Tim Z. Xiao

Hello! I am Tim, also known as Zhenzhong Xiao (肖镇中 in Chinese). Currently, I am doing my PhD in machine learning at the University of Tübingen with Robert Bamler, and as a visiting PhD student at MPI-IS Tübingen with Weiyang Liu and Bernhard Schölkopf.

I am also an organiser of FridayTalks@Tübingen, a bi-weekly AI research seminar aiming to provide a place for the Tübingen AI research community to exchange ideas.

Previously, I did a MRes Computational Statistics and Machine Learning at UCL with David Barber and a MSc in Computer Science at the University of Oxford with Yarin Gal. Prior to that I studied computer science at the University of Manchester for my undergraduate. At the time, I also had a one year industrial placement with Morgan Stanley, during which I worked with a global team to create tools for managing and monitoring the cloud platform with a huge number of servers located around the world.

Just like many computer scientists, I have faith in computing. Although computation will not solve all problems for you, I believe it will certainly take you closer to the answers.

news

Feb 17, 2025	I am honoured to be invited to give the scholar scientific talk at this year’s IMPRS-IS Interview Symposium! The topic is Verbalized Machine Learning, a similar talk can be found here.
Nov 25, 2024	I gave an invited lecture at the University of Michigan on the topic of Verbalized Machine Learning.
Sep 3, 2024	I have been selected by G-Research as one of the Auguest 2024 Grant Winners.

selected publications

Flipping Against All Odds: Reducing LLM Coin Flip Bias via Verbalized Rejection Sampling

Tim Z. Xiao, Johannes Zenn, Zhen Liu, Weiyang Liu, Robert Bamler, and Bernhard Schölkopf

arXiv preprint arXiv:2506.09998, 2025

arXiv Bib PDF

@article{xiao2025flipping,
  title = {Flipping Against All Odds: Reducing LLM Coin Flip Bias via Verbalized Rejection Sampling},
  author = {Xiao, Tim Z. and Zenn, Johannes and Liu, Zhen and Liu, Weiyang and Bamler, Robert and Schölkopf, Bernhard},
  journal = {arXiv preprint arXiv:2506.09998},
  year = {2025},
}

Verbalized Machine Learning: Revisiting Machine Learning with Language Models

Tim Z. Xiao, Robert Bamler, Bernhard Schölkopf, and Weiyang Liu

In Transactions on Machine Learning Research (TMLR), 2025

ICML 2024 Workshop on In-context Learning
ICML 2024 Workshop on LLMs and Cognition

arXiv Bib HTML PDF Video Code Poster

@inproceedings{xiao2025verbalized,
  title = {Verbalized Machine Learning: Revisiting Machine Learning with Language Models},
  author = {Xiao, Tim Z. and Bamler, Robert and Schölkopf, Bernhard and Liu, Weiyang},
  booktitle = {Transactions on Machine Learning Research (TMLR)},
  video = {https://www.youtube.com/watch?v=LCl_np5oPWA},
  year = {2025},
}

A Note on Generalization in Variational Autoencoders: How Effective Is Synthetic Data and Overparameterization?

Tim Z. Xiao*, Johannes Zenn*, and Robert Bamler

In Transactions on Machine Learning Research (TMLR), 2024

arXiv Bib HTML PDF

@inproceedings{xiao2024a,
  title = {A Note on Generalization in Variational Autoencoders: How Effective Is Synthetic Data and Overparameterization?},
  author = {Xiao, Tim Z. and Zenn, Johannes and Bamler, Robert},
  booktitle = {Transactions on Machine Learning Research (TMLR)},
  year = {2024},
}

A Compact Representation for Bayesian Neural Networks By Removing Permutation Symmetry

Tim Z. Xiao, Weiyang Liu, and Robert Bamler

arXiv preprint arXiv:2401.00611, 2023

NeurIPS 2023 Workshop on Unifying Representations in Neural Models

arXiv Bib HTML PDF Poster

@article{xiao2023compact,
  title = {A Compact Representation for Bayesian Neural Networks By Removing Permutation Symmetry},
  author = {Xiao, Tim Z. and Liu, Weiyang and Bamler, Robert},
  journal = {arXiv preprint arXiv:2401.00611},
  year = {2023},
}

The SVHN Dataset Is Deceptive for Probabilistic Generative Models Due to a Distribution Mismatch

Tim Z. Xiao*, Johannes Zenn*, and Robert Bamler

arXiv preprint arXiv:2312.02168, 2023

NeurIPS 2023 Workshop on Distribution Shifts

arXiv Bib HTML PDF Poster

@article{xiao2023the,
  title = {The SVHN Dataset Is Deceptive for Probabilistic Generative Models Due to a Distribution Mismatch},
  author = {Xiao, Tim Z. and Zenn, Johannes and Bamler, Robert},
  journal = {arXiv preprint arXiv:2312.02168},
  year = {2023},
}

Trading Information between Latents in Hierarchical Variational Autoencoders

Tim Z. Xiao, and Robert Bamler

In International Conference on Learning Representations (ICLR), 2023

arXiv Bib HTML PDF Code Poster Slides

@inproceedings{xiao2023trading,
  title = {Trading Information between Latents in Hierarchical Variational Autoencoders},
  author = {Xiao, Tim Z. and Bamler, Robert},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
}

Wat zei je? Detecting Out-of-Distribution Translations with Variational Transformers

Tim Z. Xiao, Aidan N. Gomez, and Yarin Gal

arXiv preprint arXiv:2006.08344, 2020

Spotlight talk, NeurIPS 2019 Workshop on Bayesian Deep Learning

Abs arXiv Bib HTML PDF Poster Slides

My master project at Oxford. In the project, we detect out-of-training-distribution sentences in Neural Machine Translation using the Bayesian Deep Learning equivalent of Transformer models. For this we develop a new measure of uncertainty designed specifically for long sequences of discrete random variables – i.e. words in the output sentence. Our new measure of uncertainty solves a major intractability in the naive application of existing approaches on long sentences. We use our new measure on a Transformer model trained with dropout approximate inference. On the task of German-English translation using WMT13 and Europarl, we show that with dropout uncertainty our measure is able to identify when Dutch source sentences, sentences which use the same word types as German, are given to the model instead of German.
@article{xiao2020wat, title = {Wat zei je? Detecting Out-of-Distribution Translations with Variational Transformers}, author = {Xiao, Tim Z. and Gomez, Aidan N. and Gal, Yarin}, journal = {arXiv preprint arXiv:2006.08344}, year = {2020}, }