Papers & Code

Peer-reviewed papers, preprints, and the software I build alongside them.

Equivariant ML for chemistry

Equivariant generative model that produces MD trajectories without an integrator
Given the last few frames, an E(3)-equivariant network (eSCN-style SO(2) convolutions with Wigner-D alignment, l_max = 2, causal attention over time) predicts the frame 50 fs ahead with a flow-matching head. On Lennard-Jones argon (256 atoms), 4 of 5 training seeds run 10⁴-step rollouts without crashing, and the best match OpenMM temperature, RDF, VACF and diffusion within v0 tolerances. Rollout speed is 25.8 ns/day on one A100.
Python · PyTorch · OpenMM · flow matching · A100 profiling
Rotation-aware optical chemical structure recognition
Turns a molecule drawing into SMILES with stereochemistry, and compares a standard CNN, a rotation-augmented CNN and a C8 steerable (rotation-equivariant) encoder under one shared decoder and evaluation protocol. Best result on 298 real images: 54.0% exact match (ACS 40%, UOB 84%, USPTO 37.8%) with an A + C ensemble and beam 5. Includes an interactive rotation lab.
Python · PyTorch · escnn steerable CNNs · RDKit · Transformer decoder
YLM
Language tokens that read 3D vectors and tensors directly
An Irreps-to-Text cross-attention layer: text tokens attend to SE(3)-equivariant atom features with invariant weights, so a question such as "what is the force on this oxygen?" returns a vector that rotates exactly with the molecule (error ~2e-6). On the TensorQA-v0 benchmark (84,757 questions on 20k QM9 molecules) it reaches force cosine 0.96, versus 0.11 when the question text is removed.
Python · PyTorch · MatSciBERT / MiniLM · QM9

Systems

VERDICT
Consensus optical chemical structure recognition, with a browser extension
Four independent recognizers — DECIMER, MolScribe, MolNexTR and a fine-tuned GLM-4.1V — vote by molecular identity (InChIKey), and the winner must still survive chemical parsing and an image round-trip. The answer is one canonical SMILES with a confidence tier, an explicit abstention path, and a per-engine audit trace. On ACS figures the quorum accepts 88.5% of crops at 86.2% precision.
Python · PyTorch · RDKit · HTTP service (per-engine workers) · Chrome extension
Molecule multimodal RAG
Retrieval across text, figures, and multi-scale simulation
A molecular knowledge graph in which depictions and simulations are first-class retrieval modalities, not just text. Literature text and figures are harvested and passed through OCSR, so every record carries a structure keyed on its parent InChIKey plus the DOI, figure and engine votes behind it. Retrieval mixes semantic search, structure similarity, exact-InChIKey lookup and structural search over DFT and MD records — which is what joins a molecule in a paper to the formulations it appears in.
Python · RDKit · OPSIN · SQLite/FTS5 hybrid retrieval · graph expansion
LLM and HPC agentic platform for quantum-chemistry workflows
Turns a natural-language request into production DFT calculations: an agent chain parses intent, proposes reaction hypotheses with RAG, builds structures, prepares VASP inputs, submits batch jobs to PBS/Slurm and analyses the results (adsorption and free energies). Bayesian optimisation of DFT parameters needs 73% fewer evaluations than a grid search.
Python · LLM agents · RAG · ASE / pymatgen · VASP · PBS/Slurm · AWS EKS
Multimodal agent for reasoning over scientific images
A ReAct agent that answers questions about spectra, XRD patterns, microscopy and molecule images by calling composable vision skills, returning structured data with per-skill confidence and a low-confidence flag. Includes a capability-audit benchmark and LoRA fine-tuning for Qwen-VL.
Python · vision-language models (Claude, Qwen-VL) · FastAPI · Streamlit

Tools & experiments

Submit and monitor HPC jobs over SSH from one dashboard
Python · SSH · PBS/Slurm
Bookmark manager web app with a companion browser extension
TypeScript · Next.js · Supabase · Chrome extension
Modular MCP agent with an arXiv paper-fetching tool
Python · MCP · FastAPI

