BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Mimer AI Factory - ECPv6.17.0//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Mimer AI Factory
X-ORIGINAL-URL:https://mimer-ai.eu
X-WR-CALDESC:Events for Mimer AI Factory
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20250330T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20251026T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20260329T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20261025T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20270328T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20271031T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Stockholm:20260930T100000
DTEND;TZID=Europe/Stockholm:20260930T113000
DTSTAMP:20260702T113020Z
CREATED:20260702T113020Z
LAST-MODIFIED:20260702T113020Z
UID:5629-1790762400-1790767800@mimer-ai.eu
SUMMARY:Foundation Models for Atoms: Machine-Learned Interatomic Potentials in Practice
DESCRIPTION:Mimer AI Factory and ENCCS jointly organise this webinar to introduce how machine-learned interatomic potentials can support larger and more efficient simulations on modern HPC systems. \nWhy machine-learned interatomic potentials matter\nQuantum-mechanical methods such as density functional theory (DFT) are accurate but limited to small systems and short timescales. Classical force fields are fast but often not accurate or transferable enough. Machine-learned interatomic potentials (MLIPs) could break this trade-off between accuracy and scale\, and the field is now moving at remarkable speed. \nSo-called universal or “foundation” models (e.g. MACE-MP\, UMA\, MatterSim\, Orb\, the DPA/OpenLAM series) use tens to hundreds of millions of DFT calculations spanning the periodic table for pre-training. These models approach DFT-level accuracy at a small fraction of the cost. Researchers can apply them out-of-the-box (“zero-shot”) to almost any chemistry. Afterward\, they can fine-tune them to a specific system with a small amount of targeted data. This shortens the path from question to result for both academic and industrial users. \nWhat the webinar will cover\nIn this webinar\, we will give a conceptual tour of this rapidly evolving landscape and what it means for everyday computational research on HPC systems. We will cover: \n\nwhat universal MLIPs are and how they differ from classical force fields and system-specific ML potentials;\nthe practical pre-train → fine-tune workflow and when out-of-the-box use is (and is not) good enough;\nthe new generation of batched\, GPU-accelerated simulation engines (e.g. TorchSim\, kUPS) built for high-throughput MLIP simulation;\nhow to choose and trust a model using open benchmarks;\nand a brief outlook on where the field is heading.\n\nThis includes ML making its way into electronic-structure theory itself\, with learned density functionals. We will also include a short demo on European HPC resources. Throughout\, we will point to open models\, datasets\, benchmarks\, and codes. Participants can try these on their own problems right after the webinar. \nWho is the webinar for\nThis webinar is for: \n\nresearchers and students in computational materials science\, chemistry\, and condensed-matter physics who use DFT or ab initio MD and want to reach larger systems and longer timescales without giving up accuracy;\nusers of classical molecular dynamics (LAMMPS\, GROMACS\, ASE workflows) curious about upgrading to ML-based potentials;\nindustry R&D scientists and engineers exploring AI-accelerated materials and molecular discovery;\nHPC support staff and research software engineers who want an overview of the modern MLIP software stack and what it needs from GPU systems;\nanyone curious about how the foundation-model paradigm from language and vision AI is reshaping simulation in the natural sciences.\n\nParticipants do not need prior experience with multiplet theory\, density functional theory (DFT)\, or many-body methods. Familiarity with basic concepts from solid-state or atomic physics is sufficient. The webinar will introduce the role of data and HPC in modern electronic-structure studies at a conceptual level. \nKey takeaways\nBy the end of this webinar\, participants will: \n\nunderstand what universal machine-learned interatomic potentials are and why they deliver near-DFT accuracy at a fraction of the cost;\nknow the practical pre-train → fine-tune workflow: when an off-the-shelf foundation model is sufficient\, when and how to fine-tune it with a small targeted dataset;\nget an overview of the modern MLIP software stack\, from ASE/LAMMPS integrations to GPU-native\, batched engines such as TorchSim\, and what it takes to run it efficiently on EuroHPC systems;\ncritically select and validate a model using open benchmarks and understand why no single model wins on every axis;\ngain an outlook on emerging directions: long-range electrostatics\, MLIPs that predict polarisation and spectra\, the use of machine learning within DFT itself\, and early work on AI agents that help orchestrate computational workloads.\n\nOrganisers\nMimer AI Factory & ENCCS \nSpeaker and moderator\n\nKarim Elgammal\nYonglei Wang/Wei Li
URL:https://mimer-ai.eu/event/foundation-models-for-atoms-machine-learned-interatomic-potentials-in-practice/
ATTACH;FMTTYPE=image/jpeg:https://mimer-ai.eu/wp-content/uploads/2026/07/Mimer-enccs-webinar.jpg
END:VEVENT
END:VCALENDAR