Bálint Máté (@balintmt) profile picture

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

Joined February 2021
Photo by Bálint Máté (@balintmt)Photo by Bálint Máté (@balintmt)Photo by Bálint Máté (@balintmt)Photo by Bálint Máté (@balintmt)Photo by Bálint Máté (@balintmt)Photo by Bálint Máté (@balintmt)Photo by Bálint Máté (@balintmt)Photo by Bálint Máté (@balintmt)Photo by Bálint Máté (@balintmt)Photo by Bálint Máté (@balintmt)
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
6
39
1
256
14,422
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/…
6
19
1,646
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
30
1
156
9,385
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
1
64
24,039
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
2,763
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
1
191
14,115
🚀 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
62
14
288
33,439
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
1,596
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
10
286
47,651
🚨 Workshop Alert 🚨 Dive into Gen AI and its applications, from physics to drug design, with a top-notch line-up of speakers! 🚀 Join us in Bonn this fall! 🇩🇪 Register now: indico.hiskp.uni-bonn.de/eve… #AI4Science #Workshop #UniBonn #GenerativeModels
3
8
2
33
7,038
Bálint Máté retweeted
We introduce DIAMOND (DIffusion As a Model Of eNvironment Dreams), a reinforcement learning agent trained entirely in a diffusion world model. 💎 Paper: arxiv.org/abs/2405.12399 Code: github.com/eloialonso/diamon… (1/n) 🧵👇
12
112
17
614
135,813
I am still processing the tons of applications I got for PhD positions in my group @unige_en (200+!!!) and I have a fourth opening, this one on the prediction (with NLP + time series) of Acute Kidney Failure, in collaboration with the @hug_ge. fleuret.org/francois/hiring.…
4
6
73
21,918
"Wir sollen in Europa alle Europäer sein" sagt Nobelpreisträger Ferenc Krausz auf die Frage, welchem Land sein Nobelpreis nun zuzuordnen sei. Und dem ist eigentlich nichts hinzuzufügen.
29
137
4
1,318
52,203
Aaand another one! With, among others, @atulku and @balintmate_.
1
6
472
Learning Interpolations between Boltzmann Densities Bálint Máté, François Fleuret. Action editor: Ruoyu Sun. openreview.net/forum?id=TH6Y… #boltzmann #gaussian #divergence
2
1
6
3,651