Member of Technical Staff @Angstrom_ai. prev intern @AIatMeta, @MSFTResearch, phd at @unige_en
Joined February 2021
- Tweets46
- Following329
- Followers201
- Likes433
Pinned Tweet
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. arxiv.org/abs/2410.15815
with @francoisfleuret and @tristanbereau
(1/n)
Bálint Máté retweeted
1/8) Better flow-matching samples.
No retraining.
Just multiply the velocity.
Same model.
Same 25 steps.
1.15× velocity takes FID from 28.0 to 8.7.
Unguided SiT-XL/2, ImageNet-256.
Velocity Scaling in Flow Matching, with @francoisfleuret.
Paper: arxiv.org/abs/2610.10823
Bálint Máté retweeted
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.
tristanbereau.com/positions/…
Bálint Máté retweeted
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]
Bálint Máté retweeted
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. 🧵
Bálint Máté retweeted
Now accepted at #NeurIPS2025! We basically speed up diffusion models for sampling molecular conformations by 30x :) More exciting stuff coming soon!
Bálint Máté retweeted
🚀 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. ⚛️🔥🧪⚗️🧬
Bálint Máté retweeted
🚀 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. ⚛️🔥🧪🧬
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)
1
2
407
Bálint Máté retweeted
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
Bálint Máté retweeted
To build the next generation of intelligent agents, developing efficient world models is essential.
We introduce Δ-IRIS, an agent that learns behaviors by imagining millions of trajectories in its world model.
Paper: arxiv.org/abs/2406.19320
Code: github.com/vmicheli/delta-ir…
🧵👇
New preprint on performing thermodynamic integration along the trajectories of a denoising diffusion model: arxiv.org/abs/2406.02313.
With @francoisfleuret and @tristanbereau (1/n)
Given the estimates of the canonical free energies at fixed particle count we end up with a grand canonical sampler at any choice of the chemical potential. (5/n)
1
4
1,054
