pith. sign in

arxiv: 2604.11827 · v1 · submitted 2026-04-11 · ⚛️ physics.chem-ph · cond-mat.mtrl-sci· cs.LG

Inverse Design of Inorganic Compounds with Generative AI

Hannes Kneiding , Luc\'ia Mor\'an-Gonz\'alez , Nishamol Kuriakose , Ainara Nova , David Balcells This is my paper

Pith reviewed 2026-05-10 15:30 UTC · model grok-4.3

classification ⚛️ physics.chem-ph cond-mat.mtrl-scics.LG
keywords generative AIinverse designinorganic compoundsmachine learningtransition metal complexescrystal structuressynthesizability metrics
0
0 comments X

The pith

Generative AI pipelines address the full complexity of inorganic compounds to enable inverse design.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper reviews the progress of generative AI in enabling inverse design of inorganic compounds, shifting from predicting properties of known structures to generating structures with desired properties. It covers a range of systems from molecules to crystals and examines how methods have developed data-representation-model pipelines to manage composition, geometry, symmetry, and electronic structure. Readers should care because this approach could transform how new inorganic materials and complexes are discovered in chemistry. The review also outlines future needs like standard benchmarks and synthesizability metrics to advance practical applications.

Core claim

The paper establishes that generative AI methods have evolved towards data-representation-model pipelines that address the full complexity of inorganic compounds, including their chemical composition, geometry, symmetry, and electronic structure, for systems ranging from molecules to crystals including transition metal complexes and microporous materials.

What carries the argument

Data-representation-model pipelines, which integrate representations of chemical composition, geometry, symmetry, and electronic structure to generate inorganic compounds with specified properties.

If this is right

  • Inverse design is now feasible for diverse inorganic systems including transition metal complexes and microporous materials.
  • Benchmark standardization will help evaluate and compare generative methods across studies.
  • Synthesizability metrics are essential for translating AI-generated compounds into experimentally viable targets.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • These pipelines may be extended to incorporate more detailed quantum mechanical properties during generation.
  • Success in inorganic applications could inspire similar comprehensive approaches in related fields like organic materials design.
  • Generated structures could be validated against existing chemical databases to assess novelty and feasibility.

Load-bearing premise

That the reviewed methods and literature capture the current capabilities sufficiently and that incremental evolution of pipelines will overcome inorganic challenges without requiring fundamental new ideas.

What would settle it

A study that identifies inorganic compounds with symmetry or electronic features that no current generative AI pipeline can accurately model or generate would challenge the central claim of sufficient progress.

Figures

Figures reproduced from arXiv: 2604.11827 by Ainara Nova, David Balcells, Hannes Kneiding, Luc\'ia Mor\'an-Gonz\'alez, Nishamol Kuriakose.

Figure 1
Figure 1. Figure 1: Inorganic compounds covered in this Review. a) Transition metal complexes are built around a metal center supported by a set of ligands. b) Non-porous inorganic crystals form a compact, periodic structure made of metals or ions. c) Microporous inorganic materials have porous reticular structures made with metal node-linker (MOFs) or aluminosilicate (zeolites) building blocks. In MOFs, the metal node can al… view at source ↗
Figure 2
Figure 2. Figure 2: Timeline of selected generative AI methods, including genetic algorithms (GAs), generative adversarial networks (GANs), variational autoencoders (VAEs), diffusion models (DMs), and large language models (LLMs), for inorganic compounds, including transition metal complexes (TMCs), non-porous crystals, metal organic frameworks (MOFs), and zeolites. 9/42 [PITH_FULL_IMAGE:figures/full_fig_p009_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Selected generative AI methods for TMCs. a) GA using genetic operations, fitness optimization, and selection in Pareto front problems; b) The PL-MOGA GA for directional multi-objective optimization over selected regions of the Pareto front; c) VAE encoding and decoding metal ligands through a compressed latent space representation; d) The CatDRX VAE encoding both TMCs and reaction conditions for the invers… view at source ↗
Figure 4
Figure 4. Figure 4: Diffusion models for non-porous inorganic crystals. a) Noising using of crystal structure representation with Gaussian noise and learned denoising with E(3)-equivariant graph neural networks; b) The MatterGen diffusion model doing unconditional generation with nearly DFT quality and conditional generation on multiple properties, using SUN metrics for evaluation and experiments for verification. The competi… view at source ↗
Figure 5
Figure 5. Figure 5: LLM models for MOFs. a) Whereas the classical approach encodes the materials information with tokens, quantum natural language processing (QNLP) uses a qubit representation. b) The generative process leverages a four-category classification task (low, moderate low, moderate high, and high) over two target properties (pore volume and CO2 Henry’s constant). 22/42 [PITH_FULL_IMAGE:figures/full_fig_p022_5.png] view at source ↗
read the original abstract

