Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies
if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the
same subfield and year (this is the minimum needed to enter the top 1%, not the average
within it), or reaches the top citation threshold in at least one of its specific research
topics.
Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
20181.5k citationsYarin Gal et al.Oxford University Research Archive (ORA) (University of Oxford)profile →
Inferring the effectiveness of government interventions against COVID-19
2020630 citationsJan Brauner, Sören Mindermann et al.Scienceprofile →
This map shows the geographic impact of Yarin Gal's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Yarin Gal with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Yarin Gal more than expected).
This network shows the impact of papers produced by Yarin Gal. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Yarin Gal. The network helps show where Yarin Gal may publish in the future.
Co-authorship network of co-authors of Yarin Gal
This figure shows the co-authorship network connecting the top 25 collaborators of Yarin Gal.
A scholar is included among the top collaborators of Yarin Gal based on the total number of
citations received by their joint publications. Widths of edges
represent the number of papers authors have co-authored together.
Node borders
signify the number of papers an author published with Yarin Gal. Yarin Gal is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
Rudner, Tim G. J., et al.. (2021). On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes. International Conference on Machine Learning. 9148–9156.1 indexed citations
Lyle, Clare, et al.. (2021). Speedy Performance Estimation for Neural Architecture Search. Neural Information Processing Systems. 34.2 indexed citations
7.
Zintgraf, Luisa, et al.. (2021). VariBAD: Variational Bayes-Adaptive Deep RL via Meta-Learning. Journal of Machine Learning Research. 22(289). 1–39.9 indexed citations
8.
Brauner, Jan, Sören Mindermann, Mrinank Sharma, et al.. (2020). Inferring the effectiveness of government interventions against COVID-19. Science. 371(6531).630 indexed citations breakdown →
9.
Zintgraf, Luisa, et al.. (2020). VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning. arXiv (Cornell University).9 indexed citations
10.
Rudner, Tim G. J., Dino Sejdinović, & Yarin Gal. (2020). Inter-domain Deep Gaussian Processes. Oxford University Research Archive (ORA) (University of Oxford). 8286–8294.3 indexed citations
11.
Farquhar, Sebastian, Lewis Smith, & Yarin Gal. (2020). Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations. arXiv (Cornell University). 33. 4346–4357.1 indexed citations
12.
Farquhar, Sebastian, Michael A. Osborne, & Yarin Gal. (2020). Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning.. International Conference on Artificial Intelligence and Statistics. 1352–1362.6 indexed citations
13.
Lyle, Clare, et al.. (2020). A Bayesian Perspective on Training Speed and Model Selection. Neural Information Processing Systems. 33. 10396–10408.3 indexed citations
14.
Amersfoort, Joost van, Lewis Smith, Yee Whye Teh, & Yarin Gal. (2020). Simple and Scalable Epistemic Uncertainty Estimation Using a Single Deep Deterministic Neural Network. arXiv (Cornell University). 1.9 indexed citations
15.
Gal, Yarin, et al.. (2019). Adversarial recovery of agent rewards from latent spaces of the limit order book. UPM Digital Archive (Technical University of Madrid).1 indexed citations
Smith, Lewis & Yarin Gal. (2018). Understanding Measures of Uncertainty for Adversarial Example Detection. Uncertainty in Artificial Intelligence. 560–569.12 indexed citations
18.
Alizadeh, Milad, et al.. (2018). An Empirical study of Binary Neural Networks' Optimisation. International Conference on Learning Representations.16 indexed citations
Gal, Yarin & Zoubin Ghahramani. (2014). Pitfalls in the use of Parallel Inference for the Dirichlet Process. Cambridge University Engineering Department Publications Database. 208–216.9 indexed citations
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive
bibliographic database. While OpenAlex provides broad and valuable coverage of the global
research landscape, it—like all bibliographic datasets—has inherent limitations. These include
incomplete records, variations in author disambiguation, differences in journal indexing, and
delays in data updates. As a result, some metrics and network relationships displayed in
Rankless may not fully capture the entirety of a scholar's output or impact.