Yi-Fan Hou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yi-Fan Hou has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- Pavlo O. Dral
Xiamen University
24 shared publications - Fuchun Ge
State Key Laboratory of Physical Chemistry of Solid Surfaces, College of Chemistry and Chemical Engineering, Fujian Provincial Key Laboratory of Theoretical and Computational Chemistry, and Innovation Laboratory for Sciences and Technologies of Energy Materials of Fujian Province (IKKEM), Xiamen University, Xiamen, Fujian 361005, China
9 shared publications - Lina Zhang
Xiamen University
7 shared publications - Mario Barbatti
Aix Marseille University, CNRS, ICR
7 shared publications - Yuxinxin Chen
Xiamen University
6 shared publications - Arif Ullah
Anhui University
4 shared publications
Latest Publications
- 22 June 2026
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 22 (13) , 6557-6571
Aitomia: An Agentic Framework for AI-Driven Atomistic and Quantum Chemical Simulations
We present Aitomia, an agentic framework for AI-driven atomistic and quantum chemical (QC) simulations that helps experts and nonexperts alike set up and run calculations, analyze results, and summarize them in textual and graphical forms through natural language interaction. Built on the MLatom software ecosystem, Aitomia supports AI-driven atomistic simulations as well as conventional quantum-chemical calculations, including density functional theory, semiempirical methods such as GFN2-xTB, and selected high-level wave function-based methods, through interfaces to widely used programs such as Gaussian, ORCA, PySCF, and xtb, covering tasks from ground- and excited-state calculations to geometry optimization, thermochemistry, and spectra simulations. By autonomously executing computational workflows, Aitomia can deliver infrared spectra in seconds and reaction thermochemistry in minutes, with results close to experiment or high-level theoretical references while greatly reducing the manual effort required from users. Aitomia lowers the barrier to performing atomistic simulations, thereby democratizing simulations and accelerating research and development in the relevant fields.
- 22 June 2026
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 22 (13) , 6557-6571
Aitomia: An Agentic Framework for AI-Driven Atomistic and Quantum Chemical Simulations
We present Aitomia, an agentic framework for AI-driven atomistic and quantum chemical (QC) simulations that helps experts and nonexperts alike set up and run calculations, analyze results, and summarize them in textual and graphical forms through natural language interaction. Built on the MLatom software ecosystem, Aitomia supports AI-driven atomistic simulations as well as conventional quantum-chemical calculations, including density functional theory, semiempirical methods such as GFN2-xTB, and selected high-level wave function-based methods, through interfaces to widely used programs such as Gaussian, ORCA, PySCF, and xtb, covering tasks from ground- and excited-state calculations to geometry optimization, thermochemistry, and spectra simulations. By autonomously executing computational workflows, Aitomia can deliver infrared spectra in seconds and reaction thermochemistry in minutes, with results close to experiment or high-level theoretical references while greatly reducing the manual effort required from users. Aitomia lowers the barrier to performing atomistic simulations, thereby democratizing simulations and accelerating research and development in the relevant fields.
- 20 April 2026
- Published by Elsevier in Chinese Journal of Structural Chemistry
- Vol. 45 (8)
Alkoxy chain-length engineering in heterometallic In–Sn-oxo clusters for nanolithography
- 20 April 2026
- Published by Elsevier in Chinese Journal of Structural Chemistry
- Vol. 45 (8)
Alkoxy chain-length engineering in heterometallic In–Sn-oxo clusters for nanolithography
- Open Access
- 16 March 2026
- Published by American Chemical Society (ACS) in ChemRxiv
Aitomia: Your Intelligent Assistant for AI-Driven Atomistic and Quantum Chemical Simulations
We have developed Aitomia – a platform powered by AI to assist in performing AI-driven atomistic and quantum chemical (QC) simulations. This evolving intelligent assistant platform is equipped with chatbots and AI agents to help experts and guide non-experts in setting up and running atomistic simulations, analyzing simulation results, and summarizing them for the user in both textual and graphical forms. Aitomia combines LLM-based agents with the MLatom platform to support AI-driven atomistic simulations as well as conventional quantum-chemical calculations, including DFT, semiempirical methods such as GFN2-xTB, and selected high-level wavefunction-based methods, through interfaces to widely used programs such as Gaussian, ORCA, PySCF, and xtb, covering tasks from ground-state and excited-state calculations to geometry optimization, thermochemistry, and spectra simulations. The multi-agent implementation enables autonomous execution of complex computational workflows, such as reaction enthalpy calculations. Aitomia was the first intelligent assistant publicly launched on cloud computing platforms for broad-scope atomistic simulations (Aitomistic Lab@XMU at https://atom.xmu.edu.cn and Aitomistic Hub at https://aitomistic.xyz ). Aitomia lowers the barrier to performing atomistic simulations, thereby democratizing simulations and accelerating research and development in relevant fields.
