Luke Vilnis

2.0k total citations
13 papers, 208 citations indexed

About

Luke Vilnis is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Molecular Biology. According to data from OpenAlex, Luke Vilnis has authored 13 papers receiving a total of 208 indexed citations (citations by other indexed papers that have themselves been cited), including 11 papers in Artificial Intelligence, 3 papers in Computer Vision and Pattern Recognition and 2 papers in Molecular Biology. Recurrent topics in Luke Vilnis's work include Topic Modeling (9 papers), Natural Language Processing Techniques (8 papers) and Bayesian Modeling and Causal Inference (2 papers). Luke Vilnis is often cited by papers focused on Topic Modeling (9 papers), Natural Language Processing Techniques (8 papers) and Bayesian Modeling and Causal Inference (2 papers). Luke Vilnis collaborates with scholars based in United States and India. Luke Vilnis's co-authors include Andrew McCallum, Patrick Verga, Irena Radovanovic, Dongxu Zhang, Xiang Li, Andrew McCallum, Ishan Durugkar, Akshay Krishnamurthy, Rajarshi Das and Jiaping Zheng and has published in prestigious journals such as arXiv (Cornell University), Neural Information Processing Systems and International Conference on Learning Representations.

In The Last Decade

Luke Vilnis

12 papers receiving 192 citations

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name h Career Trend Papers Cites
Luke Vilnis United States 6 202 29 22 22 16 13 208
Altaf Rahman United States 9 270 1.3× 21 0.7× 25 1.1× 17 0.8× 31 1.9× 11 283
Tim O’Gorman United States 11 316 1.6× 34 1.2× 21 1.0× 23 1.0× 26 1.6× 25 329
Weiguang Qu China 8 209 1.0× 21 0.7× 43 2.0× 10 0.5× 9 0.6× 36 227
Daniil Sorokin Germany 7 266 1.3× 39 1.3× 43 2.0× 25 1.1× 20 1.3× 11 275
Yanchao Hao China 2 239 1.2× 35 1.2× 31 1.4× 31 1.4× 9 0.6× 3 259
Zeqiu Wu United States 6 277 1.4× 33 1.1× 33 1.5× 36 1.6× 28 1.8× 10 289
Jiangming Liu United Kingdom 7 312 1.5× 28 1.0× 24 1.1× 11 0.5× 11 0.7× 18 329
José G. Moreno France 8 93 0.5× 38 1.3× 14 0.6× 8 0.4× 14 0.9× 32 135
Daniel Gillick United States 7 204 1.0× 26 0.9× 26 1.2× 21 1.0× 6 0.4× 9 218

Countries citing papers authored by Luke Vilnis

Since Specialization
Citations

This map shows the geographic impact of Luke Vilnis'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 Luke Vilnis with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Luke Vilnis more than expected).

Fields of papers citing papers by Luke Vilnis

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Luke Vilnis. 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 Luke Vilnis. The network helps show where Luke Vilnis may publish in the future.

Co-authorship network of co-authors of Luke Vilnis

This figure shows the co-authorship network connecting the top 25 collaborators of Luke Vilnis. A scholar is included among the top collaborators of Luke Vilnis 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 Luke Vilnis. Luke Vilnis is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

13 of 13 papers shown
1.
Zhang, Dongxu, et al.. (2021). Capacity and Bias of Learned Geometric Embeddings for Directed Graphs. Neural Information Processing Systems. 34. 1 indexed citations
2.
Vilnis, Luke. (2021). Geometric Representation Learning. Scholarworks (University of Massachusetts Amherst).
3.
Dasgupta, Shib Sankar, et al.. (2020). Improving Local Identifiability in Probabilistic Box Embeddings. Neural Information Processing Systems. 33. 182–192. 2 indexed citations
4.
Dasgupta, Shib Sankar, et al.. (2020). Representing Joint Hierarchies with Box Embeddings. 4 indexed citations
5.
Li, Xiang, et al.. (2018). Smoothing the Geometry of Probabilistic Box Embeddings. International Conference on Learning Representations. 23 indexed citations
6.
Verga, Patrick, et al.. (2018). Hierarchical Losses and New Resources for Fine-grained Entity Typing and Linking. 97–109. 46 indexed citations
7.
Das, Rajarshi, Shehzaad Dhuliawala, Manzil Zaheer, et al.. (2017). Go for a Walk and Arrive at the Answer: Reasoning Over Knowledge Bases with Reinforcement Learning.. Neural Information Processing Systems. 4 indexed citations
8.
Das, Rajarshi, Shehzaad Dhuliawala, Manzil Zaheer, et al.. (2017). Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning.. arXiv (Cornell University). 20 indexed citations
9.
Verga, Patrick, et al.. (2017). Finer Grained Entity Typing with TypeNet.. arXiv (Cornell University). 4 indexed citations
10.
Chang, Haw-Shiuan, et al.. (2017). Unsupervised Hypernym Detection by Distributional Inclusion Vector Embedding.. arXiv (Cornell University). 1 indexed citations
11.
Vilnis, Luke & Andrew McCallum. (2015). Word Representations via Gaussian Embedding. arXiv (Cornell University). 84 indexed citations
12.
Strubell, Emma, et al.. (2015). Learning Dynamic Feature Selection for Fast Sequential Prediction. 146–155. 6 indexed citations
13.
Zheng, Jiaping, Luke Vilnis, Sameer Singh, Jinho D. Choi, & Andrew McCallum. (2013). Dynamic Knowledge-Base Alignment for Coreference Resolution. ScholarWorks@UMassAmherst (University of Massachusetts Amherst). 153–162. 13 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.

Explore authors with similar magnitude of impact

Rankless by CCL
2026