Differential syntactic and semantic encoding in LLMs.

Alessandro Laio https://scholar.google.com/citations?user=ma-T1oEAAAAJ https://orcid.org/0000-0001-9164-7907 https://www.wikidata.org/entity/Q56979714

Santiago Acevedo Alessandro Laio Marco Baroni Differential syntactic and semantic encoding in LLMs. 2026 January abs/2601.04765 CoRR https://doi.org/10.48550/arXiv.2601.04765 db/journals/corr/corr2601.html#abs-2601-04765 streams/journals/corr

Matteo Carli Alex Rodriguez Alessandro Laio Aldo Glielmo Density estimation via binless multidimensional integration. 25052 2025 6 Mach. Learn. Sci. Technol. 2 https://doi.org/10.1088/2632-2153/add3bc db/journals/mlst/mlst6.html#CarliRLG25 streams/journals/mlst

Emily Cheng Diego Doimo Corentin Kervadec Iuri Macocco Lei Yu Alessandro Laio Marco Baroni Emergence of a High-Dimensional Abstraction Phase in Language Transformers. 2025 ICLR https://openreview.net/forum?id=0fD3iIBhlV conf/iclr/2025 db/conf/iclr/iclr2025.html#ChengDKMYLB25

Sebastian Springer Andre Scaffidi Maximilian Autenrieth Gabriella Contardo Alessandro Laio Roberto Trotta Heikki Haario Detecting Localized Density Anomalies in Multivariate Data via Coin-Flip Statistics. 2025 March abs/2503.23927 CoRR https://doi.org/10.48550/arXiv.2503.23927 db/journals/corr/corr2503.html#abs-2503-23927 streams/journals/corr

Santiago Acevedo Andrea Mascaretti Riccardo Rende Matéo Mahaut Marco Baroni Alessandro Laio An approach to identify the most semantically informative deep representations of text and images. 2025 May abs/2505.17101 CoRR https://doi.org/10.48550/arXiv.2505.17101 db/journals/corr/corr2505.html#abs-2505-17101 streams/journals/corr

Ali Hussaini Umar Franky Kevin Nando Tezoh Jean Barbier Santiago Acevedo Alessandro Laio The Effect of Label Noise on the Information Content of Neural Representations. 2025 October abs/2510.06401 CoRR https://doi.org/10.48550/arXiv.2510.06401 db/journals/corr/corr2510.html#abs-2510-06401 streams/journals/corr

Tobias Grafke Alessandro Laio Metadynamics for Transition Paths in Irreversible Dynamics. 125-141 2024 March 22 Multiscale Model. Simul. 1 https://doi.org/10.1137/23m1563025 https://www.wikidata.org/entity/Q130145177 db/journals/mmas/mmas22.html#GrafkeL24

Federica Gerace Diego Doimo Stefano Sarao Mannelli Luca Saglietti Alessandro Laio How to choose the right transfer learning protocol? A qualitative analysis in a controlled set-up. 2024 2024 Trans. Mach. Learn. Res. https://openreview.net/forum?id=XWQgXLYwv2 db/journals/tmlr/tmlr2024.html#GeraceDMSL24

Riccardo Rende Federica Gerace Alessandro Laio Sebastian Goldt A distributional simplicity bias in the learning dynamics of transformers. 2024 NeurIPS http://papers.nips.cc/paper_files/paper/2024/hash/ae6c81a39079ddeb88b034b6ef18c7fe-Abstract-Conference.html conf/nips/2024 db/conf/nips/neurips2024.html#RendeGLG24

Antonio Di Noia Iuri Macocco Aldo Glielmo Alessandro Laio Antonietta Mira Beyond the noise: intrinsic dimension estimation with optimal neighbourhood identification. 2024 abs/2405.15132 CoRR https://doi.org/10.48550/arXiv.2405.15132 db/journals/corr/corr2405.html#abs-2405-15132

Emily Cheng Diego Doimo Corentin Kervadec Iuri Macocco Jade Yu Alessandro Laio Marco Baroni Emergence of a High-Dimensional Abstraction Phase in Language Transformers. 2024 abs/2405.15471 CoRR https://doi.org/10.48550/arXiv.2405.15471 db/journals/corr/corr2405.html#abs-2405-15471

