Vaishaal Shankar

2.4k citations
16 papers · 401 indexed · h-index 9
Topics
Domain Adaptation and Few-Shot Learning (4 papers)COVID-19 diagnosis using AI (3 papers)Topic Modeling (2 papers)
Journals
Systematic BiologySolar PhysicsarXiv (Cornell University)

In The Last Decade

Vaishaal Shankar

14 papers receiving 377 citations

Peers

Vaishaal Shankar
Comparison fields: 5 of 92
  • Artificial Intelligence 168
  • Computer Networks and Communications 98
  • Information Systems 84
  • Computer Vision and Pattern Recognition 82
  • Astronomy and Astrophysics 63
Replace Michael A. Schuh with:
Michael A. Schuh United States
Andrea Clematis Italy
Haitao Huang Japan
Berkay Aydin United States
Changyou Zhang China
Tianyi Li China
Hrachya Astsatryan Armenia
Dustin Kempton United States
Vaishaal Shankar relative to Michael A. Schuh United States Michael A. Schuh's profile →
Citations per field
00.5×6.4×
Michael A. Schuh · 1×
Citations per year

Countries citing papers authored by Vaishaal Shankar

Since Specialization
Citations

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

Fields of papers citing papers by Vaishaal Shankar

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

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

Co-authorship network of co-authors of Vaishaal Shankar

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

All Works

16 of 16 papers shown
#WorkIndexed citations
1 0
2 1
3 0
4 3
5 13
6
Measuring Robustness to Natural Distribution Shifts in Image Classification
11
7 7
8 74
9
Evaluating Machine Accuracy on ImageNet
21
10 57
11
Do ImageNet Classifiers Generalize to ImageNet
38
12
A Meta-Analysis of Overfitting in Machine Learning
53
13
When Robustness Doesn’t Promote Robustness: Synthetic vs. Natural Distribution Shifts on ImageNet
2
14 66
15 2
16 53

About Vaishaal Shankar

Vaishaal Shankar is a scholar working on Health Informatics, Artificial Intelligence and Computer Vision and Pattern Recognition, having authored 16 papers that have together received 401 indexed citations. Recurring topics across this work include Domain Adaptation and Few-Shot Learning (4 papers), COVID-19 diagnosis using AI (3 papers) and Topic Modeling (2 papers). The work is most often cited by research in Artificial Intelligence (168 citations), Signal Processing (54 citations) and Computer Networks and Communications (98 citations). Vaishaal Shankar has collaborated with scholars based in United States, Israel and Switzerland. Frequent co-authors include Benjamin Recht, Ludwig Schmidt, Rebecca Roelofs, Eric Jonas, Monica Bobra, J. T. Hoeksema, Ian Bolliger, Solomon Hsiang, Tamma Carleton and Jonathan Proctor. Their work appears in journals such as Systematic Biology, Solar Physics and arXiv (Cornell University).

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