Machine learning is revolutionizing chemistry. Beyond the value of predictive models accelerating virtual screening, generative AI aims at enabling inverse design, reversing the compound-to-property prediction paradigm into property-to-compound generation. Chemists now have access to a rich AI toolbox for organic chemistry, including drug discovery. However, the application of these methods to inorganic compounds remains limited by the challenges posed by their intrinsic nature. This Review analyzes how these challenges have been addressed, considering widely diverse systems ranging from molecules to crystals, including transition metal complexes and microporous materials. The analysis focuses on how generative AI methods have evolved towards data-representation-model pipelines that address the full complexity of inorganic compounds, including their chemical composition, geometry, symmetry, and electronic structure. Future directions, like benchmark standardization and the development of synthesizability metrics, are also discussed.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 3 minor

Summary. The manuscript is a review surveying the application of generative AI to inverse design of inorganic compounds. It covers diverse systems including molecules, crystals, transition metal complexes, and microporous materials. The central descriptive claim is that generative methods have evolved from basic models into integrated data-representation-model pipelines that jointly address the full complexity of inorganic systems: chemical composition, geometry, symmetry, and electronic structure. The review discusses challenges specific to inorganics versus organics, reviews existing approaches, and outlines future directions such as benchmark standardization and synthesizability metrics.

Significance. If the literature survey is comprehensive and balanced, the review would provide a useful synthesis for researchers working at the intersection of AI and inorganic chemistry/materials science. It explicitly credits the shift toward holistic pipelines that tackle multiple structural and electronic aspects simultaneously, which is a key strength given the greater intrinsic challenges of inorganic systems (e.g., variable oxidation states, long-range order). The forward-looking sections on benchmarks and synthesizability metrics are particularly valuable as they identify actionable gaps that could accelerate reproducible progress in the field.

major comments (2)
  1. [Method evolution discussion (near abstract claim)] The central claim that methods have evolved toward pipelines addressing composition, geometry, symmetry, and electronic structure simultaneously is load-bearing for the review's thesis. However, the manuscript would be strengthened by adding an explicit timeline or comparative table (e.g., in the section discussing method evolution) that maps specific cited works to the four complexity axes, rather than relying solely on narrative description; without this, the 'evolution' narrative risks appearing qualitative rather than evidence-based.
  2. [Literature selection and crystal systems section] The weakest assumption noted in the review—that the selected literature sufficiently represents the state of the field—requires more justification. In the coverage of crystal generation, for example, the manuscript should explicitly state the search strategy or inclusion criteria used to select papers, to allow readers to assess potential omissions of counterexamples or alternative architectures.
minor comments (3)
  1. [Throughout, especially data-representation subsections] Notation for data representations (e.g., graph vs. voxel vs. string encodings) is introduced inconsistently across sections; a dedicated glossary or consistent abbreviation table would improve clarity.
  2. [Figures in the pipeline evolution sections] Several figures illustrating pipeline architectures would benefit from explicit labels indicating which complexity axes (composition/geometry/symmetry/electronic structure) each component addresses.
  3. [Future directions] The future-directions paragraph on synthesizability metrics cites the need for new metrics but does not reference any existing proxy metrics from the inorganic literature (e.g., those used in crystal structure prediction); adding 2–3 concrete citations would make the recommendation more actionable.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the positive assessment of our review and the recommendation for minor revision. The comments provide valuable guidance on strengthening the evidence base for our central thesis and improving transparency in literature selection. We address each point below and will incorporate the suggested revisions.

read point-by-point responses

  1. Referee: [Method evolution discussion (near abstract claim)] The central claim that methods have evolved toward pipelines addressing composition, geometry, symmetry, and electronic structure simultaneously is load-bearing for the review's thesis. However, the manuscript would be strengthened by adding an explicit timeline or comparative table (e.g., in the section discussing method evolution) that maps specific cited works to the four complexity axes, rather than relying solely on narrative description; without this, the 'evolution' narrative risks appearing qualitative rather than evidence-based.

