Laure Berti-Equille                             Research Director


  News

May, 2025

Paper accepted at ECML PKDD 2025 Reseach Track entitled "EM-SEC: Efficient Multi-head Set-valued Evidential Classification" with G. Bezirganyan, S. Sellami, & S. Fournier (AMU).

June, 2025

Tutorial TOTh 2025 on "Knowledge Graphs, LLMs, and RAG" with R. Giannadakis, & R. Milio (University of Crete, TALOS AI for SSH).

May, 2025

Paper accepted at Expert Systems entitled "Single Word Change is All You Need: Designing Attacks and Defenses for Text Classifiers" with L. Xu, S. Alnegheimish (MIT), Alfredo Cuesta-Infante (URJC), & K. Veeramachaneni (MIT).

Apr, 2025

Paper accepted at SIGIR 2025 Resource & Reproducibility Track entitled "Uncertainty-Aware Multimodal Learning: A Dataset and Framework" with G. Bezirganyan, S. Sellami, & S. Fournier (AMU). [GitHub]

Feb, 2025

Paper accepted at CEST 2025 entitled "Forest Resilience, Precipitation, and Ecosystem Service Value: A Correlation and Trend Analysis" with P. Nwachukwu (IRD). [GitHub]

Jan, 2025

Paper accepted at The 28th Intl. Conf. on Artificial Intelligence and Statistics (AIStats 2025) entitled "Multimodal Learning with Uncertainty Quantification based on Discounted Belief Fusion" with G. Bezirganyan, S. Sellami, & S. Fournier (AMU). [OpenReview]

Dec, 2024

MIT News on "Explingo: Explaining AI Predictions using Large Language Models" with A. Zytek, S. Pido, S. Alnegheimish, and K. Veeramachaneni (MIT).

Dec, 2024

AI Papers Podcast Daily on "MIT researchers use large language models to flag problems in complex systems" with S. Alnegheimish, L. Nguyen, and K. Veeramachaneni (MIT).

Nov, 2024

Paper accepted at IEEE Big Data Workshop MMAI 2024 entitled "MixMAS: A Framework for Sampling-Based Mixer Architecture Search for Multimodal Fusion and Learning" with A. Chergui, G. Bezirganyan, S. Sellami, & S. Fournier (AMU). [pdf]

Oct, 2024

Paper accepted at NeurIPS 2004 CCAI Workshop entitled "Hierarchical Classification for Automated Image Annotation of Coral Reef Benthic Structures" with C. Blondin, K. Inagaki, G. Longo, & J. Guérin (IRD). [arXiv.org]

Oct, 2024

Paper accepted at IEEE BigData 2024 entitled "Explingo: Explaining AI Predictions using Large Language Models" with A. Zytek, S. Pido, S. Alnegheimish, & K. Veeramachaneni (MIT). [arXiv.org]

Oct, 2024

Paper accepted at IEEE BigData 2024 entitled "OrionBench: Benchmarking Time Series Generative Models in the Service of the End-User" with S. Alnegheimish, & K. Veeramachaneni (MIT). [arXiv.org]

Oct, 2024

Happy to co-organize the 1rst International Workshop on Good Data for Generative AI in conjunction with AAAI 2025 with D. Vazquez (ServiceNow Research), S. Wang (IBM T. J. Watson Research Center) and R. Raghavendra (Meta).

Sept, 2024

Paper accepted at MVEO@BMVC 2024 Workshop at the British Machine Vision Conf. entitled "Predicting Socio-economic Indicator Variations with Satellite Image Time Series and Transformer" with R. Jarry, M. Chaumont, & G. Subsol (UM). [pdf]

Aug, 2024

Paper accepted at DSAA 2024 entitled "Can Large Language Models be Anomaly Detectors for Time Series?" with S. Alnegheimish, L. Nguyen, & K. Veeramachaneni (MIT). [pdf]

Aug, 2024

MIT News on "MIT researchers use large language models to flag problems in complex systems" with S. Alnegheimish, L. Nguyen, & K. Veeramachaneni (MIT).

Aug, 2024

NVIDIA Blog on "LLM Research Rewrites the Role of AI in Safeguarding Sustainable Systems" with A. Zytek, I. Arnaldo, D. Liu, & K. Veeramachaneni (MIT).

