Dr. Stefan Arnold

Dr. Stefan Arnold

Akademischer Rat
Raum: Raum 5.439
Lange Gasse 20
90403 Nürnberg
Deutschland

Sprechzeiten

Nach Vereinbarung über Zoom: https://fau.zoom.us/j/97869596522

Research

Denoising Diffusion Models represent a category of generative models that employ a diffusion process in which data is gradually perturbed by adding random noise, and a parametrized reverse process tasked at iteratively denoising random noise into data.

Due to their fidelity and coverage (albeit with slower sampling), diffusion models are applied to a wide variety of generative modeling tasks, including image synthesis, image upscaling, image inpainting, and image-to-image translation such as style transfer.

By conditioning the denoising process on natural language text, diffusion models permit the generation of images that correspond to textual descriptions. This involves incorporating the intended meaning of a text into the latent representation of the diffusion model. However, natural language encompasses numerous linguistic formalisms, and it remains uncertain which of these formalisms contribute to the translation of text into images.

Using a diverse set of spatio-temporal techniques drawn from introspection analysis, my guiding research objective aims to disentangle and pinpoint which linguistic formalisms are embedded within the latent representations of diffusion models.

Publications

Workshops

  • Stefan Arnold, Rene Gröbner, and Annika Schreiner. 2024. Characterizing Stereotypical Bias from Privacy-preserving Pre-Training. In Proceedings of the Fourth Workshop on Privacy in Natural Language Processing (PrivateNLP 2024), Bangkok, Thailand. Association for Computational Linguistics.
  • Stefan Arnold, Nils Kemmerzell, and Annika Schreiner. 2023. Disentangling the Linguistic Competence of BERT subjected to Text-to-Text Privatization. In Proceedings of the Sixth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP,  Singapore, Singapore. Association for Computational Linguistics.
  • Stefan Arnold, Dilara Yesilbas, and Sven Weinzierl. 2023. Driving Context into Text-to-Text Privatization. In Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023), Toronto, Canada. Association for Computational Linguistics.
  • Stefan Arnold, Dilara Yesilbas, and Sven Weinzierl. 2023. Guiding Text-to-Text Privatization by Syntax. In Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023), Toronto, Canada. Association for Computational Linguistics.
  • Dilara Yesilbas, Stefan Arnold, and Alex Felker. 2022. Rethinking Pre-Training in Industrial Quality Control. In Proceedings of the 17th International Conference on Wirtschaftsinformatik (WI 22). Nuremberg, Germany. Association for Information Systems.

Preprints

  • Stefan Arnold, Dilara Yesilbas, Rene Gröbner, Dominik Riedelbauch, Maik Horn, and Sven Weinzierl. 2024. Documentation Practices of Artificial Intelligence. arXiv preprint arXiv:2406.18620.
  • Josephine Fischer, Stefan Arnold, and Dilara Yesilbas. 2023. Crowd-Powered Medical Diagnosis: The Potential of Crowdsourcing for Patients with Rare Diseases.
  • Stefan Arnold & Dilara Yesilbas. 2021. Demystifying the Effects of Non-Independence in Federated Learning. arXiv preprint arXiv:2103.11226.