    Authors: We agree that an explicit mapping would render the evolution narrative more rigorous and evidence-based. In the revised manuscript, we will insert a comparative table in the method evolution section. The table will list representative cited works chronologically and indicate (via checkmarks or similar) which of the four complexity axes—chemical composition, geometry, symmetry, and electronic structure—each work addresses. This addition will directly support the central claim without altering the narrative flow. revision: yes

  2. Referee: [Literature selection and crystal systems section] The weakest assumption noted in the review—that the selected literature sufficiently represents the state of the field—requires more justification. In the coverage of crystal generation, for example, the manuscript should explicitly state the search strategy or inclusion criteria used to select papers, to allow readers to assess potential omissions of counterexamples or alternative architectures.

    Authors: We acknowledge that explicit documentation of the literature selection process is necessary for a balanced review. In the revised version, we will add a short dedicated paragraph (likely at the start of the crystal generation subsection or in a methods-oriented note) that details the search strategy. This will include the databases and repositories queried, the primary keywords and Boolean combinations employed, the time window covered, and the inclusion/exclusion criteria applied (e.g., focus on generative models for periodic crystals, exclusion of purely predictive rather than generative studies). Such transparency will enable readers to evaluate coverage and potential gaps. revision: yes

Circularity Check

0 steps flagged

No circularity: review paper with no derivations or predictions

full rationale

This is a survey paper that reviews existing literature on generative AI for inverse design of inorganic compounds. It makes no new mathematical claims, derivations, fitted predictions, or empirical results. The central narrative is descriptive, summarizing how data-representation-model pipelines have evolved to address composition, geometry, symmetry, and electronic structure across cited works. No load-bearing steps reduce to self-definition, self-citation chains, or renamed inputs; the argument rests entirely on the existence and behavior of the externally cited literature.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

As a review paper, the central claim rests on the assumption that the selected literature accurately reflects the field's progress; no free parameters, new axioms, or invented entities are introduced by the authors.

pith-pipeline@v0.9.0 · 5460 in / 1027 out tokens · 74803 ms · 2026-05-10T15:30:36.417908+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

260 extracted references · 260 canonical work pages · 2 internal anchors

  1. [1]

    Beitrag zur konstitution anorganischer verbindungen.Zeitschrift für anorganische Chemie3, 267–330 (1893)

    Werner, A. Beitrag zur konstitution anorganischer verbindungen.Zeitschrift für anorganische Chemie3, 267–330 (1893)

    work page

  2. [2]

    Knowles, W. S. & Sabacky, M. J. Catalytic asymmetric hydrogenation employing a soluble, optically active, rhodium complex.Chem. Commun. (London)1445–1446 (1968)

    work page 1968

  3. [3]

    Miyashita, A.et al.Synthesis of 2,2’-bis(diphenylphosphino)-1,1’-binaphthyl (binap), an atropisomeric chiral bis(triaryl)phosphine, and its use in the rhodium(i)-catalyzed asymmetric hydrogenation ofα-(acylamino)acrylic acids.J. Am. Chem. Soc.102, 7932–7934 (1980)

    work page 1980

  4. [4]

    & Suzuki, A

    Miyaura, N., Yamada, K. & Suzuki, A. A new stereospecific cross-coupling by the palladium- catalyzed reaction of 1-alkenylboranes with 1-alkenyl or 1-alkynyl halides.Tetrahedron Lett. 20, 3437–3440 (1979)

    work page 1979

  5. [5]

