Bálint Máté

Member of Technical Staff @Angstrom_ai. prev intern @AIatMeta, @MSFTResearch, phd at @unige_en

[Bálint Máté @balintmt]

new preprint on solvation free energies:

tl;dr: We define an interpolating density by its sampling process, and learn the corresponding equilibrium potential with score matching. https://t.co/sO0EI4sy5r

with @francoisfleuret and @tristanbereau
(1/n)

[Tristan Bereau @tristanbereau]

PhD position in Heidelberg: generating amorphous molecular thin films with diffusion models rather than waiting for MD to equilibrate them — free energies from the same model. With U. Köthe. 3 years, funded. Physics degree required.

https://t.co/AaabLQZYEd

[Tony RuiKang OuYang @TonyRKOuYang]

Can we improve energy-based diffusion models by solving a classification task? 🤔

🚀 Excited to share DiffCLF, accepted at ICML 2026 🇰🇷! ! We predict a sample’s noise level, and recover densities as a by-product.

Joint work with @theh2o64 (co-lead) and @jmhernandez233. [🧵1/n]

[Youssef Saied @YoussefMMSaied]

1/

What happens when a denoiser trained at one noise level is reused inside an iterative sampler?

We trained SwinIR with Noise2Noise at σ=10, then dropped it unchanged into the constrained sampler of @ZKadkhodaie & @EeroSimoncelli (NeurIPS ’21) for 10% random inpainting.

Baseline SwinIR: 6.08 dB on Set12.

SwinIR-WNE: 23.87 dB.

Same backbone. Same N2N pairs. Same sampler.

With François Fleuret @francoisfleuret. ICML 2026. 🧵

[Ameya Daigavane @BigAmeya]

Now accepted at #NeurIPS2025! We basically speed up diffusion models for sampling molecular conformations by 30x :) More exciting stuff coming soon!

[Chin-Wei Huang @chinwei_h]

🚀 After two years of intense research, we’re thrilled to introduce Skala — a scalable DL density functional that hits chemical accuracy on atomization energies and matches hybrid-level performance on main group chemistry — all at the cost of a semi-local functional. ⚛️🔥🧪⚗️🧬

[Rianne van den Berg @vdbergrianne]

🚀 After two+ years of intense research, we’re thrilled to introduce Skala — a scalable deep learning density functional that hits chemical accuracy on atomization energies and matches hybrid-level accuracy on main group chemistry — all at the cost of semi-local DFT. ⚛️🔥🧪🧬

[Bálint Máté @balintmt]

@francoisfleuret https://t.co/G2NFmEZSHI

[Bálint Máté @balintmt]

@eeevgen @francoisfleuret @tristanbereau In this particular experiment, we ran MCMC for 40k steps and dropped the first 10k as burn-in. I see your concern with direct MCMC, and I guess it depends on the target. We could get away with it for this simple target (only LJ interactions, particles are not too densely packed).

[Bálint Máté @balintmt]

New preprint on performing thermodynamic integration along the trajectories of a denoising diffusion model: https://t.co/DxTbYxVb4X.

With @francoisfleuret and @tristanbereau (1/n)

[Bálint Máté @balintmt]

@eeevgen @francoisfleuret @tristanbereau Hi, thanks for the questions!
1. Yes, we do need samples at t=1.
2. Do you mean something like annealed MCMC? If so, we don't do that, just plain MCMC at the target potential.

[Bálint Máté @balintmt]

Finally, we also look at what happens if we predict the hydration free energy of methane using the potential that was trained on water (and vice versa). (10/10)

[Bálint Máté @balintmt]

new preprint on solvation free energies:

tl;dr: We define an interpolating density by its sampling process, and learn the corresponding equilibrium potential with score matching. https://t.co/sO0EI4sy5r

with @francoisfleuret and @tristanbereau
(1/n)

[Bálint Máté @balintmt]

The approach is tested on the estimation of hydration free energies of rigid water and methane (LJ + Coulomb interactions). We find good agreement with experimental reference values. (9/n)

[Kim Andrea Nicoli @nicoli_kim]

That’s a wrap! 🤩🙏🏻
Thank you everyone for making this possible and so enjoyable!

Stay tuned for a second edition in a couple of years! 😉

#ML4PhysChem #workshop #generativeAI #AI4Science