ML @PeptoneLtd. prev intern @AIatMeta, @MSFTResearch, phd at @unige_en

Joined February 2021
Photos and videos
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)
3
19
100
12,208
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]
1
32
155
8,330
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. 🧵
3
16
61
22,948
Bálint Máté retweeted
Now accepted at #NeurIPS2025! We basically speed up diffusion models for sampling molecular conformations by 30x :) More exciting stuff coming soon!
Really excited to (finally) share the updated JAMUN preprint and codebase! We perform Langevin molecular dynamics in a smoothed space which allows us to take larger integrator steps. This requires learning a score function only at a single noise level, unlike diffusion models.
1
2
38
2,750
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. ⚛️🔥🧪⚗️🧬
1
30
189
13,931
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. ⚛️🔥🧪🧬
5
61
291
33,186
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)
3
19
100
12,208
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
401
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)
2
325
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
4
22
1,580
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… 🧵👇
12
50
287
47,538
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)
6
37
210
31,210
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
1,048
To validate all this, we compare the estimates of the average density and the excess chemical potential to grand canonical MC simulations. (6/n)
1
3
886