EC

Ekin D. Cubuk

0000-0003-0524-2837

cs.LGcs.CVcond-mat.mtrl-scistat.MLphysics.comp-phcond-mat.softcs.AIcs.CLcond-mat.dis-nnmachine learning

On Valency

published · living versions

AutoAugment: Learning Augmentation Policies from Data

with Barret Zoph, Dandelion Mane, Vijay Vasudevan, Quoc V. Le

1 version

W_n5tjnkpav1 · current

Identifying structural flow defects in disordered solids using machine learning methods

W_y25n99c2v1

Preprints & journals

82 papers in the corpus · 2012–2026

Author Correction: An autonomous laboratory for the accelerated synthesis of inorganic materials.

Szymanski, Nathan J, Rendy, Bernardus, Fei, Yuxing et al.

7 citations

415549842026Nature. 2026

Search for thermodynamically stable ambient-pressure superconducting hydrides in the GNoME database.

Sanna, Antonio, Cerqueira, Tiago F T, Cubuk, Ekin Dogus et al.

2 citations

418531322026Communications physics. 2026;9(1):94

Force-Field Optimization by End-to-End Differentiable Atomistic Simulation.

Gangan, Abhijeet Sadashiv, Cubuk, Ekin Dogus, Schoenholz, Samuel S et al.

6 citations

404720082025Journal of chemical theory and computation. 2025;21(12):5867-5879

Computational search for materials having a giant anomalous Hall effect in the pyrochlore and spinel crystal structures

Sean Sullivan, Seungjun Lee, Nathan J. Szymanski et al.

1 citation

2504.18320v22025arXiv

System of Agentic AI for the Discovery of Metal-Organic Frameworks

Theo Jaffrelot Inizan, Sherry Yang, Aaron Kaplan et al.

9 citations

2504.14110v12025arXiv

CURIE: Evaluating LLMs On Multitask Scientific Long Context Understanding and Reasoning

Hao Cui, Zahra Shamsi, Gowoon Cheon et al.

1 citation

2503.13517v22025arXiv

A practical guide to machine learning interatomic potentials -- Status and future

Ryan Jacobs, Dane Morgan, Siamak Attarian et al.

218 citations

2503.09814v12025Current Opinion in Solid State and Materials Science, 35, 101214 (2025)

Predicting emergence of crystals from amorphous precursors with deep learning potentials.

Aykol, Muratahan, Merchant, Amil, Batzner, Simon et al.

12 citations

396953212025Nature computational science. 2025;5(2):105-111

Efficient Exploratory Synthesis of Quaternary Cesium Chlorides Guided by In Silico Predictions.

Miura, Akira, Aykol, Muratahan, Kozaki, Shumma et al.

5 citations

394123342026Journal of the American Chemical Society. 2024;146(43):29637-29644

Generative Hierarchical Materials Search

Sherry Yang, Simon Batzner, Ruiqi Gao et al.

4 citations

2409.06762v12024arXiv

Scaling (Down) CLIP: A Comprehensive Analysis of Data, Architecture, and Training Strategies

Zichao Li, Cihang Xie, Ekin Dogus Cubuk

1 citation

2404.08197v22024arXiv

Accurate Surface and Finite-Temperature Bulk Properties of Lithium Metal at Large Scales Using Machine Learning Interaction Potentials.

Phuthi, Mgcini Keith, Yao, Archie Mingze, Batzner, Simon et al.

22 citations

384632742026ACS omega. 2024;9(9):10904-10912

AutoNumerics-Zero: Automated Discovery of State-of-the-Art Mathematical Functions

Esteban Real, Mirko Rossini, Connal de Souza et al.

1 citation

2312.08472v22023arXiv

Scaling deep learning for materials discovery.

Merchant, Amil, Batzner, Simon, Schoenholz, Samuel S et al.

1,500 citations

380307202023Nature. 2023;624(7990):80-85

An autonomous laboratory for the accelerated synthesis of novel materials.

Szymanski, Nathan J, Rendy, Bernardus, Fei, Yuxing et al.

1,009 citations

380307212023Nature. 2023;624(7990):86-91

Accurate Prediction of Experimental Band Gaps from Large Language Model-Based Data Extraction

Samuel J. Yang, Shutong Li, Subhashini Venugopalan et al.

6 citations

2311.13778v12023arXiv

Learning and Controlling Silicon Dopant Transitions in Graphene using Scanning Transmission Electron Microscopy

Max Schwarzer, Jesse Farebrother, Joshua Greaves et al.

0 citations

2311.17894v12023arXiv

Scalable Diffusion for Materials Generation

Sherry Yang, KwangHwan Cho, Amil Merchant et al.

28 citations

2311.09235v22023arXiv

Predicting emergence of crystals from amorphous matter with deep learning

Muratahan Aykol, Amil Merchant, Simon Batzner et al.

3 citations

2310.01117v12023arXiv

Learning molecular dynamics: predicting the dynamics of glasses by a machine learning simulator.

Liu, Han, Huang, Zijie, Schoenholz, Samuel S et al.

19 citations

373824132023Materials horizons. 2023;10(9):3416-3428

Tied-Augment: Controlling Representation Similarity Improves Data Augmentation

Emirhan Kurtulus, Zichao Li, Yann Dauphin et al.

1 citation

2305.13520v12023arXiv

LidarAugment: Searching for Scalable 3D LiDAR Data Augmentations

Zhaoqi Leng, Guowang Li, Chenxi Liu et al.

9 citations

2210.13488v12022arXiv

G-Augment: Searching for the Meta-Structure of Data Augmentation Policies for ASR

Gary Wang, Ekin D.Cubuk, Andrew Rosenberg et al.

