Work · 2020–2026

Publications,
talks, awards.

Papers across physics-informed ML, inverse design, active learning, and benchmarks, most of them co-authored with the Padilla and Malof labs at Duke.

12 papers

2026

Nature Sustainabilityequal contribution

Solution-processable bio-inspired smart skin for synergistic solar and radiative heat management⁠ (opens in new tab)

Xie, W., Deng, Y., Liu, Y., Zhao, Y., et al. (33 authors)

Advanced Functional Materials

Ionic Liquid-based Reversible Metal Electrodeposition for Adaptive Radiative Thermoregulation under Extreme Environments⁠ (opens in new tab)

Liang, J., Sui, C., Tian, J., et al.

2025

Applied Physics Reviews

Physics-Informed Learning in Artificial Electromagnetic Materials⁠ (opens in new tab)

Deng, Y., Fan, K., Jin, B., Malof, J. M., & Padilla, W. J.

IEEE Access

Can Large Language Models Learn the Physics of Metamaterials? An Empirical Study with ChatGPT⁠ (opens in new tab)

Lu, D., Deng, Y., Malof, J. M., & Padilla, W. J.

2024

Nanophotonics

Fundamental absorption bandwidth to thickness limit for transparent homogeneous layers⁠ (opens in new tab)

Padilla, W. J., Deng, Y., Khatib, O., & Tarokh, V.

2023

arXiv preprint

Deep Active Learning for Scientific Computing in the Wild⁠ (opens in new tab)

Ren, S., Deng, Y., Padilla, W. J., Collins, L., & Malof, J.

2022

Photonics and Nanostructures

Deep inverse photonic design: a tutorial⁠ (opens in new tab)

Deng, Y., Ren, S., Malof, J., & Padilla, W. J.

arXiv preprint

Towards Robust Deep Active Learning for Scientific Computing⁠ (opens in new tab)

Ren, S., Deng, Y., Padilla, W. J., & Malof, J.

Nanoscale

Inverse deep learning methods and benchmarks for artificial electromagnetic material design⁠ (opens in new tab)

Ren, S., Mahendra, A., Khatib, O., Deng, Y., Padilla, W. J., & Malof, J. M.

2021

NeurIPS D&B

Benchmarking data-driven surrogate simulators for artificial electromagnetic materials⁠ (opens in new tab)

Deng, Y., Dong, J., Ren, S., Khatib, O., Soltani, M., Tarokh, V., et al.

ICLR

Blaschke Product Neural Networks (BPNN): A Physics-Infused Neural Network for Phase Retrieval⁠ (opens in new tab)

Dong, J., Ren, S., Deng, Y., Khatib, O., Malof, J., et al.

Optics Express

Neural-adjoint method for the inverse design of all-dielectric metasurfaces⁠ (opens in new tab)

Deng, Y., Ren, S., Fan, K., Malof, J. M., & Padilla, W. J.

Talks
& posters

2022Machine learning for the next generation metamaterialsTSRC
2021Benchmarking data-driven surrogate simulatorsNeurIPS D&B
2020Deep learning for inverse design of all-dielectric metasurfacesTriangle Hard Matter Workshop

Honors

2023Best Student Talk AwardDuke ECE Retreat
2021Energy Data Analytics Ph.D. Student FellowsDuke
2020Best Graduate Student Poster AwardTriangle Hard Matter Workshop