Thanks to Asma's hard work, molpipx is now pip-installable and has a comprehensive documentation website! 🎉

pip install molpipx

📖 Docs: lnkd.in/em6NTsNr
🔗 GitHub: lnkd.in/gHeNnCqg

@compchem.bsky.social

🚀 Call for Students & Postdocs
🗓 Deadline: Feb 3
I’m scouting talented students & postdocs interested in ML for Materials and ML for Quantum Science for potential training & research opportunities under CIRTA at @McMasterCCB
Interest form: forms.gle/uV7fLhokmTCs...
#compchem

Scalable Bayesian Optimization for High-Dimensional Coarse-Grained Model Parameterization Coarse-grained (CG) force field models are extensively utilised in material simulations due to their scalability. Traditionally, these models are parameterized using hybrid strategies that integrate t...

Congrats to Carlos for getting his paper accepted at JCTC @pubs.acs.org
#compchem #bayesopt

arxiv.org/abs/2506.22533

Carbonic café around the corner is a super coffee shop!

Spectral Analysis of Molecular Kernels: When Richer Features Do Not Guarantee Better Generalization Understanding the spectral properties of kernels offers a principled perspective on generalization and representation quality. While deep models achieve state-of-the-art accuracy in molecular property...

🔥 Fresh out of the arXiv oven — new work from the ChemAI-Lab!

“Spectral Analysis of Molecular Kernels: When Richer Features Do Not Guarantee Better Generalization”

👉 arxiv.org/abs/2510.14217

#compchem
@mcmasteruniversity.bsky.social @bimr-mcmaster.bsky.social

Spectral Analysis of Molecular Kernels: When Richer Features Do Not Guarantee Better Generalization Understanding the spectral properties of kernels offers a principled perspective on generalization and representation quality. While deep models achieve state-of-the-art accuracy in molecular property...

🔥 Fresh out of the arXiv oven — new work from the ChemAI-Lab!

“Spectral Analysis of Molecular Kernels: When Richer Features Do Not Guarantee Better Generalization”

👉 arxiv.org/abs/2510.14217

#compchem
@mcmasteruniversity.bsky.social @bimr-mcmaster.bsky.social

Meta-Learning Fourier Neural Operators for Hessian Inversion and Enhanced Variational Data Assimilation Data assimilation (DA) is crucial for enhancing solutions to partial differential equations (PDEs), such as those in numerical weather prediction, by optimizing initial conditions using observational ...

🚨 New paper accepted at #NeurIPS2025 #ML4Phys!

We propose Meta-Learning Fourier Neural Operators to approximate inverse Hessians for variational data assimilation.

Isaac L. Huidobro-Meezs, Jun Dai, Rodrigo A. Vargas-Hern\'andez
Discrete Flow-Based Generative Models for Measurement Optimization in Quantum Computing
https://arxiv.org/abs/2509.15486

🚨 New on arXiv!
We adapt GFlowNets for measurement optimization in quantum computing
Generative, diverse, & hardware-aware groupings → fewer shots, flexible trade-offs.
📄 arxiv.org/abs/2509.15486

@ishume.bsky.social

#compchem #chemsky

Exciting news! 🎉

My student, @ishume.bsky.social , has been selected as one of the 2025 @sandboxaq.bsky.social Scholarship Recipients!

We can’t wait to show you what GenAI can do for quantum computing, stay tuned!!

www.sandboxaq.com/company/scho...
@mcmasteruniversity.bsky.social

Scalable Bayesian Optimization for High-Dimensional Coarse-Grained Model Parameterization Coarse-grained (CG) force field models are extensively utilised in material simulations due to their scalability. Traditionally, these models are parameterized using hybrid strategies that integrate t...

🚀BayesOpt for "large" Coarse-Grained Models!

BayesOpt enabled the optimization of a 41-parameter CG model without traditional heuristics or task decomposition.
arxiv.org/abs/2506.22533
#compchem #AI4Science #machinelearning

We’ve landed on BlueSky! Welcome to the Brockhouse Institute for Materials Research at McMaster University. On this account we will be sharing about upcoming events, recent work from our members, and all things related to the Institute. Follow along!

I had fun :) Thanks for inviting me!

Congratulations to the new PhD @guillemsimeon.bsky.social !!
From a NEURIPS poster discussion to being invited to his PhD exam!!

Thanks for inviting us :)

Slide of Alexandre de Camargo's talk on normalizing flows for orbital free DFT. Left panel shows a flow from a gaussian base distribution to a bimodal distribution for LiH at 10.0bohr. Right panel shows three distributions at R = 0.7, 2.95 & 10.0bohr

Wonderful talk and discussion by Alexandre de Camargo from @rovargash.bsky.social group at #QuNB group meeting this morning, sailing us through a #NormalizingFlow perspective of #Orbital-FreeDFT. More details at: dx.doi.org/10.1088/2632... #chemsky #theochem #ml4chem

Happy Quantum Day??

:)

Beer is better haha

Claro que tengo un poco de nervios de mi plática mañana!
Pero tmb ando bn emocionado!!! :)

El próximo viernes en el Instituto de Física en mi amada UNAM!!

Did you listen to DT’s new song???

One of my former supervisors said that seminars should be between Tuesday and Thursday so no one travels during the weekend. I kind of agree with this too

MOLPIPx: an end-to-end differentiable package for permutationally invariant polynomials in Python and Rust In this work, we present MOLPIPx, a versatile library designed to seamlessly integrate Permutationally Invariant Polynomials (PIPs) with modern machine learning frameworks, enabling the efficient deve...

🎉🪅Congrats to Asma and Manuel for getting MOLPIPx accepted in JChemPhys!!
📜: arxiv.org/abs/2411.17011
🖥️: github.com/ChemAI-Lab/m...
#compchem

The world is on 🔥 -- and here's my first publication in an astronomy journal: iopscience.iop.org/article/10.3...

We combine Gaussian processes + hidden Markov models to efficiently detect stellar flares in one modelling step. 🧪

No table was burned during this demo :)
#chemistry

✨We're hiring for bio roles at Cradle!

You can expect to work on a huge variety of problems (antibodies, enzymes, peptides, ...) across all modalities (therapeutics, agtech, biosynthesis, ...), as at this point (post series B) we work with pretty much the whole industry.

[1/2]

Chemical Formulas xkcd.com/3040

Hola :)