    Negishi, E., King, A. O. & Okukado, N. Selective carbon-carbon bond formation via transition metal catalysis. 3. a highly selective synthesis of unsymmetrical biaryls and diarylmethanes by the nickel- or palladium-catalyzed reaction of aryl- and benzylzinc derivatives with aryl halides.J. Org. Chem.42, 1821–1823 (1977)

    work page 1977

  6. [6]

    Heck, R. F. & Nolley Jr, J. Palladium-catalyzed vinylic hydrogen substitution reactions with aryl, benzyl, and styryl halides.J. Org. Chem.37, 2320–2322 (1972)

    work page 1972

  7. [7]

    H.et al.Transition-metal-catalyzed c–h bond activation for the formation of c–c bonds in complex molecules.Chem

    Docherty, J. H.et al.Transition-metal-catalyzed c–h bond activation for the formation of c–c bonds in complex molecules.Chem. Rev.123, 7692–7760 (2023)

    work page 2023

  8. [8]

    M., Joe, C

    Ganley, J. M., Joe, C. L. & Simmons, E. M. Development of robust, efficient and scalable transition metal catalyzed transformations: Translation of reactions from micromole to multi-kilogram scale processes.ACS Catal.15, 8317–8336 (2025)

    work page 2025

  9. [9]

    Rosenberg, B., VanCamp, L., Trosko, J. E. & Mansour, V. H. Platinum compounds: a new class of potent antitumour agents.Nature222, 385–386 (1969)

    work page 1969

  10. [10]

    & Costas, M

    Milan, M., Bietti, M. & Costas, M. Enantioselective aliphatic c–h bond oxidation catalyzed by bioinspired complexes.Chem. Commun.54, 9559–9570 (2018)

    work page 2018

  11. [11]

    F.et al.Coupling dinitrogen and hydrocarbons through aryl migration.Nature 584, 221–226 (2020)

    McWilliams, S. F.et al.Coupling dinitrogen and hydrocarbons through aryl migration.Nature 584, 221–226 (2020)

    work page 2020

  12. [12]

    & Beller, M

    Liang, H.-Q., Beweries, T., Francke, R. & Beller, M. Molecular catalysts for the reductive homocoupling of co2 towards c2+ compounds.Angew. Chem. Int. Ed.61, e202200723 (2022)

    work page 2022

  13. [13]

    & de Bruin, B

    Goswami, M., Chirila, A., Rebreyend, C. & de Bruin, B. Epr spectroscopy as a tool in homogeneous catalysis research.Top. Catal.58, 719–750 (2015)

    work page 2015

  14. [14]

    R., Bursch, M., Grimme, S

    Maurer, L. R., Bursch, M., Grimme, S. & Hansen, A. Assessing density functional theory for chemically relevant open-shell transition metal reactions.J. Chem. Theory Comput.17, 6134–6151 (2021)

    work page 2021

  15. [15]

    K., Rankic, D

    Prier, C. K., Rankic, D. A. & MacMillan, D. W. C. Visible light photoredox catalysis with transition metal complexes: Applications in organic synthesis.Chem. Rev.113, 5322–5363 (2013). 16.Zuo, Z.et al.Merging photoredox with nickel catalysis: Coupling ofα-carboxyl sp 3-carbons with aryl halides.Science345, 437–440 (2014). 27/42

    work page 2013

  16. [16]

    Y.et al.Metallaphotoredox: The merger of photoredox and transition metal catalysis.Chem

    Chan, A. Y.et al.Metallaphotoredox: The merger of photoredox and transition metal catalysis.Chem. Rev.122, 1485–1542 (2022)

    work page 2022

  17. [17]

    J., Pérez-Jiménez, M

    Navarro, M., Moreno, J. J., Pérez-Jiménez, M. & Campos, J. Small molecule activation with bimetallic systems: a landscape of cooperative reactivity.Chem. Commun.58, 11220–11235 (2022)

    work page 2022

  18. [18]

    D.et al.Computational approach to molecular catalysis by 3d transition metals: Challenges and opportunities.Chem

    Vogiatzis, K. D.et al.Computational approach to molecular catalysis by 3d transition metals: Challenges and opportunities.Chem. Rev.119, 2453–2523 (2019)

    work page 2019

  19. [19]

