Kim Andrea Nicoli

🙌New #SpecialIssue "Deep Generative Models for Simulating Physical Systems", edited by Dr. Kim Andrea Nicoli (@nicoli_kim ), Prof. Lei Wang (@wangleiphy ), and Dr. Anindita Maiti (@AninditaMaiti7 ), is Open for Submission! 📅Deadline: 31 March 2026 mdpi.com/journal/entrop…

Finally here! 🤩 Can’t describe how good it feels to hold a real book in your hands with your name on it! 📕

🚀 New week, new preprint! We show—for the first time—how generative models can significantly outperform state-of-the-art HMC methods on correlated electron systems. Turns out, normalizing flows still have some serious tricks up their sleeve 🧙‍♂️ 🔗 arxiv.org/pdf/2506.17015

Life twist 🌪️ As of June 1st, I’ve officially left academia and embarked on a new adventure with @oldendorff1921 as Team Lead their ML department! Still research-driven, now applying probabilistic inference to maritime logistics. Exciting times ahead! 🚢✨

POV: you’re invited to give a talk about enhancing hybrid algorithms on quantum computers using ML, and you end up being photographed with a real quantum device (a.k.a. Baby Diamond) 💎 Exciting day at the Modular Supercomputing and Quantum Computing Center in Frankfurt 🤓

Ever felt like Boltzmann Generators trained with Flow Matching were doing fine, just not good enough? We slapped Path Gradients on top, and things got better. No extra samples, no extra compute, no changes to the model. Just gradients you already have access to.

If you are at #ICLR and want to know how to integrate autoregressive models within multilevel Monte Carlo sampling, make sure to swing by our Poster #175 on Saturday 10am! Looking forward to having some great chats 🙌🏻

I am excited to announce that our paper on Stochastic Normalizing Flows for Entanglement Entropy has been accepted for publication in Physics Review Letters 🚀 -> arxiv.org/abs/2410.14466 Big up to Andrea Bulgarelli for his hard work and to the rest of the collaboration 👏

The positive ML conference strike continues 💥 I am proud to share that our paper on “Multilevel Generative Samplers for Investigating Critical Phenomena” got accepted to ICLR 2025! 🎉 Stay tuned: more will follow! 🚀

Finally the preprint for our Proceedings on simulating the Hubbard Model with Normalizing Flows is out! 🚀 There’s more to come, but for the moment you can check it out here: arxiv.org/pdf/2501.07371

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