Jul, 2024

Please check LUMA: our benchmarking dataset for learning from multimodal data with uncertainty quantitification in HuggingFace and Medium. [arXiv.org] [HuggingFace] [Medium]

May, 2024

Recipient of the Mobility Grant of TALOS-AI4SSH ERA Chair in Artificial Intelligence for Humanities and Social Sciences, May 2024.

April, 2024

Paper accepted in the Journal of Biomedical Informatics on "Creating a computer assisted ICD coding system: Performance metric choice and use of the ICD hierarchy", with Q. Marcou & N. Novelli (April 2024). [pdf]

March, 2024

Dagstuhl Seminar report on "Integrating HPC, AI, and Workflows for Scientific Data Analysis" is out. Here!

Jan, 2024

Paper accepted at ICLR 2024 entitled "Faithful Vision-Language Interpretation via Concept Bottleneck Models" with S. Lai, L. Hu, J. Wang, & D. Wang (KAUST). [pdf]

Oct, 2023

Paper accepted at TDWG 2023 (SYM11) entitled "Combining biodiversity and environmental data for addressing scientific and societal questions" with Rafael L. G. Raimundo. [pdf]

Jul, 2023

Organization of the Dagstuhl seminar entitled "Integrating HPC, AI, and Workflows for Scientific Data Analysis" (Aug. 27 – Sep. 01, 2023) with R. Ferreira da Silva, R. M. Badia, & U. Leser.

Jul, 2023

Editor of the Special Issue of Sensors on "Deep Learning for Environmental Remote Sensing" with D. Ienco and C. Fraga Dantas.

Jul, 2023

Paper accepted at IEEE BigData 2023 entitled "M2-Mixer: A Multimodal Mixer with Multi-head Loss for Classification from Multimodal Data" with G. Bezirganyan, S. Sellami, & S. Fournier. [pdf]

Jul, 2023

Paper accepted at IGARSS 2023 entitled "Comparing Spatial and Spatio-Temporal Paradigms to Estimate the Evolution of Socio-Economic Indicators from Satellite Images” with R. Jarry, M. Chaumont, and G. Subsol. [pdf]

May, 2023

Poster accepted at EPICLIN 2023 entitled "Deep learning for assisting Healthcare ICD coding" with Q. Marcou and N. Novelli.

Dec, 2022

VentureBeat on "How MIT is training AI language models in an era of quality data scarcity" with L. Xu (MIT), A. Cuesta-Infante (URJC) & K. Veeramachaneni (MIT).

Dec, 2022

Paper accepted at the 2022 IEEE BigData entitled "AER: Auto-Encoder with Regression for Time Series Anomaly Detection" with L. Wong, D. Liu, S. Alnegheimish, and K. Veeramachaneni (MIT). [pdf]

Nov, 2022

Paper accepted at Findings of AACL-IJCNLP 2022 entitled "R&R: Metric-guided Adversarial Sentence Generation" with L. Xu (MIT), A. Cuesta-Infante (Univ. Rey Juan Carlos), and K. Veeramachaneni (MIT). [pdf]

Nov, 2022

Paper accepted at the 1st AAAI 2022 Fall Symposium series on the Role of AI in Responding to Climate Challenges entitled "Discovering Transition Pathways Towards Coviability with Machine Learning" with R. L.G. Raimundo (Federal Univ. of Paraiba, Brazil). [pdf]

Aug, 2022

Best workshop paper KDD AdvML 2022 entitled "In Situ Augmentation for Defending Against Adversarial Attacks on Text Classifiers" with L. Xu (MIT), A. Cuesta Infante (Univ. Rey Juan Carlos), and K. Veeramachaneni (MIT). [pdf]

Aug, 2022

Tutorials at KDD 2022 and AI-ML Systems 2022 entitled "Advances in exploratory data analysis, visualisation and quality for data centric AI systems" presented by H. Patel (IBM Research), S. Guttula (IBM Research), R. S. Mittal (IBM Research), N. Manwani (IIITH), L. Berti-Equille (IRD), and A. Manatkar (IIITH). [slides]

July, 2022

Paper accepted in Earth and Space Science Journal entitled "Mitigation Strategies to Improve Reproducibility of Poverty Estimations From Remote Sensing Images Using Deep Learning" with J. Machicao et al. [pdf]

June, 2022

Two posters accepted in RDA 19th Plenary meeting, part of International Data Week, 20–23 June 2022, Seoul, South Korea on "Reproducibility of Deep Learning"

