- Computational scientist @ Argonne National Laboratory
- AI / ML Group @ ALCF
- Working on:
- 🧪 {AI, HPC} for science
- 🚀 training large models on supercomputers
Now Playing
🔥 What I work on
As a member of the AI / ML Group at ALCF, I work on:
📍 How I got here
My current research focuses on using deep generative modeling to help build better sampling algorithms in lattice gauge theory. In particular, I’m interested in building gauge equivariant neural network architectures and using inductive priors to incorporate physical symmetries into machine learning models.
I received my PhD in Physics from the University of Iowa in 2019 and my thesis was on Learning Better Physics: A Machine Learning Approach to Lattice Gauge Theory.
Prior to this, I completed two bachelors degrees (Engineering Physics and Applied Mathematics, 2015) at The University of Illinois at Urbana-Champaign. My undergraduate dissertation was titled Energy Storage in Quantum Resonators and was supervised by Professor Alfred Hübler within the Center for Complex Systems Research at UIUC.
This work ultimately resulted in a patent !!
Heading 1
Content 1
Heading 2
Content 2
Heading 3
Content 3
Heading 4
Content 4
Heading 5
Content 5
Heading 6
Content 6
Inspired by my neovim config:
import datetime
from rich import print
now = datetime.datetime.now()
print(
' '.join([
"[#838383]Last Updated[/]:",
f"[#E599F7]{now.strftime("%Y-%m-%d")}[/]",
"[#838383]@[/]",
f"[#00CCFF]{now.strftime("%H:%M:%S")}[/]",
])
)Last Updated: 2025-05-23 @ 07:20:27
© Copyright Sam Foreman
MProt-DPO: Breaking the ExaFLOPS Barrier for Multimodal Protein Design Workflows with Direct Preference Optimization G. Dharuman, K. Hippe, A. Brace, S. Foreman, et al. @ SC’24
Intro to HPC Bootcamp: Engaging New Communities Through Energy Justice Projects
Journal of Computational Science, 2024Thorough Characterization and Analysis of Large Transformer Model Training At-Scale
Proc. ACM Meas. Anal. Comput. Syst. 03/2024MLMC: Machine Learning Monte Carlo for Lattice Gauge Theory
S. Foreman et al. Lattice, 2023 (Proceedings), 12/2023Protein Generation via Genome-scale Language Models with Bio-physical Scoring
@ SC’23, 11/2023DeepSpeed4Science Initiative: Enabling Large-Scale Scientific Discovery […]
@ NeurIPS 2023 AI For Science Workshop, 10/2023Comprehensive Performance Study of LLMs on Novel AI Accelerators
M. Emani, S. Foreman, et al., IPDPS 2024, 10/2023Exploratory Analysis of Climate Data with
ClimRR
S. Foreman, Intro to HPC Bootcamp @ NERSC, 08/2023GenSLMs: Genome-scale language models reveal SARS-Cov-2 evolutionary dynamics
@ SC’22 10/2022Lattice QCD and Particle Physics
A.S. Kronfeld et al., 07/2022Applications of ML to Lattice QFT
D. Boyda, S. Calí, S. Foreman, et al., [arXiv:2202.05838], 02/2022LeapFrogLayers: Trainable Framework for Effective Sampling
S. Foreman, X.Y. Jin, J.C. Osborn, Lattice, 2021HMC with Normalizing Flows [slides]
S. Foreman et al., Lattice, 2021Deep Learning Hamiltonian Monte Carlo [+ poster]
S. Foreman, X.Y. Jin, & J.C. Osborn, @ SimDL Workshop @ ICLR, 2021Machine Learning and Neural Networks for Field Theory
S. Foreman, X.Y. Jin, & J.C. Osborn, SnowMass, 2020Examples of renormalization group transformations for image sets
S. Foreman et al., Physical Review E., 2018RG inspired Machine Learning for lattice field theory
S. Foreman et al., arXiv:1710.02079, 2017Large Energy Density in Three-Plate Nanocapacitors due to Coulomb Blockade
S. Foreman et al., J. Appl. Phys, 2018
References
Convert from HTML to slideshow version of a page by appending /slides to the end of its URL, e.g.
