Aleksandar Stanić

Email / CV / GitHub / Google Scholar / Twitter / LinkedIn / PhD Thesis

I am a Research Scientist at Google DeepMind working on vision and language models and other fundamental problems in Artificial Intelligence.

Previously, I obtained a PhD in Informatics (Artificial Intelligence) at the Swiss AI lab IDSIA, under the supervision of Jürgen Schmidhuber, where I worked on unsupervised/self-supervised representation learning. In particular, I am interested in learning structured (object-centric/discrete) representations with neural networks directly from raw visual input and grounding them in language. The goal is to learn object-centric representations that facilitate efficient relational reasoning, enable combinatorial (out-of-distribution) generalization of neural networks and improve their sample efficiency on the downstream task. In my PhD, I explored learning such representations in both generative and contrastive manner, as well as in an RL setup. Previously, I worked on analyzing feature extraction capabilities of convolutional neural networks via frame theory.

In 2023 I was an intern at Google with Sergi Caelles and Michael Tschannen.

In 2022 I was a Research Scientist Intern at DeepMind working with Alexander Lerchner, Loic Matthey, Jovana Mitrovic, Matko Bosnjak and Andre Saraiva.

Previously I was a Student Researcher at Google Brain with David Ha and Yujin Tang.

Prior to my PhD I received a Master’s degree from ETH Zurich, and worked as a Research Engineer at uniqFEED, a spin-off company of ETH Zurich.

selected publications

Towards Truly Zero-shot Compositional Visual Reasoning with LLMs as Programmers

Aleksandar Stanić, Sergi Caelles, and Michael Tschannen

arXiv preprint arXiv:2401.01974, 2024

arXiv Bib

@article{stanic2024towards,
  title = {Towards Truly Zero-shot Compositional Visual Reasoning with LLMs as Programmers},
  author = {Stani{\'c}, Aleksandar and Caelles, Sergi and Tschannen, Michael},
  journal = {arXiv preprint arXiv:2401.01974},
  year = {2024},
}

Contrastive Training of Complex-Valued Autoencoders for Object Discovery

Aleksandar Stanić^*, Anand Gopalakrishnan^*, Kazuki Irie, and 1 more author

In Neural Information Processing Systems (NeurIPS), 2023

arXiv Bib Code

@inproceedings{stanic2023contrastive,
  title = {Contrastive Training of Complex-Valued Autoencoders for Object Discovery},
  author = {Stani{\'c}, Aleksandar and Gopalakrishnan, Anand and Irie, Kazuki and Schmidhuber, J{\"u}rgen},
  booktitle = {Neural Information Processing Systems (NeurIPS)},
  year = {2023},
}

The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute

Aleksandar Stanić^*, Dylan Ashley, Oleg Serikov, and 5 more authors

arXiv preprint arXiv:2309.11197, 2023

arXiv Bib

@article{stanic2023languini,
  title = {The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute},
  author = {Stani{\'c}, Aleksandar and Ashley, Dylan and Serikov, Oleg and Kirsch, Louis and Faccio, Francesco and Schmidhuber, J{\"u}rgen and Hofmann, Thomas and Schlag, Imanol},
  journal = {arXiv preprint arXiv:2309.11197},
  year = {2023},
}

Learning to Generalize with Object-centric Agents in the Open World Survival Game Crafter

Aleksandar Stanić, Yujin Tang, David Ha, and 1 more author

IEEE Transactions on Games, 2023

arXiv Bib Code

@article{stanic2023learning,
  title = {Learning to Generalize with Object-centric Agents in the Open World Survival Game Crafter},
  author = {Stani{\'c}, Aleksandar and Tang, Yujin and Ha, David and Schmidhuber, J{\"u}rgen},
  journal = {IEEE Transactions on Games},
  year = {2023},
}

Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling

Djordje Miladinović, Aleksandar Stanić, Stefan Bauer, and 2 more authors

In International Conference on Learning Representations (ICLR), 2021

arXiv Bib Code

@inproceedings{miladinovic2021spatial,
  title = {Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling},
  author = {Miladinovi{\'c}, Djordje and Stani{\'c}, Aleksandar and Bauer, Stefan and Schmidhuber, J{\"u}rgen and Buhmann, Joachim},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
}

Hierarchical Relational Inference

Aleksandar Stanić, Sjoerd Steenkiste, and Jürgen Schmidhuber

In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2021

arXiv Bib Code

@inproceedings{stanic2021hierarchical,
  title = {Hierarchical Relational Inference},
  author = {Stani{\'c}, Aleksandar and van Steenkiste, Sjoerd and Schmidhuber, J{\"u}rgen},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
}