Matteo Carli Alex Rodriguez Alessandro Laio Aldo Glielmo Density Estimation via Binless Multidimensional Integration. 2024 abs/2407.08094 CoRR https://doi.org/10.48550/arXiv.2407.08094 db/journals/corr/corr2407.html#abs-2407-08094 streams/journals/corr

Riccardo Rende Federica Gerace Alessandro Laio Sebastian Goldt A distributional simplicity bias in the learning dynamics of transformers. 2024 abs/2410.19637 CoRR https://doi.org/10.48550/arXiv.2410.19637 db/journals/corr/corr2410.html#abs-2410-19637 streams/journals/corr

Romina Wild Vittorio Del Tatto Felix Wodaczek Bingqing Cheng Alessandro Laio Automatic feature selection and weighting using Differentiable Information Imbalance. 2024 abs/2411.00851 CoRR https://doi.org/10.48550/arXiv.2411.00851 db/journals/corr/corr2411.html#abs-2411-00851 streams/journals/corr

Santiago Acevedo Alex Rodriguez Alessandro Laio Unsupervised detection of semantic correlations in big data. 2024 abs/2411.02126 CoRR https://doi.org/10.48550/arXiv.2411.02126 db/journals/corr/corr2411.html#abs-2411-02126 streams/journals/corr

Lucrezia Valeriani Diego Doimo Francesca Cuturello Alessandro Laio Alessio Ansuini Alberto Cazzaniga The geometry of hidden representations of large transformer models. 2023 NeurIPS http://papers.nips.cc/paper_files/paper/2023/hash/a0e66093d7168b40246af1cddc025daa-Abstract-Conference.html conf/nips/2023 db/conf/nips/neurips2023.html#ValerianiDCLAC23

Lucrezia Valeriani Diego Doimo Francesca Cuturello Alessandro Laio Alessio Ansuini Alberto Cazzaniga The geometry of hidden representations of large transformer models. 2023 abs/2302.00294 CoRR https://doi.org/10.48550/arXiv.2302.00294 db/journals/corr/corr2302.html#abs-2302-00294

Federica Gerace Diego Doimo Stefano Sarao Mannelli Luca Saglietti Alessandro Laio Optimal transfer protocol by incremental layer defrosting. 2023 abs/2303.01429 CoRR https://doi.org/10.48550/arXiv.2303.01429 db/journals/corr/corr2303.html#abs-2303-01429

Riccardo Rende Federica Gerace Alessandro Laio Sebastian Goldt Optimal inference of a generalised Potts model by single-layer transformers with factored attention. 2023 abs/2304.07235 CoRR https://doi.org/10.48550/arXiv.2304.07235 db/journals/corr/corr2304.html#abs-2304-07235

Aldo Glielmo Iuri Macocco Diego Doimo Matteo Carli Claudio Zeni Romina Wild Maria d'Errico Alex Rodriguez Alessandro Laio DADApy: Distance-based analysis of data-manifolds in Python. 100589 2022 3 Patterns 10 https://doi.org/10.1016/j.patter.2022.100589 https://www.wikidata.org/entity/Q122914926 db/journals/patterns/patterns3.html#GlielmoMDCZWdRL22

Elena Tea Russo Federico Barone Alex Bateman Stefano Cozzini Marco Punta Alessandro Laio DPCfam: Unsupervised protein family classification by Density Peak Clustering of large sequence datasets. 1010610 2022 October 18 PLoS Comput. Biol. 10 https://doi.org/10.1371/journal.pcbi.1010610 db/journals/ploscb/ploscb18.html#RussoBBCPL22

Diego Doimo Aldo Glielmo Sebastian Goldt Alessandro Laio Redundant representations help generalization in wide neural networks. 2022 conf/nips/2022 NeurIPS http://papers.nips.cc/paper_files/paper/2022/hash/7c3a8d20ceadb7c519e9ac1bb77a15ff-Abstract-Conference.html db/conf/nips/neurips2022.html#DoimoGGL22 Paolo Muratore Sina Tafazoli Eugenio Piasini Alessandro Laio Davide Zoccolan Prune and distill: similar reformatting of image information along rat visual cortex and deep neural networks. 2022 conf/nips/2022 NeurIPS http://papers.nips.cc/paper_files/paper/2022/hash/c2d82a425af4c18a35049899fea5ee82-Abstract-Conference.html db/conf/nips/neurips2022.html#MuratoreTPLZ22