| What | Where | When |
|---|---|---|
| LLMs on Aurora: Overview | 2025 ALCF INCITE GPU Hackathon | 2025-05-21 |
| LLMs on Aurora: Hands-On | 2025 ALCF INCITE GPU Hackathon | 2025-05-07 |
| AuroraGPT: Foundation Models for Science | Foundation Models for the Electric Grid | 2025-02-12 |
| Parallel Training Methods | Intro to AI-driven Science on Supercomputers | 2024-11-05 |
| AuroraGPT: ANL’s General Purpose Scientific LLM | ALCF Hands-on HPC Workshop | 2024-10-30 |
| Deep Learning and Foundation Models at Scale | ALCF Hands-on HPC Workshop | 2024-10-29 |
| AuroraGPT | HPC User Forum Fall ’24 | 2024-09-04 |
| Training LLMs at Scale | ATPESC 2024 | 2024-08-09 |
| LLMs on Polaris | SciFM Summer School ’24 | 2024-07-17 |
| MLMC: Machine Learning Monte Carlo | Lattice 2023 (Fermilab) | 2023-07-31 |
📆 2025
📆 2024
📆 2023
📆 2022
📆 2021
📆 2020
| What | When |
|---|---|
🚧 Frameworks Issue with numpy > 2
|
2025-05-03 |
| 🔥 Building PyTorch from Source on Aurora | 2025-04-28 |
| 👤 Résumé | 2025-04-26 |
| 🪛 Torchtune on Aurora | 2025-03-23 |
| 🚑 Torchtune Patch on Aurora | 2025-03-23 |
| 🫥 svgbob | 2024-11-15 |
| 💾 Converting Checkpoints | 2024-10-17 |
| 🏔️ Spike Skipper | 2024-09-17 |
🍋 ezpz @ ALCF
|
2024-08-23 |
| 📝 ezpz-v1 | 2024-08-23 |
| 💅 How to Make Dope Slides | 2024-08-13 |
🎰 Deterministic flash-attn
|
2024-06-17 |
📸 flash-attn on Sunspot
|
2024-06-17 |
| 🏎️ Megatron-DeepSpeed on Intel XPU | 2024-06-15 |
🐛 mpi4py bug on Sunspot
|
2024-05-25 |
| 🎲 MCMC + Diffusion Sampling | 2024-04-15 |
| 🐢 Starting Up Distributed Training on Aurora | 2024-03-21 |
| 🚂 Loooooooong Sequence Lengths | 2024-02-12 |
🏁 l2hmc Example: 2D U(1)
|
2024-02-12 |
🎢 l2hmc-qcd Example: 2D U(1)
|
2023-12-14 |
🔳 l2hmc-qcd Example: 4D SU(3)
|
2023-12-06 |
Even More !!
Wakatime
saforem2/
🎓 Education
- Ph.D., Physics
- University of Iowa, 2019
- Learning Better Physics: A Machine Learning Approach to Lattice Gauge Theory
- University of Iowa, 2019
- B.S. in Engineering Physics
- University of Illinois at Urbana-Champaign, 2015
- Energy Storage in Quantum Resonators (US Patent #US9741492B2)
- B.S. in Applied Mathematics
- University of Illinois at Urbana-Champaign, 2015
🧑🔬 Professional Experience
- Assistant Computational Scientist
- Argonne National Laboratory, Argonne Leadership Computing Facility (ALCF)
- Lemont, IL | 2022 – Present
- Research lead on scaling large language models (LLMs) and generative AI for science on supercomputers (Aurora, Frontier, LUMI, Leonardo, …).
- Optimize large-scale training of foundation models and language models for scientific applications.
- Collaborate with interdisciplinary teams to enhance simulation efficiency and scalability.
