Sadman Sadeed Omee

Hi, I am Sadman Sadeed Omee.

I am a Ph.D. Candidate in the Department of Computer Science and Engineering at the University of South Carolina. I am advised by Dr. Jianjun Hu, and I work as a Graduate Research Assistant in the Machine Learning and Evolution Laboratory under his supervision. My Ph.D. research focuses on using Artificial Intelligence (AI) and Machine Learning (ML) to solve problems from the materials science domain, leveraging concepts from core ML areas, such as natural language processing (NLP) and computer vision (CV).

My aim is to solve real-world scientific challenges, particularly core and unsolved problems, through the integration of advanced AI/ML techniques with fundamental scientific principles. I aspire to develop intelligent computational systems that can assist scientists in making new discoveries, unveiling hidden patterns in complex data, and advancing our understanding of the physical world.

News / Updates
  • [December 31, 2025] Our in-context learning foundation model framework paper's preprint is available on arXiv.
  • [October 24, 2025] Our updated template-based crystal structure prediction paper publihsed in Computational Materials Science.
  • [September 26, 2025] Our polymorphism crystal structure prediction paper publihsed in Advanced Science.
  • [August 8, 2025] Completed summer internship at KLA.
  • [May 12, 2025] Started summer internship at KLA.
Education
 
 
 
 
 
UofSC logo

University of South Carolina

Ph.D.
Computer Science
August 2021 - Present
 
 
 
 
 
UofSC logo

University of South Carolina

M.S. (en route to Ph.D.)
Computer Science
August 2021 - December 2024
 
 
 
 
 
BUET logo

Bangladesh University of Engineering and Technology

B.S.
Computer Science and Engineering
February 2015 - April 2019
Experience
 
 
 
 
 
UofSC logo

Graduate Research Assistant

Machine Learning and Evoluation Laboratory
Department of Computer Science and Engineering
University of South Carolina
Columbia, South Carolina, United States
January 2022 - Present
  • Designed and applied advanced deep learning models, including graph neural networks (GNNs), large language models (LLMs), and diffusion models, to solve problems from the materials science domain such as crystal structure prediction (CSP), materials property prediction, and generative models for materials.
  • Authored multiple peer-reviewed research publications in high-impact journals, demonstrating strong research productivity and impact in AI for science.
  • Currently developing a conditional E(3)-equivariant diffusion model for 3D crystal polyhedra generation from chemical compositions, targeting fundamental scalability and accuracy bottlenecks in CSP.
 
 
 
 
 
UofSC logo

Graduate Teaching Assistant

Course: General Applications Programming (CSCE 102)
Department of Computer Science and Engineering
University of South Carolina
Columbia, South Carolina, United States
August 2023 - Present
  • Teaching HTML, CSS, and JavaScript to three lecture and one lab group of approximately 75 students and 25 students, respectively.
  • Responsibilities include delivering lectures, preparing examinations and assignments, grading examinations and assignments, tracking students' performances, and publishing results.
 
 
 
 
 
UofSC logo

Summer Intern

KLA
Ann Arbor, Michigan, United States
May 2025 - August 2025
  • Developed a continual transfer learning framework for predicting semiconductor wafer critical dimensions from spectral data.
  • Improved out-of-distribution (OOD) robustness of ML-based metrology models, enabling reliable performance under real-world manufacturing distribution shifts.
  • Collaborated with cross-functional engineering teams in a production-oriented research environment.
 
 
 
 
 
UofSC logo

Summer Intern

Lawrence Livermore National Laboratory
Livermore, California, United States
May 2024 - August 2024
  • Co-developed a multimodal molecular foundation model integrating molecular structure, XANES spectra, SMILES representations, and HOMO–LUMO gap data using contrastive learning–based latent space alignment.
  • Implemented modality-specific encoders, including graph neural networks for molecular structures and deep neural network architectures for spectral and string-based modalities, to enable unified cross-modal molecular representations.
  • Participated in weekly research seminars with LLNL scientists focused on advanced machine learning models for materials and molecular science, high-performance computing (HPC), and related computational science fields.
 
 
 
 
 
UofSC logo

Graduate Instructional Assistant

Course: Introduction to Computer Concepts (CSCE 101) & General Applications Programming (CSCE 102)
Department of Computer Science and Engineering
University of South Carolina
Columbia, South Carolina, United States
August 2021 - December 2021
  • Conducted web-development lab sessions of two lab groups of approximately 50 students.
Research

My Ph.D. research focuses on AI-driven materials science.