- 16 March 2026
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessAitomia: Your Intelligent Assistant for AI-Driven Atomistic and Quantum Chemical Simulations
We have developed Aitomia – a platform powered by AI to assist in performing AI-driven atomistic and quantum chemical (QC) simulations. This evolving intelligent assistant platform is equipped with chatbots and AI agents to help experts and guide non-experts in setting up and running atomistic simulations, analyzing simulation results, and summarizing them for the user in both textual and graphical forms. Aitomia combines LLM-based agents with the MLatom platform to support AI-driven atomistic simulations as well as conventional quantum-chemical calculations, including DFT, semiempirical methods such as GFN2-xTB, and selected high-level wavefunction-based methods, through interfaces to widely used programs such as Gaussian, ORCA, PySCF, and xtb, covering tasks from ground-state and excited-state calculations to geometry optimization, thermochemistry, and spectra simulations. The multi-agent implementation enables autonomous execution of complex computational workflows, such as reaction enthalpy calculations. Aitomia was the first intelligent assistant publicly launched on cloud computing platforms for broad-scope atomistic simulations (Aitomistic Lab@XMU at https://atom.xmu.edu.cn and Aitomistic Hub at https://aitomistic.xyz ). Aitomia lowers the barrier to performing atomistic simulations, thereby democratizing simulations and accelerating research and development in relevant fields.
- 14 February 2026
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 22 (5) , 2232-2242
AIQM3: Targeting Coupled-Cluster Accuracy with Semi-Empirical Speed across Seven Main-Group Elements
The AIQM series of methods are successful neural network-based models that target coupled-cluster accuracy while maintaining high robustness and transferability across various tasks by leveraging Δ-learning. However, the previous AIQM1 and AIQM2 models are limited to molecular systems with four elements: H, C, N, and O, which fall short of meeting the common needs for atomistic simulations. Here, we introduce the extension─AIQM3─that covers three additional chemical elements: S, F, and Cl, and approaches coupled-cluster level at the speed of a semiempirical method. AIQM3 maintains the accuracy of its predecessor AIQM2, surpasses the commonly used density functional theory (DFT) method in different types of molecular interactions, and its efficiency is competitive with that of machine learning interatomic potentials on commodity CPU hardware. AIQM3's superiority is showcased for reaction simulations and tasks related to drug design, where it delivers accurate torsion profiles for various real-world drug-like molecules. Remarkably, without training on radicals and charged species, AIQM3 can deliver near-DFT accuracy on the binding energy of ion pairs and the radical stabilization energies. In addition, AIQM3 can be used for infrared (IR) spectra calculations at low cost. We provide a web service for the AIQM3 calculations on the Aitomistic Hub at aitomistic.xyz and Aitomistic Lab@XMU (https://atom.xmu.edu.cn, free for academic users), to democratize and facilitate its use with the assistance of AI agents.
- 14 February 2026
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 22 (5) , 2232-2242
AIQM3: Targeting Coupled-Cluster Accuracy with Semi-Empirical Speed across Seven Main-Group Elements
The AIQM series of methods are successful neural network-based models that target coupled-cluster accuracy while maintaining high robustness and transferability across various tasks by leveraging Δ-learning. However, the previous AIQM1 and AIQM2 models are limited to molecular systems with four elements: H, C, N, and O, which fall short of meeting the common needs for atomistic simulations. Here, we introduce the extension─AIQM3─that covers three additional chemical elements: S, F, and Cl, and approaches coupled-cluster level at the speed of a semiempirical method. AIQM3 maintains the accuracy of its predecessor AIQM2, surpasses the commonly used density functional theory (DFT) method in different types of molecular interactions, and its efficiency is competitive with that of machine learning interatomic potentials on commodity CPU hardware. AIQM3's superiority is showcased for reaction simulations and tasks related to drug design, where it delivers accurate torsion profiles for various real-world drug-like molecules. Remarkably, without training on radicals and charged species, AIQM3 can deliver near-DFT accuracy on the binding energy of ion pairs and the radical stabilization energies. In addition, AIQM3 can be used for infrared (IR) spectra calculations at low cost. We provide a web service for the AIQM3 calculations on the Aitomistic Hub at aitomistic.xyz and Aitomistic Lab@XMU (https://atom.xmu.edu.cn, free for academic users), to democratize and facilitate its use with the assistance of AI agents.