- Focus on AI and HPC for scientific applications, including:
- Developing improved sampling algorithms for lattice quantum chromodynamics (QCD)
- Training large language models on supercomputers
- https://www.alcf.anl.gov/about/people/sam-foreman
- Argonne National Laboratory, Argonne Leadership Computing Facility (ALCF)
- Postdoctoral Researcher
- Argonne National Laboratory, Argonne Leadership Computing Facility (ALCF)
- Lemont, IL | 2019 – 2022
- Applied deep learning to lattice gauge theory and quantum field simulations.
- Developed ML-enhanced Monte Carlo methods for QCD.
- Engaged in AI-for-Science collaborations with national labs and university partners.
- Argonne National Laboratory, Argonne Leadership Computing Facility (ALCF)
- Graduate Researcher
- Argonne National Laboratory, Math and Computer Sciences (MCS)
- Lemont, IL | 2018 – 2019
- Collaborated with ALCF while completing Ph.D., integrating ML into physical sciences workflows.
🏆 Awards and Honors
- ACM Gordon Bell Special Prize for High Performance Computing-Based COVID-19 Research, 2022
- Recognized for contributions to the GenSLMs project, which developed genome-scale language models to study SARS-CoV-2 evolutionary dynamics.
- https://www.acm.org/media-center/2022/november/gordon-bell-special-prize-covid-research-2022
- Finalist, ACM Gordon Bell Prize, 2024
- Acknowledged for the MProt-DPO project, which achieved over 4 ExaFLOP sustained performance in multimodal protein design workflows using Direct Preference Optimization.
- https://sc.cels.anl.gov/gordon-bell-argonne-team-breaks-new-ground-in-ai-driven-protein-design/
- DOE Office of Science Graduate Student Research Fellow, 2018
- Awarded by the Department of Energy for outstanding research contributions during graduate studies.
📚 Publications1
- MProt-DPO: Breaking the ExaFLOPS Barrier for Multimodal Protein Design Workflows with Direct Preference Optimization
- GenSLMs: Genome-Scale Language Models Reveal SARS-CoV-2 Evolutionary Dynamics
- Applications of Machine Learning to Lattice Quantum Field Theory
- HMC with Normalizing Flows
- Deep Learning Hamiltonian Monte Carlo
- Examples of Renormalization Group Transformations for Image Sets
🎤 Selected Talks2
- AuroraGPT: Foundation Models for Science @ Foundation Models for the Electric Grid [02/2025]
- Parallel Training Methods @ AI-for-Science on Supercomputers [11/2024]
- AuroraGPT @ HPC User Forum, 2024 [09/2024]
- Machine Learning and Foundation Models at Scale @ 2024 ALCF Hands-On HPC Workshop [10/2024]
- Training LLMs at Scale @ ATPESC, 2024 [08/2024]
- LLMs from Scratch @ LLM Tutorial Workshop [02/2024]
- Exascale Science on Aurora @ Intel oneAPI Workshop @ UIC [10/2023]
- Scaling LLMs for Science @ Data-Intensive Computing + AI/ML at Scale [08/2023]
- MLMC: Machine Learning Monte Carlo @ Lattice 2023 [07/2023]
- Generative Modeling and Efficient Sampling @ PASC23 [07/2023]
🎪 Events
Organizer for:
SC24 Workshop: High Performance Python for Science at Scale (HPPSS), November 2024
SC23 Workshop: High Performance Python for Science at Scale (HPPSS), November 2023
Machine Learning and Quantum Computing for Earth Sciences at 17th U. S. National Congress on Computational Mechanics, July 2023
👔 Employment
| Position | @ | Start | End |
|---|---|---|---|
| Assistant Computational Scientist | ALCF | 2022 | – |
| Postdoc | ALCF | 2019 | 2022 |
| Graduate Researcher | ANL | 2018 | 2019 |
🍎 School
Footnotes
See full list on Google Scholar↩︎
See full list at: samforeman.me/talks↩︎
Citation
@online{foreman2025,
author = {Foreman, Sam},
date = {2025-05-23},
url = {https://samforeman.me/},
langid = {en}
}