Daniel Ochs

Hey, my name is Daniel. I am a PhD student at the Artificial Intelligence and Machine Learning Lab of TU Darmstadt. My research is centered on bringing symbolic and neural systems closer to solve challenging problems like understanding and reasoning about visual scenes. Currently, I am working on the advancement of deep probabilistic programming languages and how we can monitor our ever-changing planet using satellite imagery. I am supervised by Prof. Kristian Kersting and Dr. Devendra Singh Dhami.

news

Jan 10, 2024	Want to learn how to use transformer architectures for automatic pipeline monitoring with low-resolution satellite imagery? Check out our newly published paper in Remote Sensing: Effective Risk Detection for Natural Gas Pipelines Using Low-Resolution Satellite Images.
Nov 16, 2023	Our paper Scalable Neural-Probabilistic Answer Set Programming is now published in JAIR . Check it out here.
Jul 31, 2023	Last week I attended the first European Summer School on Artificial Intelligence (ESSAI). It was a cool experience seeing all the other European PhD students and openly discussing their research with them. Also, thanks for the nice lectures I was able to attend. Hope to see you again next year!
Jun 16, 2023	We got a new arxiv preprint on Scalable Neural-Probabilistic Answer Set Programming!. Check out how we used SLASH for VQA and how you can prune stochastically insignificant parts of the (ground) program to speed up reasoning without sacrificing predictive performance.

selected publications

2024

Effective Risk Detection for Natural Gas Pipelines Using Low-Resolution Satellite Images

Daniel Ochs, Karsten Wiertz, Sebastian Bußmann, Kristian Kersting, and Devendra Singh Dhami

Remote Sensing, 2024

Bib HTML

@article{pipeline,
  author = {Ochs, Daniel and Wiertz, Karsten and Bußmann, Sebastian and Kersting, Kristian and Dhami, Devendra Singh},
  title = {Effective Risk Detection for Natural Gas Pipelines Using Low-Resolution Satellite Images},
  journal = {Remote Sensing},
  volume = {16},
  year = {2024},
  number = {2},
  article-number = {266},
}

2023

Scalable Neural-Probabilistic Answer Set Programming

Arseny Skryagin, Daniel Ochs, Devendra Singh Dhami, and Kristian Kersting

Journal of Artificial Intelligence Research (JAIR) , 2023

Bib HTML

@article{same,
  year = { 2023 },
  crossref = { https://github.com/ml-research/SLASH },
  title = { Scalable Neural-Probabilistic Answer Set Programming },
  pages = { 579--617 },
  volume = { 78 },
  journal = { Journal of Artificial Intelligence Research (JAIR) },
  author = {Skryagin, Arseny and Ochs, Daniel and Dhami, Devendra Singh and Kersting, Kristian},
}

2022

Neural-Probabilistic Answer Set Programming

Arseny Skryagin, Wolfgang Stammer, Daniel Ochs, Devendra Singh Dhami, and Kristian Kersting

In Proceedings of the 19th International Conference on Principles of Knowledge Representation and Reasoning (KR), 2022

Bib HTML

@inproceedings{slash,
  author = {Skryagin, Arseny and Stammer, Wolfgang and Ochs, Daniel and Dhami, Devendra Singh and Kersting, Kristian},
  title = {Neural-Probabilistic Answer Set Programming},
  booktitle = {Proceedings of the 19th International Conference on Principles of
                    Knowledge Representation and Reasoning ({KR})},
  year = {2022},
}