    Wheelhouse, K. M. P., Webster, R. L. & Beutner, G. L. Advances and applications in catalysis with earth-abundant metals.Org. Process Res. Dev.27, 1157–1159 (2023)

    work page 2023

  20. [20]

    K.et al.Recent advances in metallodrug: Coordination-induced synergy between clinically approved drugs and metal ions.Mater

    Kim, W. K.et al.Recent advances in metallodrug: Coordination-induced synergy between clinically approved drugs and metal ions.Mater. Today Adv.25, 100569 (2025)

    work page 2025

  21. [21]

    & Gagliardi, L

    Sauza-de la Vega, A., Darù, A., Nofz, S. & Gagliardi, L. Designing molecular qubits: computational insights into first-row and group 6 transition metal complexes.Chem. Sci.16, 12896–12905 (2025)

    work page 2025

  22. [22]

    M.et al.Reticular synthesis and the design of new materials.Nature423, 705–714 (2003)

    Yaghi, O. M.et al.Reticular synthesis and the design of new materials.Nature423, 705–714 (2003)

    work page 2003

  23. [23]

    Hoskins, B. F. & Robson, R. Design and construction of a new class of scaffolding- like materials comprising infinite polymeric frameworks of 3d-linked molecular rods. a reappraisal of the zinc cyanide and cadmium cyanide structures and the synthesis and structure of the diamond-related frameworks [n(ch3)4][cuiznii(cn)4] and cui[4,4’,4”,4”’- tetracyanotet...

    work page 1990

  24. [24]

    & Seki, K

    Kondo, M., Yoshitomi, T., Matsuzaka, H., Kitagawa, S. & Seki, K. Three-dimensional framework with channeling cavities for small molecules: [M2(4, 4′-bpy)3(NO3)4]·xH2On (m = co, ni, zn).Angew. Chem. Int. Ed. Engl.36, 1725–1727 (1997)

    work page 1997

  25. [25]

    Eddaoudi, M.et al.Systematic design of pore size and functionality in isoreticular mofs and their application in methane storage.Science295, 469–472 (2002)

    work page 2002

  26. [26]

    Nature635, 96–101 (2024)

    Zhou, Z.et al.Carbon dioxide capture from open air using covalent organic frameworks. Nature635, 96–101 (2024)

    work page 2024

  27. [27]

    Lin, J.-B.et al.A scalable metal-organic framework as a durable physisorbent for carbon dioxide capture.Science374, 1464–1469 (2021)

    work page 2021

  28. [28]

    C., Aksu, G

    Daglar, H., Gulbalkan, H. C., Aksu, G. O. & Keskin, S. Computational simulations of metal–organic frameworks to enhance adsorption applications.Adv. Mater.37, 2405532 (2024). 30.Fathieh, F.et al.Practical water production from desert air.Sci. Adv.4, eaat3198 (2018)

    work page 2024

  29. [29]

    E., O’Keeffe, M

    Furukawa, H., Cordova, K. E., O’Keeffe, M. & Yaghi, O. M. The chemistry and applications of metal-organic frameworks.Science341, 1230444 (2013)

    work page 2013

  30. [30]

    Alezi, D.et al.Mof crystal chemistry paving the way to gas storage needs: Aluminum-based soc-mof for ch4, o2, and co2 storage.J. Am. Chem. Soc.137, 13308–13318 (2015)

    work page 2015

  31. [31]

    O., Idrees, K

    Chen, Z., Kirlikovali, K. O., Idrees, K. B., Wasson, M. C. & Farha, O. K. Porous materials for hydrogen storage.Chem8, 693–716 (2022). 28/42

    work page 2022

  32. [32]

    Chen, Z.et al.Balancing volumetric and gravimetric uptake in highly porous materials for clean energy.Science368, 297–303 (2020)

    work page 2020

  33. [33]

    & Meyer, D

    Sini, K., Bourgeois, D., Idouhar, M., Carboni, M. & Meyer, D. Metal-organic frameworks cavity size effect on the extraction of organic pollutants.Mater. Lett.250, 92–95 (2019)

    work page 2019

  34. [34]