As a Ph.D. candidate in Computer Science at the University of South Carolina, I conduct research at the intersection of AI/ML and materials science. My work focuses on developing advanced machine learning methods to accelerate the discovery and design of novel materials. I specialize in graph neural networks (GNNs), large language models (LLMs), foundation models, and diffusion models for solving core materials informatics challenges such as crystal structure prediction (CSP), materials property prediction, and generative modeling of materials.

My research particularly emphasizes AI-driven approaches for crystal structure prediction, a long-standing challenge in materials science similar to the protein structure prediction problem. I draw inspiration from breakthroughs such as AlphaFold2 (won 2024 Nobel Prize in Chemistry) and aim to extend similar paradigms to crystalline systems. By integrating scientific domain knowledge with state-of-the-art AI models, I seek to enable automated materials discovery and accelerate innovation in materials design.

My current research focuses on developing an E(3)-equivariant diffusion model for conditional generation of 3D crystal polyhedra (building blocks of crystals), given their chemical compositions (e.g., NaCl, SrTiO3, Cu4FeGe2S7). Successful prediction of the polyhedra of a crystal can lead to accurate prediction of the full crystal structure and provide an efficient solution to the CSP problem. I am inspired by successful diffusion model-based approaches in similar problems, such as molecular and protein structure prediction.

Research Metrics
Loading metrics…
Publications
Journal Papers
  • ParetoCSP2 image

    Polymorphism Crystal Structure Prediction with Adaptive Space Group Diversity Control

    Sadman Sadeed Omee, Lai Wei, Sourin Dey, Jianjun Hu
    Advanced Science
    2025
    Paper PDF PDF (arxiv) Code
  • DeeperGATGNN image

    Scalable Deeper Graph Neural Networks for High-Performance Materials Property Prediction

    Sadman Sadeed Omee, Steph-Yves Louis, Nihang Fu, Lai Wei, Sourin Dey, Rongzhi Dong, Qinyang Li, Jianjun Hu
    Patterns
    2022
    Paper PDF PDF (arxiv) Code
  • OOD Materials Benchmark image

    Structure-Based Out-of-Distribution (OOD) Materials Property Prediction: A Benchmark Study

    Sadman Sadeed Omee, Nihang Fu, Rongzhi Dong, Ming Hu, Jianjun Hu
    npj Computational Materials
    2024
    Paper PDF PDF (arxiv) Code
  • ParetoCSP image

    Crystal Structure Prediction Using Neural Network Potential and Age-Fitness Pareto Genetic Algorithm

    Sadman Sadeed Omee, Lai Wei, Ming Hu, Jianjun Hu
    Journal of Materials Informatics
    2024
    Paper PDF (arxiv) Code
  • MD-HIT image

    MD-HIT: Machine Learning for Materials Property Prediction with Dataset Redundancy Control

    Qin Li, Nihang Fu, Sadman Sadeed Omee, Jianjun Hu
    npj Computational Materials
    2024
    Paper PDF PDF (arxiv) Code
  • MaterialsAtlas image

    MaterialsAtlas.org: A Materials Informatics Web App Platform for Materials Discovery and Survey of State-of-the-Art

    Jianjun Hu, Stanislav Stefanov, Yuqi Song, Sadman Sadeed Omee, Steph-Yves Louis, Edirisuriya M. D. Siriwardane, Yong Zhao
    npj Computational Materials
    2022
    Paper PDF PDF (arxiv)
  • CSPBench

    TCSP 2.0: Template Based Crystal Structure Prediction with Improved Oxidation State Prediction and Chemistry Heuristics

    Lai Wei, Rongzhi Dong, Nihang Fu, Sadman Sadeed Omee, Jianjun Hu
    2025
    Paper PDF (arxiv) Code
  • Material Transformers image

    Material Transformers: Deep Learning Language Models for Generative Materials Design

    Nihang Fu, Lai Wei, Yuqi Song, Qinyang Li, Rui Xin, Sadman Sadeed Omee, Rongzhi Dong, Edirisuriya M Dilanga Siriwardane, Jianjun Hu
    Machine Learning: Science and Technology
    2023
    Paper PDF PDF (arxiv) Code
  • Voltage GNN image

    Accurate Prediction of Voltage of Battery Electrode Materials Using Attention Based Graph Neural Networks

    Steph-Yves Louis, Edirisuriya M. D. Siriwardane, Rajendra P. Joshi, Sadman Sadeed Omee, Neeraj Kumar, Jianjun Hu
    ACS Applied Materials & Interfaces
    2022
    Paper PDF (chemrxiv) Code
  • DeepXRD image