2 citations

2210.10879v22022arXiv

What does a deep neural network confidently perceive? The effective dimension of high certainty class manifolds and their low confidence boundaries

Stanislav Fort, Ekin Dogus Cubuk, Surya Ganguli et al.

0 citations

2210.05546v12022arXiv

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao et al.

569 citations

2206.04615v32022Transactions on Machine Learning Research, May/2022, https://openreview.net/forum?id=uyTL5Bvosj

PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions

Zhaoqi Leng, Mingxing Tan, Chenxi Liu et al.

109 citations

2204.12511v22022International Conference on Learning Representations. 2021

Do better ImageNet classifiers assess perceptual similarity better?

Manoj Kumar, Neil Houlsby, Nal Kalchbrenner et al.

13 citations

2203.04946v32022arXiv

No One Representation to Rule Them All: Overlapping Features of Training Methods

Raphael Gontijo-Lopes, Yann Dauphin, Ekin D. Cubuk

15 citations

2110.12899v32021International Conference on Learning Representations (ICLR) 2022

Multi-Task Self-Training for Learning General Representations

Golnaz Ghiasi, Barret Zoph, Ekin D. Cubuk et al.

83 citations

2108.11353v12021arXiv

Learn2Hop: Learned Optimization on Rough Landscapes

Amil Merchant, Luke Metz, Sam Schoenholz et al.

2 citations

2107.09661v12021arXiv

dPV: An End-to-End Differentiable Solar-Cell Simulator

Sean Mann, Eric Fadel, Samuel S. Schoenholz et al.

15 citations

2105.06305v32021arXiv

Revisiting ResNets: Improved Training and Scaling Strategies

Irwan Bello, William Fedus, Xianzhi Du et al.

229 citations

2103.07579v12021arXiv

Designing self-assembling kinetics with differentiable statistical physics models.

Goodrich, Carl P, King, Ella M, Schoenholz, Samuel S et al.

67 citations

336539602021Proceedings of the National Academy of Sciences of the United States of America. 2021;118(10)

Kohn-Sham Equations as Regularizer: Building Prior Knowledge into Machine-Learned Physics.

Li, Li, Hoyer, Stephan, Pederson, Ryan et al.

171 citations

335439802021Physical review letters. 2021;126(3):036401

Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation

Golnaz Ghiasi, Yin Cui, Aravind Srinivas et al.

1,225 citations

2012.07177v22020arXiv

Dataset of Random Relaxations for Crystal Structure Search of Li-Si System

Gowoon Cheon, Lusann Yang, Kevin McCloskey et al.

1 citation

2012.02920v32020arXiv

Self-assembling kinetics: Accessing a new design space via differentiable statistical-physics models

Carl P. Goodrich, Ella M. King, Samuel S. Schoenholz et al.

2 citations

2010.15175v22020arXiv

Does Data Augmentation Benefit from Split BatchNorms

Amil Merchant, Barret Zoph, Ekin Dogus Cubuk

4 citations

2010.07810v12020arXiv

Unifying framework for strong and fragile liquids via machine learning: a study of liquid silica

Ekin D. Cubuk, Andrea J. Liu, Efthimios Kaxiras et al.

6 citations

2008.09681v12020arXiv

Combining Superionic Conduction and Favorable Decomposition Products in the Crystalline Lithium-Boron-Sulfur System: A New Mechanism for Stabilizing Solid Li-Ion Electrolytes.

Sendek, Austin D, Antoniuk, Evan R, Cubuk, Ekin D et al.

39 citations

327008962020ACS applied materials & interfaces. 2020;12(34):37957-37966

Forward and Inverse Design of Kirigami via Supervised Autoencoder

Paul Z. Hanakata, Ekin D. Cubuk, David K. Campbell et al.

60 citations

2008.05298v12020Phys. Rev. Research 2, 042006 (2020)

Rethinking Pre-training and Self-training

Barret Zoph, Golnaz Ghiasi, Tsung-Yi Lin et al.

510 citations

2006.06882v22020arXiv

Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation

Liang-Chieh Chen, Raphael Gontijo Lopes, Bowen Cheng et al.

165 citations

2005.10266v42020arXiv

Improving 3D Object Detection through Progressive Population Based Augmentation

Shuyang Cheng, Zhaoqi Leng, Ekin Dogus Cubuk et al.

62 citations

2004.00831v22020arXiv

Affinity and Diversity: Quantifying Mechanisms of Data Augmentation

Raphael Gontijo-Lopes, Sylvia J. Smullin, Ekin D. Cubuk et al.

52 citations

2002.08973v22020arXiv

FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

Kihyuk Sohn, David Berthelot, Chun-Liang Li et al.

2,937 citations

2001.07685v22020arXiv

JAX, M.D.: A Framework for Differentiable Physics

Samuel S. Schoenholz, Ekin D. Cubuk

132 citations

1912.04232v22019Advances in Neural Information Processing Systems 33 (2020)

AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty

Dan Hendrycks, Norman Mu, Ekin D. Cubuk et al.

783 citations

1912.02781v22019arXiv

ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring

David Berthelot, Nicholas Carlini, Ekin D. Cubuk et al.

494 citations

1911.09785v22019arXiv

RandAugment: Practical automated data augmentation with a reduced search space

Ekin D. Cubuk, Barret Zoph, Jonathon Shlens et al.

3,218 citations

1909.13719v22019arXiv

Career total: 146 works. 82 are in this corpus.Showing the 50 most recent.

Profile built from the corpus for this byline.

146

works

28.9K

citations

54

h-index

Corpus papers per year

Author records are still filling in while the Hub is in beta. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.