- 3 November 2025
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry Letters
- Vol. 16 (45) , 11732-11744
A Descriptor Is All You Need: Accurate Machine Learning of Nonadiabatic Coupling Vectors
Nonadiabatic couplings (NACs) play a crucial role in modeling photochemical and photophysical processes with methods such as the widely used fewest-switches surface hopping (FSSH). There is, therefore, a strong incentive to machine learn NACs for accelerating simulations. However, this is challenging due to NACs' vectorial, double-valued character and the singularity near a conical intersection seam. For the first time, we design NAC-specific descriptors based on our domain expertise and show that they allow learning NACs with never-before-reported accuracy of R2 exceeding 0.99. The key to success is also our new ML phase-correction procedure. We demonstrate the efficiency and robustness of our approach on a prototypical example of fully ML-driven FSSH simulations of fulvene targeting the SA-2-CASSCF(6,6) electronic structure level. This ML-FSSH dynamics leads to an accurate description of S1 decay while reducing error bars by allowing the execution of a large ensemble of trajectories. Our approach is generalizable to more states as we demonstrate for a three-state ML-FSSH simulation of methylenimmonium cation. Our implementations are available in open-source MLatom.
- 3 November 2025
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry Letters
- Vol. 16 (45) , 11732-11744
A Descriptor Is All You Need: Accurate Machine Learning of Nonadiabatic Coupling Vectors
Nonadiabatic couplings (NACs) play a crucial role in modeling photochemical and photophysical processes with methods such as the widely used fewest-switches surface hopping (FSSH). There is, therefore, a strong incentive to machine learn NACs for accelerating simulations. However, this is challenging due to NACs' vectorial, double-valued character and the singularity near a conical intersection seam. For the first time, we design NAC-specific descriptors based on our domain expertise and show that they allow learning NACs with never-before-reported accuracy of R2 exceeding 0.99. The key to success is also our new ML phase-correction procedure. We demonstrate the efficiency and robustness of our approach on a prototypical example of fully ML-driven FSSH simulations of fulvene targeting the SA-2-CASSCF(6,6) electronic structure level. This ML-FSSH dynamics leads to an accurate description of S1 decay while reducing error bars by allowing the execution of a large ensemble of trajectories. Our approach is generalizable to more states as we demonstrate for a three-state ML-FSSH simulation of methylenimmonium cation. Our implementations are available in open-source MLatom.
- Open Access
- 29 October 2025
- Published by American Chemical Society (ACS) in ChemRxiv
AIQM3: Targeting Coupled-Cluster Accuracy with Semi-Empirical Speed Across Seven Main Group Elements
The AIQM series methods are successful neural network-based models that target coupled-cluster accuracy while maintaining high robustness and transferability across various tasks by leveraging Δ-learning. However, the previous AIQM1 and AIQM2 models are limited to molecular systems with four elements: H, C, N, and O, which falls short of meeting the common needs for atomistic simulations. Here, we introduce the extension—AIQM3—that covers three additional chemical elements: S, F, Cl, and approaches coupled cluster level at the speed of a semi-empirical method. AIQM3 maintains the accuracy of its predecessor AIQM2, surpasses the commonly used density functional theory (DFT) method in different types of molecular interactions, and its efficiency is competitive with that of machine learning interatomic potentials on commodity CPU hardware. AIQM3 superiority is showcased for reaction simulations and tasks related to drug design, where it delivers accurate torsion profiles for various real-world drug-like molecules. In addition, AIQM3 can be used for infrared (IR) spectra calculations at a low cost. We provide a web service for the AIQM3 calculations on the Aitomistic Hub at aitomistic.xyz, to democratize and facilitate its use with the assistance of AI agents.
- 29 October 2025
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessAIQM3: Targeting Coupled-Cluster Accuracy with Semi-Empirical Speed Across Seven Main Group Elements
The AIQM series methods are successful neural network-based models that target coupled-cluster accuracy while maintaining high robustness and transferability across various tasks by leveraging Δ-learning. However, the previous AIQM1 and AIQM2 models are limited to molecular systems with four elements: H, C, N, and O, which falls short of meeting the common needs for atomistic simulations. Here, we introduce the extension—AIQM3—that covers three additional chemical elements: S, F, Cl, and approaches coupled cluster level at the speed of a semi-empirical method. AIQM3 maintains the accuracy of its predecessor AIQM2, surpasses the commonly used density functional theory (DFT) method in different types of molecular interactions, and its efficiency is competitive with that of machine learning interatomic potentials on commodity CPU hardware. AIQM3 superiority is showcased for reaction simulations and tasks related to drug design, where it delivers accurate torsion profiles for various real-world drug-like molecules. In addition, AIQM3 can be used for infrared (IR) spectra calculations at a low cost. We provide a web service for the AIQM3 calculations on the Aitomistic Hub at aitomistic.xyz, to democratize and facilitate its use with the assistance of AI agents.