    DeepXRD: A Deep Learning Model for Predicting XRD Spectrum from Materials Composition

    Rongzhi Dong, Yong Zhao, Yuqi Song, Nihang Fu, Sadman Sadeed Omee, Sourin Dey, Qinyang Li, Lai Wei, Jianjun Hu
    ACS Applied Materials & Interfaces
    2022
    Paper PDF (arxiv)
  • UQ Benchmark image

    Materials Property Prediction with Uncertainity Estimation: A Benchmark Study

    Daniel Varivoda, Rongzhi Dong, Sadman Sadeed Omee, Jianjun Hu
    Applied Physics Reviews
    2023
    Paper PDF (arxiv) Code
  • Physical Encoding image

    Physical Encoding Improves out-of-distribution (OOD) Performance in Deep Learning Materials Property Prediction

    Nihang Fu, Sadman Sadeed Omee, Jianjun Hu
    Computational Materials Science
    2024
    Paper PDF (arxiv) Code
  • Global Mapping image

    Global Mapping of Structures and Properties of Crystal Materials

    Qinyang Li, Rongzhi Dong, Nihang Fu, Sadman Sadeed Omee, Lai Wei, Jianjun Hu
    Journal of Chemical Information and Modeling
    2023
    Paper PDF PDF (arxiv) Code
  • CSP Metrics image

    Towards Quantitative Evaluation of Crystal Structure Prediction Performance

    Lai Wei, Qin Li, Sadman Sadeed Omee, Jianjun Hu
    Computational Materials Science
    2024
    PDF PDF (arxiv) Code
  • TCSP image

    TCSP: A Template-Based Crystal Structure Prediction Algorithm for Materials Discovery

    Lai Wei, Nihang Fu, Edirisuriya M. D. Siriwardane, Wenhui Yang, Sadman Sadeed Omee, Rongzhi Dong, Rui Xin, Jianjun Hu
    Inorganic Chemistry
    2022
    Paper PDF (arxiv)
Book Chapters
  • Book Chapter image

    Evolutionary Machine Learning in Science and Engineering

    Jianjun Hu, Yuqi Song, Sadman Sadeed Omee, Lai Wei, Rongzhi Dong, Siddharth Gianey
    Handbook of Evolutionary Machine Learning
    2023
    Chapter
Pre-prints
  • FARM image

    In Context Learning Foundation Models for Materials Property Prediction with Small Datasets

    Qinyang Li, Rongzhi Dong, Nicholas Miklaucic, Jeffrey Hu, Sadman Sadeed Omee, Lai Wei, Sourin Dey, Ming Hu, Jianjun Hu
    2025
    PDF (arxiv)
  • CSPBench

    Facet: Highly Efficient E(3)-Equivariant Networks for Interatomic Potentials

    Nicholas Miklaucic, Lai Wei, Rongzhi Dong, Nihang Fu, Sadman Sadeed Omee, Qingyang Li, Sourin Dey, Victor Fung Jianjun Hu
    2025
    PDF (arxiv) Code
  • CSPBench

    Data-Driven Topological Analysis of Polymorphic Crystal Structures

    Sourin Dey, Nicholas Miklaucic, Sadman Sadeed Omee, Rongzhi Dong, Lai Wei, Qinyang Li, Nihang Fu, Jianjun Hu
    2025
    PDF (arxiv)
  • CSPBench

    Crystal Structure Prediction: a Benchmark and Modern Evaluation

    Lai Wei, Sadman Sadeed Omee, Rongzhi Dong, Nihang Fu, Yuqi Song, Edirisuriya Siriwardane, Meiling Xu, Chris Wolverton, Jianjun Hu
    2024
    PDF (arxiv)
Résumé

It appears you don't have a PDF plugin for this browser. No problem... you can click here to download the PDF file.

Blogs

I will try to write blogs on Deep Learning concepts, especially on the paradigm of Generative AI. I will also try to cover some important research papers in this field and some of my own papers.

Coming soon ...
Contact
Personal: 
omee.sadman@gmail.com
Instituitional: 
somee@email.sc.edu
Columbia, SC, United States
+1 (803)-243-3777
Connect me on 
Linked
in
Check my codes on 
GitHub
Follow my research on ORC
iD
Follow my research on 
G
o
o
g
l
e
 Scholar
Follow my research on  
p
ublons
Follow my research on  
RG
esearchGate
Add me on  
Facebook
Follow me on  
X
Follow me on  
Instagram
Follow me on  
Pinterest