T
Tim Z. Xiao
Researcher at University College London
Publications - 6
Citations - 27
Tim Z. Xiao is an academic researcher from University College London. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 1, co-authored 2 publications receiving 7 citations.
Papers
More filters
Journal Article
Wat zei je? Detecting Out-of-Distribution Translations with Variational Transformers
TL;DR: A new measure of uncertainty designed specifically for long sequences of discrete random variables is developed and 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.
Proceedings ArticleDOI
Iterative Teaching by Data Hallucination
Zeju Qiu,Weiyang Liu,Tim Z. Xiao,Zhen Liu,Umang Bhatt,Yucen Luo,Adrian Weller,Bernhard Schölkopf +7 more
TL;DR: In this article , the authors propose data hallucination teaching (DHT) where the teacher can generate input data intelligently based on labels, the learner's status and the target concept.
Journal ArticleDOI
Out-of-Distribution Detection with Class Ratio Estimation
TL;DR: This work proposes to unify density ratio based methods under a novel framework that builds energy-based models and employs differing base distributions and proposes to directly estimate the density ratio of a data sample through class ratio estimation.
Journal ArticleDOI
Improving VAE-based Representation Learning
TL;DR: It is shown that by using a decoder that prefers to learn local features, the remaining global features can be well captured by the latent, which significantly improves performance of a downstream classi-cation task.
Proceedings ArticleDOI
Trading Information between Latents in Hierarchical Variational Autoencoders
Tim Z. Xiao,Robert Bamler +1 more
TL;DR: In this article , the authors consider hierarchical VAEs with more than one layer of latent variables and derive theoretical bounds on the performance of downstream tasks as functions of the individual layers' rates and verify their theoretical findings in large-scale experiments.