Alert button
Picture for Santiago Miret

Santiago Miret

Alert button

Are LLMs Ready for Real-World Materials Discovery?

Feb 07, 2024
Santiago Miret, N M Anoop Krishnan

Viaarxiv icon

A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems

Dec 12, 2023
Alexandre Duval, Simon V. Mathis, Chaitanya K. Joshi, Victor Schmidt, Santiago Miret, Fragkiskos D. Malliaros, Taco Cohen, Pietro Lio, Yoshua Bengio, Michael Bronstein

Viaarxiv icon

Towards equilibrium molecular conformation generation with GFlowNets

Oct 20, 2023
Alexandra Volokhova, Michał Koziarski, Alex Hernández-García, Cheng-Hao Liu, Santiago Miret, Pablo Lemos, Luca Thiede, Zichao Yan, Alán Aspuru-Guzik, Yoshua Bengio

Viaarxiv icon

Reflection-Equivariant Diffusion for 3D Structure Determination from Isotopologue Rotational Spectra in Natural Abundance

Oct 17, 2023
Austin Cheng, Alston Lo, Santiago Miret, Brooks Pate, Alán Aspuru-Guzik

Viaarxiv icon

HoneyBee: Progressive Instruction Finetuning of Large Language Models for Materials Science

Oct 12, 2023
Yu Song, Santiago Miret, Huan Zhang, Bang Liu

Figure 1 for HoneyBee: Progressive Instruction Finetuning of Large Language Models for Materials Science
Figure 2 for HoneyBee: Progressive Instruction Finetuning of Large Language Models for Materials Science
Figure 3 for HoneyBee: Progressive Instruction Finetuning of Large Language Models for Materials Science
Figure 4 for HoneyBee: Progressive Instruction Finetuning of Large Language Models for Materials Science
Viaarxiv icon

On the importance of catalyst-adsorbate 3D interactions for relaxed energy predictions

Oct 10, 2023
Alvaro Carbonero, Alexandre Duval, Victor Schmidt, Santiago Miret, Alex Hernandez-Garcia, Yoshua Bengio, David Rolnick

Figure 1 for On the importance of catalyst-adsorbate 3D interactions for relaxed energy predictions
Figure 2 for On the importance of catalyst-adsorbate 3D interactions for relaxed energy predictions
Figure 3 for On the importance of catalyst-adsorbate 3D interactions for relaxed energy predictions
Figure 4 for On the importance of catalyst-adsorbate 3D interactions for relaxed energy predictions
Viaarxiv icon

Searching for High-Value Molecules Using Reinforcement Learning and Transformers

Oct 04, 2023
Raj Ghugare, Santiago Miret, Adriana Hugessen, Mariano Phielipp, Glen Berseth

Viaarxiv icon

EGraFFBench: Evaluation of Equivariant Graph Neural Network Force Fields for Atomistic Simulations

Oct 03, 2023
Vaibhav Bihani, Utkarsh Pratiush, Sajid Mannan, Tao Du, Zhimin Chen, Santiago Miret, Matthieu Micoulaut, Morten M Smedskjaer, Sayan Ranu, N M Anoop Krishnan

Figure 1 for EGraFFBench: Evaluation of Equivariant Graph Neural Network Force Fields for Atomistic Simulations
Figure 2 for EGraFFBench: Evaluation of Equivariant Graph Neural Network Force Fields for Atomistic Simulations
Figure 3 for EGraFFBench: Evaluation of Equivariant Graph Neural Network Force Fields for Atomistic Simulations
Figure 4 for EGraFFBench: Evaluation of Equivariant Graph Neural Network Force Fields for Atomistic Simulations
Viaarxiv icon

MatSciML: A Broad, Multi-Task Benchmark for Solid-State Materials Modeling

Sep 12, 2023
Kin Long Kelvin Lee, Carmelo Gonzales, Marcel Nassar, Matthew Spellings, Mikhail Galkin, Santiago Miret

Figure 1 for MatSciML: A Broad, Multi-Task Benchmark for Solid-State Materials Modeling
Figure 2 for MatSciML: A Broad, Multi-Task Benchmark for Solid-State Materials Modeling
Figure 3 for MatSciML: A Broad, Multi-Task Benchmark for Solid-State Materials Modeling
Figure 4 for MatSciML: A Broad, Multi-Task Benchmark for Solid-State Materials Modeling
Viaarxiv icon

Using Multiple Vector Channels Improves E(n)-Equivariant Graph Neural Networks

Sep 06, 2023
Daniel Levy, Sékou-Oumar Kaba, Carmelo Gonzales, Santiago Miret, Siamak Ravanbakhsh

Figure 1 for Using Multiple Vector Channels Improves E(n)-Equivariant Graph Neural Networks
Figure 2 for Using Multiple Vector Channels Improves E(n)-Equivariant Graph Neural Networks
Figure 3 for Using Multiple Vector Channels Improves E(n)-Equivariant Graph Neural Networks
Figure 4 for Using Multiple Vector Channels Improves E(n)-Equivariant Graph Neural Networks
Viaarxiv icon