Aldo Glielmo Iuri Macocco Diego Doimo Matteo Carli Claudio Zeni Romina Wild Maria d'Errico Alex Rodriguez Alessandro Laio DADApy: Distance-based Analysis of DAta-manifolds in Python. 2022 abs/2205.03373 CoRR https://doi.org/10.48550/arXiv.2205.03373 db/journals/corr/corr2205.html#abs-2205-03373

Paolo Muratore Sina Tafazoli Eugenio Piasini Alessandro Laio Davide Zoccolan Prune and distill: similar reformatting of image information along rat visual cortex and deep neural networks. 2022 abs/2205.13816 CoRR https://doi.org/10.48550/arXiv.2205.13816 db/journals/corr/corr2205.html#abs-2205-13816

Iuri Macocco Aldo Glielmo Jacopo Grilli Alessandro Laio Intrinsic dimension estimation for discrete metrics. 2022 abs/2207.09688 CoRR https://doi.org/10.48550/arXiv.2207.09688 db/journals/corr/corr2207.html#abs-2207-09688

Elena Tea Russo Alessandro Laio Marco Punta Density Peak clustering of protein sequences associated to a Pfam clan reveals clear similarities and interesting differences with respect to manual family annotation. 121 2021 22 BMC Bioinform. 1 https://doi.org/10.1186/s12859-021-04013-x db/journals/bmcbi/bmcbi22.html#RussoLP21

Rodrigo Ochoa Miguel A. Soler Alessandro Laio Pilar Cossio PARCE: Protocol for Amino acid Refinement through Computational Evolution. 107716 2021 260 Comput. Phys. Commun. https://doi.org/10.1016/j.cpc.2020.107716 db/journals/cphysics/cphysics260.html#OchoaSLC21

Maria d'Errico Elena Facco Alessandro Laio Alex Rodriguez Automatic topography of high-dimensional data sets by non-parametric density peak clustering. 476-492 2021 560 Inf. Sci. https://doi.org/10.1016/j.ins.2021.01.010 db/journals/isci/isci560.html#dErricoFLR21

Aldo Glielmo Claudio Zeni Bingqing Cheng Gábor Csányi Alessandro Laio Ranking the information content of distance measures. 2021 abs/2104.15079 CoRR https://arxiv.org/abs/2104.15079 db/journals/corr/corr2104.html#abs-2104-15079

Diego Doimo Aldo Glielmo Sebastian Goldt Alessandro Laio Representation mitosis in wide neural networks. 2021 abs/2106.03485 CoRR https://arxiv.org/abs/2106.03485 db/journals/corr/corr2106.html#abs-2106-03485

Nina I Ilieva Nicola Galvanetto Michele Allegra Marco Brucale Alessandro Laio Automatic classification of single-molecule force spectroscopy traces from heterogeneous samples. 5014-5020 2020 36 Bioinform. 20 https://doi.org/10.1093/bioinformatics/btaa626 https://www.wikidata.org/entity/Q97554563 db/journals/bioinformatics/bioinformatics36.html#IlievaGABL20

Michele Allegra Shima Seyed-Allaei Nicolas W. Schuck Daniele Amati Alessandro Laio Carlo Reverberi Brain network dynamics during spontaneous strategy shifts and incremental task optimization. 116854 2020 217 NeuroImage https://doi.org/10.1016/j.neuroimage.2020.116854 https://www.wikidata.org/entity/Q93223406 db/journals/neuroimage/neuroimage217.html#AllegraSSALR20

Diego Doimo Aldo Glielmo Alessio Ansuini Alessandro Laio Hierarchical nucleation in deep neural networks. 2020 NeurIPS https://proceedings.neurips.cc/paper/2020/hash/54f3bc04830d762a3b56a789b6ff62df-Abstract.html conf/nips/2020 db/conf/nips/neurips2020.html#DoimoGAL20

Diego Doimo Aldo Glielmo Alessio Ansuini Alessandro Laio Hierarchical nucleation in deep neural networks. 2020 abs/2007.03506 CoRR https://arxiv.org/abs/2007.03506 db/journals/corr/corr2007.html#abs-2007-03506

