
Member of Technical Staff @Angstrom_ai. prev intern @AIatMeta, @MSFTResearch, phd at @unige_en
Joined February 2021
- Tweets46
- Following329
- Followers201
- Likes433
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. ⚛️🔥🧪🧬
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…
🧵👇
Bálint Máté retweeted
🚨 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
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) 🧵👇
Bálint Máté retweeted
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.…
Bálint Máté retweeted
"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.
Bálint Máté retweeted
Aaand another one! With, among others, @atulku and @balintmate_.
Bálint Máté retweeted
Learning Interpolations between Boltzmann Densities
Bálint Máté, François Fleuret.
Action editor: Ruoyu Sun.
openreview.net/forum?id=TH6Y…
#boltzmann #gaussian #divergence
Bálint Máté retweeted
Can you train GNNs without backprop? We extend the forward-forward algorithm to graph property prediction tasks, and the results are promising.
Joint work with @miniapeur @balintmate_ @francoisfleuret.
arxiv.org/abs/2302.05282
1/N


















