Galke:
Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models? CoRR abs/2502.11895 (2025) - [i32]Richard Sléher, William Brach, Tibor Sloboda, Kristián Kostál, Lukas Galke:
Guarded Query Routing for Large Language Models. CoRR abs/2505.14524 (2025) - [i31]Eva Seidlmayer, Lukas Galke, Konrad U. Förstner:
Four Shades of Life Sciences: A Dataset for Disinformation Detection in the Life Sciences. CoRR abs/2507.03488 (2025) - [i30]Danial Namazifard, Lukas Galke:
Isolating Culture Neurons in Multilingual Large Language Models. CoRR abs/2508.02241 (2025) - [i29]Kenneth C. Enevoldsen, Kristian Nørgaard Jensen, Jan Kostkan, Balázs Szabó, Márton Kardos, Kirten Vad, Johan Heinsen, Andrea Blasi Núñez, Gianluca Barmina, Jacob Nielsen, Rasmus Larsen, Peter Bjerregaard Vahlstrup, Per Møldrup-Dalum, Desmond Elliott, Lukas Galke, Peter Schneider-Kamp, Kristoffer L. Nielbo:
Dynaword: From One-shot to Continuously Developed Datasets. CoRR abs/2508.02271 (2025) - [i28]Filippo Tonini, Lukas Galke:
Super-additive Cooperation in Language Model Agents. CoRR abs/2508.15510 (2025) - [i27]Marcel Hoffmann, Lukas Galke, Ansgar Scherp:
Gumbel-MPNN: Graph Rewiring with Gumbel-Softmax. CoRR abs/2508.17531 (2025) - [i26]Stine Lyngsø Beltoft, Lukas Galke:
Not Everything That Counts Can Be Counted: A Case for Safe Qualitative AI. CoRR abs/2511.09325 (2025) - [i25]William Brach, Lukas Galke:
Chain of Summaries: Summarization Through Iterative Questioning. CoRR abs/2511.15719 (2025) - [i24]Gianluca Barmina, Nathalie Carmen Hau Norman, Peter Schneider-Kamp, Lukas Galke Poech:
DaLA: Danish Linguistic Acceptability Evaluation Guided by Real World Errors. CoRR abs/2512.04799 (2025) - [i23]Niklas Mellgren, Peter Schneider-Kamp, Lukas Galke Poech:
Training Language Models to Use Prolog as a Tool. CoRR abs/2512.07407 (2025) - 2024
- [j4]Eva Seidlmayer, Tetyana Melnychuk, Lukas Galke, Lisa Kühnel, Klaus Tochtermann, Carsten Schultz, Konrad U. Förstner:
Research topic displacement and the lack of interdisciplinarity: lessons from the scientific response to COVID-19. Scientometrics 129(9): 5141-5179 (2024) - [j3]Tetyana Melnychuk, Lukas Galke, Eva Seidlmayer, Stefanie Bröring, Konrad U. Förstner, Klaus Tochtermann, Carsten Schultz:
Development of Similarity Measures From Graph-Structured Bibliographic Metadata: An Application to Identify Scientific Convergence. IEEE Trans. Engineering Management 71: 9171-9187 (2024) - [c20]Marcel Hoffmann, Lukas Galke, Ansgar Scherp:
POWN: Prototypical Open-World Node Classification. CoLLAs 2024: 672-691 - [c19]Yousef Younes, Lukas Galke, Ansgar Scherp:
RADAr: A Transformer-Based Autoregressive Decoder Architecture for Hierarchical Text Classification. ECAI 2024: 1559-1566 - [i22]Lukas Galke, Limor Raviv:
Emergent communication and learning pressures in language models: a language evolution perspective. CoRR abs/2403.14427 (2024) - [i21]Marcel Hoffmann, Lukas Galke, Ansgar Scherp:
POWN: Prototypical Open-World Node Classification. CoRR abs/2406.09926 (2024) - [i20]Thao Anh Dang, Limor Raviv, Lukas Galke:
Tokenization and Morphology in Multilingual Language Models: A Comparative Analysis of mT5 and ByT5. CoRR abs/2410.11627 (2024) - [i19]Jacob Nielsen, Lukas Galke, Peter Schneider-Kamp:
When are 1.58 bits enough? A Bottom-up Exploration of BitNet Quantization. CoRR abs/2411.05882 (2024) - [i18]Nerijus Bertalis, Paul Granse, Ferhat Gül, Florian Hauss, Leon Menkel, David Schüler, Tom Speier, Lukas Galke, Ansgar Scherp:
Hierarchical Text Classification (HTC) vs. eXtreme Multilabel Classification (XML): Two Sides of the Same Medal. CoRR abs/2411.13687 (2024) - [i17]Andor Diera, Lukas Galke, Ansgar Scherp:
Isotropy Matters: Soft-ZCA Whitening of Embeddings for Semantic Code Search. CoRR abs/2411.17538 (2024) - [i16]Andor Diera, Lukas Galke, Fabian Karl, Ansgar Scherp:
Continual Learning for Encoder-only Language Models via a Discrete Key-Value Bottleneck. CoRR abs/2412.08528 (2024) - 2023
- [b1]Lukas Galke:
Representation Learning for Texts and Graphs: A Unified Perspective on Efficiency, Multimodality, and Adaptability. University of Kiel, Germany, 2023 - [j2]Lukas Galke, Iacopo Vagliano, Benedikt Franke, Tobias Zielke, Marcel Hoffmann, Ansgar Scherp:
Lifelong learning on evolving graphs under the constraints of imbalanced classes and new classes. Neural Networks 164: 156-176 (2023) - [c18]Marcel Hoffmann, Lukas Galke, Ansgar Scherp:
Open-World Lifelong Graph Learning. IJCNN 2023: 1-9 - [i15]Lukas Galke, Yoav Ram, Limor Raviv:
What makes a language easy to deep-learn? CoRR abs/2302.12239 (2023) - [i14]Marcel Hoffmann, Lukas Galke, Ansgar Scherp:
Open-World Lifelong Graph Learning. CoRR abs/2310.12565 (2023) - [i13]Andor Diera, Abdelhalim Hafedh Dahou, Lukas Galke, Fabian Karl, Florian Sihler, Ansgar Scherp:
GenCodeSearchNet: A Benchmark Test Suite for Evaluating Generalization in Programming Language Understanding. CoRR abs/2311.09707 (2023) - 2022
- [j1]Iacopo Vagliano, Lukas Galke, Ansgar Scherp:
Recommendations for item set completion: on the semantics of item co-occurrence with data sparsity, input size, and input modalities. Inf. Retr. J. 25(3): 269-305 (2022) - [c17]Lukas Galke, Ansgar Scherp:
Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP. ACL (1) 2022: 4038-4051 - [c16]Lukas Galke, Isabelle Cuber, Christoph Meyer, Henrik Ferdinand Nölscher, Angelina Sonderecker, Ansgar Scherp:
General Cross-Architecture Distillation of Pretrained Language Models into Matrix Embeddings. IJCNN 2022: 1-10 - [i12]Andor Diera, Bao Xin Lin, Bhakti Khera, Tim Meuser, Tushar Singhal, Lukas Galke, Ansgar Scherp:
Bag-of-Words vs. Sequence vs. Graph vs. Hierarchy for Single- and Multi-Label Text Classification. CoRR abs/2204.03954 (2022) - [i11]Lukas Galke, Yoav Ram, Limor Raviv:
Emergent Communication for Understanding Human Language Evolution: What's Missing? CoRR abs/2204.10590 (2022) - 2021
- [c15]Lukas Galke, Eva Seidlmayer, Gavin Lüdemann, Lisa Langnickel, Tetyana Melnychuk, Konrad U. Förstner, Klaus Tochtermann, Carsten Schultz:
COVID-19++: A Citation-Aware Covid-19 Dataset for the Analysis of Research Dynamics. IEEE BigData 2021: 4350-4355 - [c14]Lukas Galke, Benedikt Franke, Tobias Zielke, Ansgar Scherp:
Lifelong Learning of Graph Neural Networks for Open-World Node Classification. IJCNN 2021: 1-8 - [i10]Iacopo Vagliano, Lukas Galke, Ansgar Scherp:
Recommendations for Item Set Completion: On the Semantics of Item Co-Occurrence With Data Sparsity, Input Size, and Input Modalities. CoRR abs/2105.04376 (2021) - [i9]Lukas Galke, Ansgar Scherp:
Forget me not: A Gentle Reminder to Mind the Simple Multi-Layer Perceptron Baseline for Text Classification. CoRR abs/2109.03777 (2021) - [i8]Lukas Galke, Isabelle Cuber, Christoph Meyer, Henrik Ferdinand Nölscher, Angelina Sonderecker, Ansgar Scherp:
New Students on Sesame Street: What Order-Aware Matrix Embeddings Can Learn from BERT. CoRR abs/2109.08449 (2021) - [i7]Lukas Galke, Iacopo Vagliano, Benedikt Franke, Tobias Zielke, Ansgar Scherp:
Lifelong Learning in Evolving Graphs with Limited Labeled Data and Unseen Class Detection. CoRR abs/2112.10558 (2021) - 2020
- [c13]Eva Seidlmayer, Jakob Voß, Tetyana Melnychuk, Lukas Galke, Klaus Tochtermann, Carsten Schultz, Konrad U. Förstner:
ORCID for Wikidata. Data enrichment for scientometric applications. Wikidata@ISWC 2020 - [d2]Lukas Galke, Benedikt Franke, Tobias Zielke, Ansgar Scherp:
Lifelong Learning of Graph Neural Networks for Open-World Node Classification. Zenodo, 2020
- [d1]Florian Mai, Lukas Galke, Ansgar Scherp:
Embeddings from "CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix-Space Model". Zenodo, 2020 - [i6]Lukas Galke, Iacopo Vagliano, Ansgar Scherp:
Incremental Training of Graph Neural Networks on Temporal Graphs under Distribution Shift. CoRR abs/2006.14422 (2020)
2010 – 2019
- 2019
- [c12]Lukas Galke, Tetyana Melnychuk, Eva Seidlmayer, Steffen Trog, Konrad U. Förstner, Carsten Schultz, Klaus Tochtermann:
Inductive Learning of Concept Representations from Library-Scale Bibliographic Corpora. GI-Jahrestagung 2019: 219-232 - [c11]Lukas Galke, Florian Mai, Ansgar Scherp:
What If We Encoded Words as Matrices and Used Matrix Multiplication as Composition Function? GI-Jahrestagung 2019: 287-288 - [c10]Eva Seidlmayer, Lukas Galke, Tetyana Melnychuk:
Take it Personally - A Python library for data enrichment for infometrical applications. SEMANTiCS (Posters & Demos) 2019 - [c9]Florian Mai, Lukas Galke, Ansgar Scherp:
CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model. ICLR (Poster) 2019 - [i5]Florian Mai, Lukas Galke, Ansgar Scherp:
CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model. CoRR abs/1902.06423 (2019) - [i4]Lukas Galke, Iacopo Vagliano, Ansgar Scherp:
Can Graph Neural Networks Go "Online"? An Analysis of Pretraining and Inference. CoRR abs/1905.06018 (2019) - [i3]Lukas Galke, Florian Mai, Iacopo Vagliano, Ansgar Scherp:
Multi-Modal Adversarial Autoencoders for Recommendations of Citations and Subject Labels. CoRR abs/1907.12366 (2019) - 2018
- [c8]Lukas Galke, Gunnar Gerstenkorn, Ansgar Scherp:
A Case Study of Closed-Domain Response Suggestion with Limited Training Data. DEXA Workshops 2018: 218-229 - [c7]Ahmed Saleh, Tilman Beck, Lukas Galke, Ansgar Scherp:
Performance Comparison of Ad-Hoc Retrieval Models over Full-Text vs. Titles of Documents. ICADL 2018: 290-303 - [c6]Anne Lauscher, Kai Eckert, Lukas Galke, Ansgar Scherp, Syed Tahseen Raza Rizvi, Sheraz Ahmed, Andreas Dengel, Philipp Zumstein, Annette Klein:
Linked Open Citation Database: Enabling Libraries to Contribute to an Open and Interconnected Citation Graph. JCDL 2018: 109-118 - [c5]Florian Mai, Lukas Galke, Ansgar Scherp:
Using Deep Learning for Title-Based Semantic Subject Indexing to Reach Competitive Performance to Full-Text. JCDL 2018: 169-178 - [c4]Iacopo Vagliano, Lukas Galke, Florian Mai, Ansgar Scherp:
Using Adversarial Autoencoders for Multi-Modal Automatic Playlist Continuation. RecSys Challenge 2018: 5:1-5:6 - [c3]Lukas Galke, Florian Mai, Iacopo Vagliano, Ansgar Scherp:
Multi-Modal Adversarial Autoencoders for Recommendations of Citations and Subject Labels. UMAP 2018: 197-205 - [i2]Florian Mai, Lukas Galke, Ansgar Scherp:
Using Deep Learning For Title-Based Semantic Subject Indexing To Reach Competitive Performance to Full-Text. CoRR abs/1801.06717 (2018) - 2017
- [c2]Lukas Galke, Ahmed Saleh, Ansgar Scherp:
Word Embeddings for Practical Information Retrieval. GI-Jahrestagung 2017: 2155-2167 - [c1]Lukas Galke, Florian Mai, Alan Schelten, Dennis Brunsch, Ansgar Scherp:
Using Titles vs. Full-text as Source for Automated Semantic Document Annotation. K-CAP 2017: 20:1-20:4 - [i1]Lukas Galke, Florian Mai, Alan Schelten, Dennis Brunsch, Ansgar Scherp:
Comparing Titles vs. Full-text for Multi-Label Classification of Scientific Papers and News Articles. CoRR abs/1705.05311 (2017)
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2026-04-12 23:39 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