Rodrigo Ochoa Alessandro Laio Pilar Cossio Predicting the Affinity of Peptides to Major Histocompatibility Complex Class II by Scoring Molecular Dynamics Simulations. 3464-3473 2019 59 J. Chem. Inf. Model. 8 https://doi.org/10.1021/acs.jcim.9b00403 https://www.wikidata.org/entity/Q91763887 db/journals/jcisd/jcisd59.html#OchoaLC19

Elena Facco Andrea Pagnani Elena Tea Russo Alessandro Laio The intrinsic dimension of protein sequence evolution. 2019 15 PLoS Comput. Biol. 4 https://doi.org/10.1371/journal.pcbi.1006767 https://www.wikidata.org/entity/Q64018805 db/journals/ploscb/ploscb15.html#FaccoPRL19

Alessio Ansuini Alessandro Laio Jakob H. Macke Davide Zoccolan Intrinsic dimension of data representations in deep neural networks. 6109-6119 2019 NeurIPS https://proceedings.neurips.cc/paper/2019/hash/cfcce0621b49c983991ead4c3d4d3b6b-Abstract.html http://papers.nips.cc/paper/8843-intrinsic-dimension-of-data-representations-in-deep-neural-networks conf/nips/2019 db/conf/nips/nips2019.html#AnsuiniLMZ19

Michele Allegra Elena Facco Alessandro Laio Antonietta Mira Clustering by the local intrinsic dimension: the hidden structure of real-world data. 2019 abs/1902.10459 CoRR http://arxiv.org/abs/1902.10459 db/journals/corr/corr1902.html#abs-1902-10459

Alessio Ansuini Alessandro Laio Jakob H. Macke Davide Zoccolan Intrinsic dimension of data representations in deep neural networks. 2019 abs/1905.12784 CoRR http://arxiv.org/abs/1905.12784 db/journals/corr/corr1905.html#abs-1905-12784

Luisa M. R. Napolitano Arin Marchesi Alex Rodriguez Matteo De March Silvia Onesti Alessandro Laio Vincent Torre The permeation mechanism of organic cations through a CNG mimic channel. 2018 14 PLoS Comput. Biol. 8 https://doi.org/10.1371/journal.pcbi.1006295 https://www.wikidata.org/entity/Q58803068 db/journals/ploscb/ploscb14.html#NapolitanoMRMOL18

Maria d'Errico Elena Facco Alessandro Laio Alex Rodriguez Automatic topography of high-dimensional data sets by non-parametric Density Peak clustering. 2018 abs/1802.10549 CoRR http://arxiv.org/abs/1802.10549 db/journals/corr/corr1802.html#abs-1802-10549

Elena Facco Maria d'Errico Alex Rodriguez Alessandro Laio Estimating the intrinsic dimension of datasets by a minimal neighborhood information. 2018 abs/1803.06992 CoRR http://arxiv.org/abs/1803.06992 db/journals/corr/corr1803.html#abs-1803-06992

Toni Giorgino Alessandro Laio Alex Rodriguez METAGUI 3: A graphical user interface for choosing the collective variables in molecular dynamics simulations. 204-209 2017 217 Comput. Phys. Commun. https://doi.org/10.1016/j.cpc.2017.04.009 db/journals/cphysics/cphysics217.html#GiorginoLR17

Francesca Rizzato Alex Rodriguez Alessandro Laio Non-Markovian effects on protein sequence evolution due to site dependent substitution rates. 258 2016 17 BMC Bioinform. https://doi.org/10.1186/s12859-016-1135-1 https://www.wikidata.org/entity/Q36061349 db/journals/bmcbi/bmcbi17.html#RizzatoRL16

Changru Ma Layla Martin-Samos Stefano Fabris Alessandro Laio Simone Piccinin QMMMW: A wrapper for QM/MM simulations with Quantum ESPRESSO and LAMMPS. 191-198 2015 195 Comput. Phys. Commun. https://doi.org/10.1016/j.cpc.2015.04.024 db/journals/cphysics/cphysics195.html#MaMFLP15

Ina Bisha Alex Rodriguez Alessandro Laio Alessandra Magistrato Metadynamics Simulations Reveal a Na<sup>+</sup> Independent Exiting Path of Galactose for the Inward-Facing Conformation of vSGLT. 2014 10 PLoS Comput. Biol. 12 https://doi.org/10.1371/journal.pcbi.1004017 https://www.wikidata.org/entity/Q34732259 db/journals/ploscb/ploscb10.html#BishaRLM14