- Open Access
- 14 July 2025
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 6 (3) , 035004
Active delta-learning for fast construction of interatomic potentials and stable molecular dynamics simulations
Active learning (AL) requires massive time for comprehensive sampling of complex potential energy surfaces to achieve desirable accuracy and stability of machine learning (ML) potentials. Here, we develop an active delta-learning (ADL) protocol for speeding up AL and building delta-learning models yielding stable simulations. ADL converges after a few iterations and needs tenfold fewer sampled points than without delta-learning while leading to models of similar accuracy, as we show on the test simulations of Diels–Alder reactions. The test reactions include one small (ethene + 1,3-butadiene) and one relatively big (C60 + 2,3-dimethyl-1,3-butadiene) system, treated with a target density functional theory level (U)B3LYP(-D4)/6-31G* and a baseline semi-empirical quantum mechanical method, GFN2-xTB. The crucial advantage of the models built with the delta-learning protocol is their remarkable simulation stability: even models from the initial ADL iterations yield reasonable results. In contrast, the pure ML potentials built without delta-learning often lead to the collapse in simulations, i.e. to unphysical structures.
- 14 July 2025
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 6 (3) , 035004
Open AccessActive delta-learning for fast construction of interatomic potentials and stable molecular dynamics simulations
Active learning (AL) requires massive time for comprehensive sampling of complex potential energy surfaces to achieve desirable accuracy and stability of machine learning (ML) potentials. Here, we develop an active delta-learning (ADL) protocol for speeding up AL and building delta-learning models yielding stable simulations. ADL converges after a few iterations and needs tenfold fewer sampled points than without delta-learning while leading to models of similar accuracy, as we show on the test simulations of Diels–Alder reactions. The test reactions include one small (ethene + 1,3-butadiene) and one relatively big (C60 + 2,3-dimethyl-1,3-butadiene) system, treated with a target density functional theory level (U)B3LYP(-D4)/6-31G* and a baseline semi-empirical quantum mechanical method, GFN2-xTB. The crucial advantage of the models built with the delta-learning protocol is their remarkable simulation stability: even models from the initial ADL iterations yield reasonable results. In contrast, the pure ML potentials built without delta-learning often lead to the collapse in simulations, i.e. to unphysical structures.
- Open Access
- 29 May 2025
- Published by American Chemical Society (ACS) in ChemRxiv
A Descriptor Is All You Need: Accurate Machine Learning of Nonadiabatic Coupling Vectors
Nonadiabatic couplings (NACs) play a crucial role in modeling photochemical and photophysical processes with methods such as the widely used fewest-switches surface hopping (FSSH). There is therefore a strong incentive to machine learn NACs for accelerating simulations. However, this is challenging due to NACs’ vectorial, double-valued character and the singularity near a conical intersection seam. For the first time, we design NAC-specific descriptors based on our domain expertise and show that they allow learning NACs with never-before-reported accuracy of R2 exceeding 0.99. The key to success is also our new ML phase-correction procedure. We demonstrate the efficiency and robustness of our approach on a prototypical example of fully ML-driven FSSH simulations of fulvene targeting the SA-2-CASSCF(6,6) electronic structure level. This ML-FSSH dynamics leads to an accurate description of S1 decay while reducing error bars by allowing the execution of a large ensemble of trajectories. Our implementations are available in open-source MLatom.
- 29 May 2025
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessA Descriptor Is All You Need: Accurate Machine Learning of Nonadiabatic Coupling Vectors
Nonadiabatic couplings (NACs) play a crucial role in modeling photochemical and photophysical processes with methods such as the widely used fewest-switches surface hopping (FSSH). There is therefore a strong incentive to machine learn NACs for accelerating simulations. However, this is challenging due to NACs’ vectorial, double-valued character and the singularity near a conical intersection seam. For the first time, we design NAC-specific descriptors based on our domain expertise and show that they allow learning NACs with never-before-reported accuracy of R2 exceeding 0.99. The key to success is also our new ML phase-correction procedure. We demonstrate the efficiency and robustness of our approach on a prototypical example of fully ML-driven FSSH simulations of fulvene targeting the SA-2-CASSCF(6,6) electronic structure level. This ML-FSSH dynamics leads to an accurate description of S1 decay while reducing error bars by allowing the execution of a large ensemble of trajectories. Our implementations are available in open-source MLatom.