    Asgari, M.et al.The structuring of porous reticular materials for energy applications at industrial scales.Chem. Soc. Rev.54, 4701–4744 (2025)

    work page 2025

  35. [35]

    Férey, G.et al.A chromium terephthalate-based solid with unusually large pore volumes and surface area.Science309, 2040–2042 (2005)

    work page 2040

  36. [36]

    H.et al.A new zirconium inorganic building brick forming metal organic frameworks with exceptional stability.J

    Cavka, J. H.et al.A new zirconium inorganic building brick forming metal organic frameworks with exceptional stability.J. Am. Chem. Soc.130, 13850–13851 (2008)

    work page 2008

  37. [37]

    & Pang, H

    Xu, Y., Li, Q., Xue, H. & Pang, H. Metal-organic frameworks for direct electrochemical applications.Coord. Chem. Rev.376, 292–318 (2018)

    work page 2018

  38. [38]

    V.et al.Mof-derived cobalt nanoparticles catalyze a general synthesis of amines

    Jagadeesh, R. V.et al.Mof-derived cobalt nanoparticles catalyze a general synthesis of amines. Science358, 326–332 (2017)

    work page 2017

  39. [39]

    & Gates, B

    Yang, D. & Gates, B. C. Catalysis by metal organic frameworks: Perspective and suggestions for future research.ACS Catal.9, 1779–1798 (2019). 42.Barrer, R. M. 435. syntheses and reactions of mordenite.J. Chem. Soc.2158–2163 (1948)

    work page 2019

  40. [40]

    Inorganic solid acids and their use in acid-catalyzed hydrocarbon reactions.Chem

    Corma, A. Inorganic solid acids and their use in acid-catalyzed hydrocarbon reactions.Chem. Rev.95, 559–614 (1995)

    work page 1995

  41. [41]

    & Pirngruber, G

    Chizallet, C., Bouchy, C., Larmier, K. & Pirngruber, G. Molecular views on mechanisms of brønsted acid-catalyzed reactions in zeolites.Chem. Rev.123, 6107–6196 (2023)

    work page 2023

  42. [42]

    Li, Y. & Yu, J. Emerging applications of zeolites in catalysis, separation and host–guest assembly.Nat. Rev. Mater.6, 1156–1174 (2021)

    work page 2021

  43. [43]

    & Rey, F

    Pérez-Botella, E., Valencia, S. & Rey, F. Zeolites in adsorption processes: State of the art and future prospects.Chem. Rev.122, 17647–17695 (2022)

    work page 2022

  44. [44]

    d., Martínez, C

    Campo, P. d., Martínez, C. & Corma, A. Activation and conversion of alkanes in the confined space of zeolite-type materials.Chem. Soc. Rev.50, 8511–8595 (2021)

    work page 2021

  45. [45]

    Jiao, F.et al.Disentangling the activity-selectivity trade-off in catalytic conversion of syngas to light olefins.Science380, 727–730 (2023)

    work page 2023

  46. [46]

    Matito-Martos, I.et al.Zeolite screening for the separation of gas mixtures containing SO2, CO2 and CO.Phys. Chem. Chem. Phys.16, 19884–19893 (2014)

    work page 2014

  47. [47]

    Deng, L.et al.Atom-economic synthesis of zeolites.J. Am. Chem. Soc.146, 29115–29122 (2024)

    work page 2024

  48. [48]

    F., Abdelhamid, H

    Abdel-Magied, A. F., Abdelhamid, H. N., Ashour, R. M., Zou, X. & Forsberg, K. Hierarchical porous zeolitic imidazolate frameworks nanoparticles for efficient adsorption of rare-earth elements.Micropor. Mesopor. Mat.278, 175–184 (2019)

    work page 2019

  49. [49]

    Zhang, Q., Gao, S. & Yu, J. Metal sites in zeolites: Synthesis, characterization, and catalysis. Chem. Rev.123, 6039–6106 (2023). 53.Zhao, M.et al.Low-temperature hydroformylation of ethylene by phosphorous stabilized rh sites in a one-pot synthesized rh-(o)-p-mfi zeolite.Nat. Commun.14, 7174 (2023). 29/42

    work page 2023

  50. [50]