Edoardo Sarti Stefano Zamuner Pilar Cossio Alessandro Laio Flavio Seno Antonio Trovato BACHSCORE. A tool for evaluating efficiently and reliably the quality of large sets of protein structures. 2860-2865 2013 184 Comput. Phys. Commun. 12 https://doi.org/10.1016/j.cpc.2013.07.019 https://www.wikidata.org/entity/Q58032973 db/journals/cphysics/cphysics184.html#SartiZCLST13

Xevi Biarnés Fabio Pietrucci Fabrizio Marinelli 0002 Alessandro Laio METAGUI. A VMD interface for analyzing metadynamics and molecular dynamics simulations. 203-211 2012 183 Comput. Phys. Commun. 1 https://doi.org/10.1016/j.cpc.2011.08.020 https://www.wikidata.org/entity/Q58325550 db/journals/cphysics/cphysics183.html#BiarnesPML12

Pilar Cossio Antonio Trovato Fabio Pietrucci Flavio Seno Amos Maritan Alessandro Laio Exploring the Universe of Protein Structures beyond the Protein Data Bank. 2010 6 PLoS Comput. Biol. 11 https://doi.org/10.1371/journal.pcbi.1000957 https://www.wikidata.org/entity/Q27334418 db/journals/ploscb/ploscb6.html#CossioTPSML10

Fabrizio Marinelli 0002 Fabio Pietrucci Alessandro Laio Stefano Piana A Kinetic Model of Trp-Cage Folding from Multiple Biased Molecular Dynamics Simulations. 2009 5 PLoS Comput. Biol. 8 https://doi.org/10.1371/journal.pcbi.1000452 https://www.wikidata.org/entity/Q21092563 db/journals/ploscb/ploscb5.html#MarinelliPLP09

Håkan W. Hugosson Alessandro Laio Patrick Maurer Ursula Rothlisberger A comparative theoretical study of dipeptide solvation in water. 672-684 2006 27 J. Comput. Chem. 5 https://doi.org/10.1002/jcc.20360 https://www.wikidata.org/entity/Q46943944 db/journals/jcc/jcc27.html#HugossonLMR06

Santiago Acevedo Michele Allegra Daniele Amati Alessio Ansuini Maximilian Autenrieth Jean Barbier Federico Barone Marco Baroni Alex Bateman Xevi Biarnés Ina Bisha Marco Brucale Matteo Carli Alberto Cazzaniga Bingqing Cheng Emily Cheng Gabriella Contardo Pilar Cossio Stefano Cozzini Gábor Csányi Francesca Cuturello Maria d'Errico Diego Doimo Stefano Fabris Elena Facco Nicola Galvanetto Federica Gerace Toni Giorgino Aldo Glielmo Sebastian Goldt Tobias Grafke Jacopo Grilli Heikki Haario Håkan W. Hugosson Nina I Ilieva Corentin Kervadec Changru Ma Jakob H. Macke Iuri Macocco Alessandra Magistrato Matéo Mahaut Stefano Sarao Mannelli Matteo De March Arin Marchesi Fabrizio Marinelli 0002 Amos Maritan Layla Martin-Samos Andrea Mascaretti Patrick Maurer Antonietta Mira Paolo Muratore Luisa M. R. Napolitano Antonio Di Noia Rodrigo Ochoa Silvia Onesti Andrea Pagnani Stefano Piana Eugenio Piasini Simone Piccinin Fabio Pietrucci Marco Punta Riccardo Rende Carlo Reverberi Francesca Rizzato Alex Rodriguez Ursula Rothlisberger Elena Tea Russo Luca Saglietti Edoardo Sarti Andre Scaffidi Nicolas W. Schuck Flavio Seno Shima Seyed-Allaei Miguel A. Soler Sebastian Springer Sina Tafazoli Vittorio Del Tatto Franky Kevin Nando Tezoh Vincent Torre Roberto Trotta Antonio Trovato Ali Hussaini Umar Lucrezia Valeriani Romina Wild Felix Wodaczek Jade Yu Lei Yu Stefano Zamuner Claudio Zeni Davide Zoccolan