talks

[Invited] Rethinking Materials Discovery with Generative Models, AI4Science workshop, Rabat, Morocco. [Link]
[Invited] Rethinking Materials Discovery with Generative Models, Cantab Capital Institute for the Mathematics of Information, University of Cambridge, Cambridge, UK. [Link]
[Invited] Rethinking Materials Discovery with Generative Models, EGNE 2022, Korea. [Link]
[Invited] Rethinking Materials Discovery with Generative Models, Intel, online.
[Invited] Rethinking Materials Discovery with Generative Models, Meta AI, online.
[Invited] Rethinking the Future of Machine Learning Guided Materials Discovery, Shell.ai Scientific Conference 2022 on Digital Material Design for Sustainability and Circularity, Bangalore, India. [Link]
[Invited] Forward and inverse design of solid materials, Artificial Intelligence for Materials Science (AIMS) workshop, online. [Link]
[Invited] Forward and Inverse Design of Solid Materials with Graph Neural Networks, MIT GraphEx Symposium 2022, online. [Link]

[Contributed talk] (top 2 %) Crystal Diffusion Variational Autoencoder for Periodic Material Generation, NeurIPS 2021 Machine Learning and the Physical Sciences Workshop, online. [Link]
[Invited] Physics-based deep learning models for the discovery, understanding, and design of solid materials, DP Technology AI for energy material simulation series, in Chinese, online. [Video]
[Invited] Understanding the atomic scale dynamics in materials with unsupervised learning from molecular dynamics, MIT-IBM Watson AI Lab, online.

[Spotlight Talk] Accelerate the screening of complex materials by learning to reduce random and systematic errors, NeurIPS ML4Molecules workshop, online. [Link] [Video]
Understanding the dynamical processes in materials with unsupervised learning from molecular dynamics, AI for Materials: From Discovery to Production, online. [Link]
Understanding Li-ion solvation dynamics with unsupervised learning from molecular dynamics, APS March Meeting, online. [Link]
[Thesis defense] Deep Learning Methods for the Design and Understanding of Solid Materials, MIT DMSE Doctoral Thesis Defense, online. [Link] [YouTube] [Slides]
[Invited] Physics Guided Neural Networks for the Design and Understanding of Materials, Aron Walsh’s group at Imperial College London, online.
[Invited] Physics Guided Neural Networks for the Design and Understanding of Materials, MIT IDSS/DMSE Special Seminar, online. [link]

Understanding the atomic scale dynamics in materials with unsupervised learning from molecular dynamics, MRS Fall Meeting, Boston, MA. [Link] [PDF]
[Invited] High Throughput, Rapid Materials Design for Energy Storage, MIT Energy Initiative Annual Research Conference, Cambridge, MA.
[Invited] Graph neural networks as a general framework for the design and understanding of materials, Computational Chemistry and Machine Learning Workshop, Xiamen, China.
[Invited] Unsupervised Learning of Atomic Scale Dynamics in Materials, Toyota Research Institute, Mountain View, CA.

CGCNN—A Graph Representation of Materials for Property Prediction and Materials Design, MRS Fall Meeting, Boston, MA. [Link] [PDF]
Continuous Representation of Chemical Environments for the Prediction of Material Properties, APS March Meeting, Los Angeles, CA. [Link]

Graph Representation of Periodic Systems for Accurate and Explainable Prediction of Material Properties via Machine Learning, MRS Fall Meeting, Boston, MA. [Link]

posters

Graph dynamical networks: unsupervised learning of atomic scale dynamics in materials, AI Powered Drug Discovery and Manufacturing Conference, Cambridge, MA. [Link] [PDF]

CGCNN: a graph representation of materials for property prediction and materials design, MRL Materials Day, Cambridge, MA. [Link] [PDF] [Highlight]
Understanding Lithium-ion Transport with Deep Neural Networks, TRI Accelerated Materials Design & Discovery workshop, Redwood City, CA. [Link]
Artificial Intelligence for Accelerated Materials Design, MIT Intelligence Quest Launch, Cambridge, MA. [Link] [PDF]