    Nature636, 368–373 (2024)

    Lu, P.et al.A stable zeolite with atomically ordered and interconnected mesopore channel. Nature636, 368–373 (2024)

    work page 2024

  51. [51]

    V.et al.Advances in theory and their application within the field of zeolite chemistry.Chem

    Speybroeck, V. V.et al.Advances in theory and their application within the field of zeolite chemistry.Chem. Soc. Rev.44, 7044–7111 (2015)

    work page 2015

  52. [52]

    Yan, W., Li, Y., Xiao, F.-S., Liu, Z. & Yu, J. The future of zeolites.Chem. Mater.36, 7103–7105 (2024)

    work page 2024

  53. [53]

    & Yeh, J.-W

    Hsu, W.-L., Tsai, C.-W., Yeh, A.-C. & Yeh, J.-W. Clarifying the four core effects of high- entropy materials.Nat. Rev. Chem.8, 471–485 (2024)

    work page 2024

  54. [54]

    Electronic and optical properties of nanostructured MoS2 materials: influence of reduced spatial dimensions and edge effects.Phys

    Mlinar, V. Electronic and optical properties of nanostructured MoS2 materials: influence of reduced spatial dimensions and edge effects.Phys. Chem. Chem. Phys.19, 15891–15902 (2017)

    work page 2017

  55. [55]

    & Miyasaka, T

    Kojima, A., Teshima, K., Shirai, Y. & Miyasaka, T. Organometal halide perovskites as visible-light sensitizers for photovoltaic cells.J. Am. Chem. Soc.131, 6050–6051 (2009)

    work page 2009

  56. [56]

    C., Ehrler, B

    Polman, A., Knight, M., Garnett, E. C., Ehrler, B. & Sinke, W. C. Photovoltaic materials: Present efficiencies and future challenges.Science352, aad4424 (2016)

    work page 2016

  57. [57]

    Snaith, H. J. Present status and future prospects of perovskite photovoltaics.Nature Mater. 17, 372–376 (2018)

    work page 2018

  58. [58]

    & Park, N.-G

    Im, J.-H., Lee, C.-R., Lee, J.-W., Park, S.-W. & Park, N.-G. 6.5% efficient perovskite quantum-dot-sensitized solar cell.Nanoscale3, 4088–4093 (2011)

    work page 2011

  59. [59]

    Chiba, T.et al.Anion-exchange red perovskite quantum dots with ammonium iodine salts for highly efficient light-emitting devices.Nature Photon12, 681–687 (2018)

    work page 2018

  60. [60]

    Synth4, 1056–1067 (2025)

    Song, M.et al.Synthesis of single-unit-cell-thick perovskites by liquid-phase confined assembly for high-performance ultrastable x-ray detectors.Nat. Synth4, 1056–1067 (2025). 65.Hwang, J.et al.Perovskites in catalysis and electrocatalysis.Science358, 751–756 (2017)

    work page 2025

  61. [61]

    Al-Ashouri, A.et al.Monolithic perovskite/silicon tandem solar cell with >29% efficiency by enhanced hole extraction.Science370, 1300–1309 (2020)

    work page 2020

  62. [62]

    M., Teuscher, J., Miyasaka, T., Murakami, T

    Lee, M. M., Teuscher, J., Miyasaka, T., Murakami, T. N. & Snaith, H. J. Efficient hybrid solar cells based on meso-superstructured organometal halide perovskites.Science338, 643–647 (2012)

    work page 2012

  63. [63]

    I., Yang, Y

    Lee, J.-W., Tan, S., Seok, S. I., Yang, Y. & Park, N.-G. Rethinking the a cation in halide perovskites.Science375, eabj1186 (2022)

    work page 2022

  64. [64]

    Correa-Baena, J.-P.et al.Promises and challenges of perovskite solar cells.Science358, 739–744 (2017)

    work page 2017

  65. [65]

    & Park, N.-G

    Zhang, C. & Park, N.-G. Materials and methods for cost-effective fabrication of perovskite photovoltaic devices.Commun. Mater.5, 194 (2024)

    work page 2024

  66. [66]

