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.
Advances in Variational Inference
2018349 citationsCheng Zhang, Hedvig Kjellström et al.profile →
Peers — A (Enhanced Table)
Peers by citation overlap · career bar shows stage (early→late)
cites ·
hero ref
This map shows the geographic impact of Stephan Mandt'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 Stephan Mandt with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Stephan Mandt more than expected).
This network shows the impact of papers produced by Stephan Mandt. 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 Stephan Mandt. The network helps show where Stephan Mandt may publish in the future.
Co-authorship network of co-authors of Stephan Mandt
This figure shows the co-authorship network connecting the top 25 collaborators of Stephan Mandt.
A scholar is included among the top collaborators of Stephan Mandt 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 Stephan Mandt. Stephan Mandt is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
Yang, Yibo & Stephan Mandt. (2021). Lower Bounding Rate-Distortion From Samples. International Conference on Learning Representations.1 indexed citations
8.
Mukkavilli, S. Karthik, et al.. (2020). Generative Large Eddy Simulations with conditional Variational Autoencoders. AGU Fall Meeting Abstracts. 2020.1 indexed citations
9.
Yang, Yibo, Robert Bamler, & Stephan Mandt. (2020). Improving Inference for Neural Image Compression. arXiv (Cornell University). 33. 573–584.5 indexed citations
10.
Lombardo, Salvator, Jun Han, Christopher Schroers, & Stephan Mandt. (2019). Deep Generative Video Compression. Neural Information Processing Systems. 32. 9283–9294.5 indexed citations
11.
Li, Yingzhen & Stephan Mandt. (2018). A Deep Generative Model for Disentangled Representations of Sequential Data.. arXiv (Cornell University).3 indexed citations
12.
Yue, Yisong, et al.. (2018). Learning to Infer. International Conference on Learning Representations.1 indexed citations
Bamler, Robert, Cheng Zhang, Manfred Opper, & Stephan Mandt. (2017). Perturbative Black Box Variational Inference. Neural Information Processing Systems. 30. 5079–5088.3 indexed citations
15.
Bamler, Robert & Stephan Mandt. (2017). Dynamic Word Embeddings via Skip-Gram Filtering.. arXiv (Cornell University).4 indexed citations
16.
Zhang, Cheng, Hedvig Kjellström, & Stephan Mandt. (2017). Balanced Mini-batch Sampling for SGD Using Determinantal Point Processes.. Uncertainty in Artificial Intelligence.2 indexed citations
17.
Bamler, Robert & Stephan Mandt. (2017). Dynamic word embeddings. International Conference on Machine Learning. 380–389.40 indexed citations
18.
Mandt, Stephan, Florian Wenzel, Shinichi Nakajima, et al.. (2017). Sparse probit linear mixed model. Machine Learning. 106(9-10). 1621–1642.5 indexed citations
19.
Mandt, Stephan, et al.. (2014). Deterministic Annealing for Stochastic Variational Inference.. arXiv (Cornell University).1 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.