updated publications

_bibliography/lab_publications.bib

@@ -1173,3 +1173,65 @@ @article{jhawar_how_2023
 	pages = {20230290},
 	file = {Full Text PDF:/Users/tim/Zotero/storage/K76A2BQQ/Jhawar et al. - 2023 - How honeybees respond to heat stress from the indi.pdf:application/pdf},
 }
+
+
+@inproceedings{solopova_check_2024,
+	address = {St. Julians, Malta},
+	title = {Check {News} in {One} {Click}: {NLP}-{Empowered} {Pro}-{Kremlin} {Propaganda} {Detection}},
+	shorttitle = {Check {News} in {One} {Click}},
+	url = {https://aclanthology.org/2024.eacl-demo.6},
+	abstract = {Many European citizens become targets of the Kremlin propaganda campaigns, aiming to minimise public support for Ukraine, foster a climate of mistrust and disunity, and shape elections (Meister, 2022). To address this challenge, we developed “Check News in 1 Click”, the first NLP-empowered pro-Kremlin propaganda detection application available in 7 languages, which provides the lay user with feedback on their news, and explains manipulative linguistic features and keywords. We conducted a user study, analysed user entries and models' behaviour paired with questionnaire answers, and investigated the advantages and disadvantages of the proposed interpretative solution.},
+	urldate = {2024-04-07},
+	booktitle = {Proceedings of the 18th {Conference} of the {European} {Chapter} of the {Association} for {Computational} {Linguistics}: {System} {Demonstrations}},
+	publisher = {Association for Computational Linguistics},
+	author = {Solopova, Veronika and Herman, Viktoriia and Benzmüller, Christoph and Landgraf, Tim},
+	editor = {Aletras, Nikolaos and De Clercq, Orphee},
+	month = mar,
+	year = {2024},
+	pages = {44--51},
+	file = {Full Text PDF:/Users/tim/Zotero/storage/Y8UMKKYC/Solopova et al. - 2024 - Check News in One Click NLP-Empowered Pro-Kremlin.pdf:application/pdf},
+}
+
+@misc{granz_weiper_2024,
+	title = {{WeiPer}: {OOD} {Detection} using {Weight} {Perturbations} of {Class} {Projections}},
+	shorttitle = {{WeiPer}},
+	url = {http://arxiv.org/abs/2405.17164},
+	doi = {10.48550/arXiv.2405.17164},
+	abstract = {Recent advances in out-of-distribution (OOD) detection on image data show that pre-trained neural network classifiers can separate in-distribution (ID) from OOD data well, leveraging the class-discriminative ability of the model itself. Methods have been proposed that either use logit information directly or that process the model's penultimate layer activations. With "WeiPer", we introduce perturbations of the class projections in the final fully connected layer which creates a richer representation of the input. We show that this simple trick can improve the OOD detection performance of a variety of methods and additionally propose a distance-based method that leverages the properties of the augmented WeiPer space. We achieve state-of-the-art OOD detection results across multiple benchmarks of the OpenOOD framework, especially pronounced in difficult settings in which OOD samples are positioned close to the training set distribution. We support our findings with theoretical motivations and empirical observations, and run extensive ablations to provide insights into why WeiPer works.},
+	urldate = {2024-06-18},
+	publisher = {arXiv},
+	author = {Granz, Maximilian and Heurich, Manuel and Landgraf, Tim},
+	month = may,
+	year = {2024},
+	note = {arXiv:2405.17164 [cs]},
+	keywords = {Computer Science - Machine Learning},
+	file = {arXiv Fulltext PDF:/Users/tim/Zotero/storage/GKC46CT6/Granz et al. - 2024 - WeiPer OOD Detection using Weight Perturbations o.pdf:application/pdf;arXiv.org Snapshot:/Users/tim/Zotero/storage/TECJLEHU/2405.html:text/html},
+}
+
+@misc{mellert_collective_2024,
+	title = {Collective flow of circadian clock information in honeybee colonies},
+	copyright = {© 2024, Posted by Cold Spring Harbor Laboratory. The copyright holder for this pre-print is the author. All rights reserved. The material may not be redistributed, re-used or adapted without the author's permission.},
+	url = {https://www.biorxiv.org/content/10.1101/2024.07.29.605620v1},
+	doi = {10.1101/2024.07.29.605620},
+	abstract = {Honeybee colonies exhibit a collective circadian rhythm reflecting the periodic dynamics of the environment. Thousands of workers, including those engaged in in-hive tasks, must synchronize in various processes that may be rhythmic, such as nectar inflows, or non-rhythmic, such as brood care but it remains unknown how those different rhythms are integrated into a colony-level circadian rhythm. Using an AI-driven automated tracking system, we obtained uninterrupted long-term tracking of all individuals in two honeybee colonies. We demonstrate that circadian rhythmicity is present across all age groups and that this rhythm is entrained into all individuals, however, with peak activity shifting by up to 2 hours in workers furthest from the entrance. Extensive data analysis and an agent-based model suggest that mechanical interactions between individuals facilitate the transfer of movement speed, and hence Zeitgeber information. Finally, we show that this speed transfer leads to a collective slow wave of activity that initiates at the nest entrance, spreading throughout the nest. This simple mechanism, workers bumping into each other, enables colonies to entrain their rhythm to the daily cycle of the external environment and, because of the spatial organization of the nest, activates different groups of workers sequentially. The speed transfer interactions demonstrate a tightly-tuned mechanism that underlines the elegant self-organization of the superorganism.},
+	language = {en},
+	urldate = {2024-10-01},
+	publisher = {bioRxiv},
+	author = {Mellert, Julia and Kłos, Weronika and Dormagen, David M. and Wild, Benjamin and Zachariae, Adrian and Smith, Michael L. and Galizia, C. Giovanni and Landgraf, Tim},
+	month = jul,
+	year = {2024},
+	note = {Pages: 2024.07.29.605620
+Section: New Results},
+	file = {Full Text PDF:/Users/tim/Zotero/storage/X53Y4FDN/Mellert et al. - 2024 - Collective flow of circadian clock information in honeybee colonies.pdf:application/pdf},
+}
+
+@inproceedings{solopova_ai-powered_2024,
+	title = {{AI}-powered automatic feedback on reflective writing},
+	url = {http://fis.uni-bamberg.de/bitstreams/c052c8b0-c990-4780-99f0-8b387c693fc5/download},
+	urldate = {2024-10-01},
+	booktitle = {Annual {Conference} of the {European} {Teacher} {Education} {Network} ({ETEN})“{Teacher} {Education}–{Connecting} {Glocal}”},
+	publisher = {Otto-Friedrich-Universität},
+	author = {Solopova, Veronika and Romeike, Ralf and Gläser-Zikuda, Michaela and Benzmüller, Christoph and Landgraf, Tim and Hofmann, Florian and Schießl, Jessica and Zhang, Chengming and Plößl, Lea and Witte, Sascha},
+	year = {2024},
+	file = {Available Version (via Google Scholar):/Users/tim/Zotero/storage/EK32PDPT/Solopova et al. - 2024 - AI-powered automatic feedback on reflective writing.pdf:application/pdf},
+}