World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
33
Citations
9270
World Ranking
12390
National Ranking
5020

Overview

Mario Lucic is affiliated with Google in the United States and has a research focus primarily in Computer Science. Within this field, their work is concentrated on subfields such as Computer Vision and Pattern Recognition, Artificial Intelligence, Computer Graphics and Computer-Aided Design, Aerospace Engineering, and Signal Processing.

The scientist's research covers a range of topics. Notable areas include Domain Adaptation and Few-Shot Learning, Advanced Neural Network Applications, Multimodal Machine Learning Applications, Advanced Vision and Imaging, Adversarial Robustness in Machine Learning, Advanced Image and Video Retrieval Techniques, and Human Pose and Action Recognition.

Mario Lucic has authored many publications across distinguished venues. Frequent publication platforms include:

  • arXiv (Cornell University)
  • 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
  • ACM Transactions on Graphics
  • Proceedings of the AAAI Conference on Artificial Intelligence

Among their recent papers are:

  • MLP-Mixer: An all-MLP Architecture for Vision (2021, arXiv (Cornell University))
  • Underspecification Presents Challenges for Credibility in Modern Machine Learning (2020, arXiv (Cornell University))
  • Scaling Vision Transformers to 22 Billion Parameters (2023, arXiv (Cornell University))
  • Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations (2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR))
  • ViViT: A Video Vision Transformer (2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV))

Their research collaborations include frequent co-authors such as Neil Houlsby, Josip Djolonga, Anurag Arnab, Mostafa Dehghani, and Daniel Duckworth.

Best Publications

  • MLP-Mixer: An all-MLP Architecture for Vision

    Ilya Tolstikhin;Neil Houlsby;Alexander Kolesnikov;Lucas Beyer

  • MLP-Mixer: An all-MLP Architecture for Vision

    Ilya Tolstikhin;Neil Houlsby;Alexander Kolesnikov;Lucas Beyer

  • Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations

    Francesco Locatello;Stefan Bauer;Mario Lučić;Gunnar Rätsch

  • Are GANs Created Equal? A Large-Scale Study

    Mario Lucic;Karol Kurach;Marcin Michalski;Sylvain Gelly

  • Underspecification Presents Challenges for Credibility in Modern Machine Learning

    Alexander D'Amour;Katherine A. Heller;Dan Moldovan;Ben Adlam

  • Recent Advances in Autoencoder-Based Representation Learning

    Michael Tschannen;Olivier Frederic Bachem;Mario Lučić

  • Assessing Generative Models via Precision and Recall

    Mehdi S. M. Sajjadi;Olivier Bachem;Mario Lucic;Olivier Bousquet

  • Self-Supervised GANs via Auxiliary Rotation Loss

    Ting Chen;Xiaohua Zhai;Marvin Ritter;Mario Lucic

  • Scaling Vision Transformers to 22 Billion Parameters

    Unknown

  • On Mutual Information Maximization for Representation Learning

    Michael Tschannen;Josip Djolonga;Paul K. Rubenstein;Sylvain Gelly

  • On Mutual Information Maximization for Representation Learning

    Michael Tschannen;Josip Djolonga;Paul K. Rubenstein;Sylvain Gelly

  • Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations

    Francesco Locatello;Stefan Bauer;Mario Lucic;Gunnar Rätsch

  • A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark

    Xiaohua Zhai;Joan Puigcerver;Alexander Kolesnikov;Pierre Ruyssen

  • Practical Coreset Constructions for Machine Learning

    Olivier Bachem;Mario Lucic;Andreas Krause

  • Approximate k-means++ in sublinear time

    Olivier Bachem;Mario Lucic;S. Hamed Hassani;Andreas Krause

  • Fast and Provably Good Seedings for k-Means

    Olivier Bachem;Mario Lucic;Hamed Hassani;Andreas Krause

  • The GAN Landscape: Losses, Architectures, Regularization, and Normalization

    Karol Kurach;Mario Lucic;Xiaohua Zhai;Marcin Michalski

  • High-Fidelity Image Generation With Fewer Labels

    Mario Lucic;Michael Tschannen;Marvin Ritter;Xiaohua Zhai

  • A Large-Scale Study on Regularization and Normalization in GANs

    Karol Kurach;Mario Lučić;Xiaohua Zhai;Marcin Michalski

  • On Self Modulation for Generative Adversarial Networks

    Ting Chen;Mario Lucic;Neil Houlsby;Sylvain Gelly

  • Scalable k -Means Clustering via Lightweight Coresets

    Olivier Bachem;Mario Lucic;Andreas Krause

  • Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations.

    Mehdi S. M. Sajjadi;Henning Meyer;Etienne Pot;Urs Bergmann

  • ViViT: A Video Vision Transformer

    Anurag Arnab;Mostafa Dehghani;Georg Heigold;Chen Sun

  • Coresets for Nonparametric Estimation - the Case of DP-Means

    Olivier Bachem;Mario Lucic;Andreas Krause

  • The Visual Task Adaptation Benchmark

    Xiaohua Zhai;Joan Puigcerver;Alexander Kolesnikov;Pierre Ruyssen

Frequent Co-Authors

Sylvain Gelly
Sylvain Gelly Google (United States)
Andreas Krause
Andreas Krause ETH Zurich
Xiaohua Zhai
Xiaohua Zhai Google (United States)
Olivier Bousquet
Olivier Bousquet Google (United States)
Bernhard Schölkopf
Bernhard Schölkopf Max Planck Institute for Intelligent Systems
Gunnar Rätsch
Gunnar Rätsch ETH Zurich
Alexey Dosovitskiy
Alexey Dosovitskiy Google (United States)
Marco Cuturi
Marco Cuturi École Nationale de la Statistique et de l'Administration Économique

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring Computer Science in the USA opens doors to a variety of related fields and flexible study options. Many students now opt for fully online degrees, providing greater accessibility and convenience, especially for those balancing work or family commitments.

If you’re looking for accelerated learning, a 1 year computer science degree online can help you quickly gain critical tech skills and enter the workforce faster. Those interested in engineering can pursue an environmental engineering bachelor's degree online that focuses on sustainability and the growing “green” job market.

For students concerned with affordability, consider the cheapest mechanical engineering degree online, which offers robust technical training without the steep cost. Lastly, those passionate about discovery and research may find a bachelor of science in physics online to be a rewarding choice with broad career prospects.

These pathways demonstrate the diversity of online STEM education in the USA, letting you tailor your learning journey to your goals, schedule, and budget.

Best Scientists Citing Mario Lucic

Trending Scientists

Recently Published Articles