- 14 April 2025
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry A
- Vol. 129 (16) , 3613-3623
Accurate and Affordable Simulation of Molecular Infrared Spectra with AIQM Models
Infrared (IR) spectroscopy is a potent tool for identifying molecular structures and studying the chemical properties of compounds, and hence, various theoretical approaches have been developed to simulate and predict the IR spectra. However, the theoretical approaches based on quantum chemical calculations suffer from high computational cost (e.g., density functional theory, DFT) or insufficient accuracy (e.g., semiempirical methods orders of magnitude faster than DFT). Here, we introduce a new approach, based on the universal machine learning (ML) models of the AIQM series targeting CCSD(T)/CBS level, that can deliver molecular IR spectra with accuracy close to DFT (compared to the experiment) and the speed close to a semiempirical GFN2-xTB method. This approach is based on the harmonic oscillator approximation with the frequency scaling factors fitted to experimental data. While the benchmarks reported here are focused on harmonic IR spectra, our implementation supports anharmonic spectra simulations via molecular dynamics and VPT2. These implementations are available in MLatom as described in https://github.com/dralgroup/mlatom and can be performed online via a web browser.
- 14 April 2025
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry A
- Vol. 129 (16) , 3613-3623
Accurate and Affordable Simulation of Molecular Infrared Spectra with AIQM Models
Infrared (IR) spectroscopy is a potent tool for identifying molecular structures and studying the chemical properties of compounds, and hence, various theoretical approaches have been developed to simulate and predict the IR spectra. However, the theoretical approaches based on quantum chemical calculations suffer from high computational cost (e.g., density functional theory, DFT) or insufficient accuracy (e.g., semiempirical methods orders of magnitude faster than DFT). Here, we introduce a new approach, based on the universal machine learning (ML) models of the AIQM series targeting CCSD(T)/CBS level, that can deliver molecular IR spectra with accuracy close to DFT (compared to the experiment) and the speed close to a semiempirical GFN2-xTB method. This approach is based on the harmonic oscillator approximation with the frequency scaling factors fitted to experimental data. While the benchmarks reported here are focused on harmonic IR spectra, our implementation supports anharmonic spectra simulations via molecular dynamics and VPT2. These implementations are available in MLatom as described in https://github.com/dralgroup/mlatom and can be performed online via a web browser.
- Open Access
- 11 April 2025
- Published by American Chemical Society (ACS) in ChemRxiv
Accurate and Affordable Simulation of Molecular Infrared Spectra with AIQM Models
Infrared (IR) spectroscopy is a potent tool for identifying molecular structures and studying the chemical properties of compounds, and hence, various theoretical approaches have been developed to simulate and predict the IR spectra. However, the theoretical approaches based on quantum chemical calculations suffer from high computational cost (e.g., density functional theory, DFT) or insufficient accuracy (e.g., semi-empirical methods orders of magnitude faster than DFT). Here, we introduce a new approach, based on the universal machine learning (ML) models of the AIQM series targeting CCSD(T)/CBS level, that can deliver molecular IR spectra with accuracy close to DFT (compared to the experiment) and the speed close to a semi-empirical GFN2-xTB method. This approach is based on the harmonic oscillator approximation with the frequency scaling factors fitted to experimental data. While the benchmarks reported here are focused on harmonic IR spectra, our implementation supports anharmonic spectra simulations via molecular dynamics and VPT2. These implementations are available in MLatom as described in https://github.com/dralgroup/mlatom and can be performed online via a web browser.
- 11 April 2025
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessAccurate and Affordable Simulation of Molecular Infrared Spectra with AIQM Models
Infrared (IR) spectroscopy is a potent tool for identifying molecular structures and studying the chemical properties of compounds, and hence, various theoretical approaches have been developed to simulate and predict the IR spectra. However, the theoretical approaches based on quantum chemical calculations suffer from high computational cost (e.g., density functional theory, DFT) or insufficient accuracy (e.g., semi-empirical methods orders of magnitude faster than DFT). Here, we introduce a new approach, based on the universal machine learning (ML) models of the AIQM series targeting CCSD(T)/CBS level, that can deliver molecular IR spectra with accuracy close to DFT (compared to the experiment) and the speed close to a semi-empirical GFN2-xTB method. This approach is based on the harmonic oscillator approximation with the frequency scaling factors fitted to experimental data. While the benchmarks reported here are focused on harmonic IR spectra, our implementation supports anharmonic spectra simulations via molecular dynamics and VPT2. These implementations are available in MLatom as described in https://github.com/dralgroup/mlatom and can be performed online via a web browser.