ML Anthology

Exploiting Cultural Biases via Homoglyphs inText-to-Image Synthesis (Abstract Reprint)

Lukas Struppek, Dominik Hintersdorf, Felix Friedrich, Manuel Brack, Patrick Schramowski, Kristian Kersting
IJCAI 2024 pp. 8486
doi:10.24963/ijcai.2024/958 /ijcai/2024/struppek2024ijcai-exploiting/

Abstract

Deterministic partially observable Markov decision processes (DetPOMDPs) often arise in planning problems where the agent is uncertain about its environmental state but can act and observe deterministically. In this paper, we propose DetMCVI, an adaptation of the Monte Carlo Value Iteration (MCVI) algorithm for DetPOMDPs, which builds policies in the form of finite-state controllers (FSCs). DetMCVI solves large problems with a high success rate, outperforming existing baselines for DetPOMDPs. We also verify the performance of the algorithm in a real-world mobile robot forest mapping scenario.

PDF IJCAI Semantic Scholar

Cite

Text

Struppek et al. "Exploiting Cultural Biases via Homoglyphs inText-to-Image Synthesis (Abstract Reprint)." International Joint Conference on Artificial Intelligence, 2024. doi:10.24963/ijcai.2024/958

Markdown

[Struppek et al. "Exploiting Cultural Biases via Homoglyphs inText-to-Image Synthesis (Abstract Reprint)." International Joint Conference on Artificial Intelligence, 2024.](https://mlanthology.org/ijcai/2024/struppek2024ijcai-exploiting/) doi:10.24963/ijcai.2024/958

BibTeX

@inproceedings{struppek2024ijcai-exploiting,
  title     = {{Exploiting Cultural Biases via Homoglyphs inText-to-Image Synthesis (Abstract Reprint)}},
  author    = {Struppek, Lukas and Hintersdorf, Dominik and Friedrich, Felix and Brack, Manuel and Schramowski, Patrick and Kersting, Kristian},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {8486},
  doi       = {10.24963/ijcai.2024/958},
  url       = {https://mlanthology.org/ijcai/2024/struppek2024ijcai-exploiting/}
}