    & Liao, L.-S

    Chen, C.-H., Cheng, S.-N., Cheng, L., Wang, Z.-K. & Liao, L.-S. Toxicity, leakage, and recycling of lead in perovskite photovoltaics.Adv. Energy Mater.13, 2204144 (2023)

    work page 2023

  67. [67]

    L., Nova, A

    Morán-González, L., Burnage, A. L., Nova, A. & Balcells, D. Ai approaches to homogeneous catalysis with transition metal complexes.ACS Catal.15, 9089–9105 (2025). 30/42

    work page 2025

  68. [68]

    Xin, H.et al.Roadmap for transforming heterogeneous catalysis with artificial intelligence. Nat. Catal.9, 102–111 (2026)

    work page 2026

  69. [69]

    Wang, C.et al.Metal-based approaches for the fight against antimicrobial resistance: Mecha- nisms, opportunities, and challenges.J. Am. Chem. Soc.147, 12361–12380 (2025)

    work page 2025

  70. [70]

    M.et al.Porous materials: The next frontier in energy technologies.Science390, eadn9391 (2025)

    Farber, E. M.et al.Porous materials: The next frontier in energy technologies.Science390, eadn9391 (2025)

    work page 2025

  71. [71]

    Yao, Y.et al.Roadmap for next-generation electrochemical energy storage technologies: Secondary batteries and supercapacitors.ACS Nano19, 30568–30687 (2025)

    work page 2025

  72. [72]

    Anstine, D. M. & Isayev, O. Generative models as an emerging paradigm in the chemical sciences.J. Am. Chem. Soc.145, 8736–8750 (2023)

    work page 2023

  73. [73]

    H., Kim, S

    Noh, J., Gu, G. H., Kim, S. & Jung, Y. Machine-enabled inverse design of inorganic solid materials: promises and challenges.Chem. Sci.11, 4871–4881 (2020)

    work page 2020

  74. [74]

    arXiv preprint arXiv:2404.07771 , year=

    Chen, M., Mei, S., Fan, J. & Wang, M. An overview of diffusion models: Applications, guided generation, statistical rates and optimization.arXivpreprint, 2404.07771 (2024)

    work page arXiv 2024

  75. [75]

    Kingma, D. P. & Welling, M. An introduction to variational autoencoders.arXivpreprint, 1906.02691 (2019). 81.Zhao, W. X.et al.A survey of large language models.arXivpreprint, 2303.18223 (2026)

    work page arXiv 1906

  76. [76]

    Gui, J., Sun, Z., Wen, Y., Tao, D. & Ye, J. A review on generative adversarial networks: Algorithms, theory, and applications.IEEE Trans. Knowl. Data Eng.35, 3313–3332 (2023). 83.Murphy, K. Reinforcement learning: An overview.arXivpreprint, 2412.05265 (2025)

    work page arXiv 2023

  77. [77]

    Chemical space: limits, evolution and modelling of an object bigger than our universal library.Digital Discovery1, 568–585 (2022)

    Restrepo, G. Chemical space: limits, evolution and modelling of an object bigger than our universal library.Digital Discovery1, 568–585 (2022). 85.Simon, D. Evolutionary optimization algorithms.First EditionBook, Wiley (2013)

    work page 2022

  78. [78]

    R., Bruno, I

    Groom, C. R., Bruno, I. J., Lightfoot, M. P. & Ward, S. C. The cambridge structural database. Acta Crystallogr. B72, 171–179 (2016)

    work page 2016

  79. [79]

    Gražulis, S.et al.Crystallography open database (cod): an open-access collection of crystal structures and platform for world-wide collaboration.Nucleic Acids Res.40, D420–D427 (2011)

    work page 2011

  80. [80]

    & Rehme, S

    Zagorac, D., Müller, H., Ruehl, S., Zagorac, J. & Rehme, S. Recent developments in the inorganic crystal structure database: theoretical crystal structure data and related features. J. Appl. Cryst.52, 918–925 (2019)

    work page 2019

Showing first 80 references.