Publications

410 citations · h-index 9 · i10-index 9 — Google Scholar

Papers & preprints

  1. Nature Catal.
    Desolvated cations promote CO2 electroreduction through partial covalent interactions
    Yu Shan, Maximilian Jaugstetter, Julian Feijóo, and 14 more authors
    Nature Catalysis, Sep 2026
    Yu Shan, Maximilian Jaugstetter, Julian Feijóo and Yani Guan contributed equally.
  2. Ag Amination
    ag_amination.jpeg
    Electrochemical Amination of Acetone using Ag as Cathode: Mechanism and Role of Pb Impurities for Hydrogen Transfer
    Yani Guan, Justus Kümper, Angelina Cuomo, and 6 more authors
    Catalysis Science & Technology, Sep 2026
  3. MU-PFF MD
    mu_md_platform.png
    High-throughput Molecular Dynamics Simulation on an AI-powered Platform
    Dengpan Dong, Yani Guan, Shuang Luo, and 5 more authors
    ChemRxiv preprint, Sep 2026
    MU-PFF: a machine-learned many-body polarizable force field plus automated system building and trajectory analysis, taking an electrolyte formulation from SMILES to predicted properties without manual parameterization.
  4. OCSR VLM
    ocsr_real_data.png
    Real Data Closes Synthetic-to-Real Gap in Optical Chemical Structure Recognition
    Yani Guan, Dengpan Dong, Zi Wei, and 4 more authors
    arXiv preprint arXiv:2608.09100, Sep 2026
    * Equal contribution. Vision-language models for image-to-SMILES: real labeled depictions, not more synthetic data, are what close the synthetic-to-real gap.
  5. VERDICT
    VERDICT: Agreement Beats Pixel-Space Verification in Real-Document OCSR
    Yani Guan, Dengpan Dong, Shuang Luo, and 6 more authors
    arXiv preprint arXiv:2608.22183, Sep 2026
    Label-free verification for image-to-SMILES at scale: agreement among four architecturally distinct recognizers reaches AUROC 0.916, while re-rendering a prediction and comparing pixels barely beats chance at 0.547.
  6. EDLC
    capacitance.png
    Probing the Electric Double-Layer Capacitance to Understand the Reaction Environment in Conditions of Electrochemical Amination of Acetone
    Yani Guan, Justus Kümper, Simran Kumari, and 6 more authors
    ACS Applied Materials & Interfaces, Sep 2025
  7. DFT-KMC
    First-principles-based kinetic monte carlo model of hydrogen evolution reaction under realistic conditions: solvent, hydrogen coverage and electric field effects
    Yuhong Luo, Yani Guan, Guihua Liu, and 3 more authors
    ACS Catalysis, Sep 2024
  8. pb.png
    Metallic Impurities in Electrolysis: Catalytic Effect of Pb Traces in Reductive Amination and Acetone Reduction
    Justus Kümper, Sonja D Mürtz, Yani Guan, and 5 more authors
    Angewandte Chemie International Edition, Sep 2024
  9. Metallische Verunreinigungen in der Elektrolyse: Katalytische Wirkung von Pb-Spuren in der reduktiven Aminierung und Acetonreduktion
    Justus Kümper, Sonja D Mürtz, Yani Guan, and 5 more authors
    Angewandte Chemie, Sep 2024
    German edition of the Angewandte Chemie International Edition article of the same title.
  10. Cu Dissolution
    Dissolution.png
    Origin of copper dissolution under electrocatalytic reduction conditions involving amines
    Yani Guan, Justus Kümper, Sonja D Mürtz, and 4 more authors
    Chemical Science, Sep 2024
  11. ML for Catalysis
    ml_catalysis.jpeg
    Machine learning in solid heterogeneous catalysis: Recent developments, challenges and perspectives
    Yani Guan, Donovan Chaffart, Guihua Liu, and 5 more authors
    Chemical Engineering Science, Sep 2022
  12. Li-S Battery
    Ordered macroporous V-doped ZnO framework impregnated with microporous carbon nanocages as multifunctional sulfur reservoir in lithium-sulfur batteries
    Ximeng Zhao, Yani Guan, Xiaohang Du, and 3 more authors
    Chemical Engineering Journal, Sep 2022
  13. A conductive and ordered macroporous structure design of titanium oxide-based catalytic cathode for lithium–sulfur batteries
    Fan Liu, Yani Guan, Xiaohang Du, and 3 more authors
    Nanotechnology, Sep 2021
  14. Zn-Air Battery
    A macroporous titanium oxynitride-supported bifunctional oxygen electrocatalyst for zinc–air batteries
    Weixing Niu, Yani Guan, Yuhong Luo, and 2 more authors
    Catalysis Science & Technology, Sep 2021
  15. CO2 DFT
    co2_dft.png
    Insights on the catalytic active site for CO2 reduction on copper-based catalyst: a DFT study
    Yani Guan, Wei Suo, Zisheng Zhang, and 3 more authors
    Molecular Catalysis, Sep 2021
  16. Nanoscale melamine-based porous organic frameworks as host material for efficient polysulfides chemisorption in lithium–sulfur batteries
    Miao Sun, Haifeng Ji, Yani Guan, and 5 more authors
    Nanotechnology, Sep 2020
  17. Bifunc. Catalyst
    cobalt_nitride.jpeg
    Surface-engineered cobalt nitride composite as efficient bifunctional oxygen electrocatalyst
    Yani Guan, Guihua Liu, Jingde Li, and 2 more authors
    Nanotechnology, Sep 2019

Conference

  1. Origin of Copper Dissolution in Electrocatalytic Reduction Conditions Involving Amines
    Yani Guan and Philippe Sautet
    In Electrochemical Society Meeting Abstracts prime2024, 2024

Thesis

  1. Modeling the Electrocatalytic Interface in the Conditions of Electrochemical Amination of Acetone with Methylamine as Nitrogen Source
    Yani Guan
    University of California, Los Angeles, 2024