June, 2022

Paper accepted at ICPRAI 2022 entitled "Stochastic pairing for contrastive anomaly detection on time series" with G. Chambaret, F. Bouchara, E. Bruno, V. Martin and F. Chaillan. [pdf]

June, 2022

Paper accepted at SIGMOD 2022 (ACM International Conference on Management of Data) entitled "Sintel: An Overarching Ecosystem for End-to-End Time Series Anomaly Detection" with S. Alnegheimish, D. Liu, C. Sala, and K. Veeramachaneni. [pdf]   [code]

June, 2022

MIT News on "Building Explainability into the Components of Machine Learning Models" with A. Zytek, I. Arnaldo, D. Liu, & K. Veeramachaneni (MIT).

June, 2022

Paper accepted at KDD Explorations entitled "The Need for Interpretable Features: Motivation and Taxonomy" with A. Zytek, I. Arnaldo, D. Liu, and K. Veeramachaneni (MIT). [arXiv.org]

May, 2022

Paper accepted at ICDE 2022 (International Conference on Data Engineering) entitled "Provenance-aware Discovery of Functional Dependencies on Integrated Views" with U. Comignani, N. Novelli, and A. Bonifati. [arXiv.org]  [code]  [video]

Mar, 2022

Delighted to be joining and as a visiting scientist in the DataToAI group

Jan, 2022

Happy to be the co-leader of IDEAL, the first International Joint Research Lab on AI Applied to Agroecology with Prof. Rafael L.G. Raimundo, Federal Univ. of Paraiba, Brazil.

Nov, 2021

Best Demo paper at CIKM 2021 entitled "DORA The Explorer: Exploring Data with Interactive Deep Reinforcement Learning" with A. Personnaz, S. Amer-Yahia, M. Fabricius, S. Subramanian. [pdf]

Oct, 2021

Paper accepted at DSAA 2021 (International Conference on Data Science and Advanced Analytics) entitled "Statistically Sound User Segment Search" with A. Chibah and S. Amer-Yahia. [pdf]

Aug, 2021

Tutorial presented at KDD 2021 on Challenges in KDD and ML for Sustainable Development with D. Dao, S. Ermon, and B. Goswami. [slides] [abstract]

  Research Focus

I am a Research Director (DR1) in Data Analytics and Applied Machine Learning at IRD, the French research institute on Sustainable Development. My research focuses on designing methods, algorithms, and systems that assist the users in complex and necessary tasks for multimodal data intelligence, multimodal learning, and critical decision making. These tasks combine core data management and engineering techniques (including data integration, fusion, cleaning, and preparation), data analytics, and statistical machine learning methods. The final goal is to let the users focus exclusively on the logic of their application, without being concerned by the underlying models or the execution details of data preprocessing, feature and ML model engineering. Frugality and sustainability are becoming prevalent in my work. See below an overview of the methods, data types, and applications I have been working on so far. Topics

I design and code techniques and end-to-end analytical pipelines, as well as scientific workflows including the following key aspects of Data Science and AI:

    Topics
  • Multimodal Deep Learning
  • Uncertainty Quantification in ML
  • Anomaly Detection
  • Data cleaning, integration, fusion, and preparation
  • Frugal AI, Explainable AI
  • Detection of false information (fake news), fact-checking, and truth discovery
  • Applied ML: sustainability science, SDGs, healthcare and biomedical domains, environmental and Earth Observation sciences, and Internet of Behaviors (IoB).

  IDEAL Lab Leader

I am the co-leader of the International Joint Lab IDEAL (artificial Intelligence, Data analytics, and Earth observation applied to sustAinability Lab) with Rafael L. G. Raimundo, Professor in Ecology at the Federal University of Paraiba, Brazil. With more than 60 permanent researchers, IDEAL lab promotes transdisciplinary research bridging agroecology, artificial intelligence and social sciences to find coviability transition pathways. We also support governance and education projects with integrative approaches to ecological restoration, social inclusion, and bioeconomies. [More information]

  Books

Fact-Checking Data Governance Data Quality
Topics Topics Topics

Publications

Partially on:   DBLP    ResearchGate    GoogleScholar    arXiv    HAL   

2025

2024

Projects

IDEAL International Joint Lab (artificial Intelligence, Data analytics, and Earth observation applied to sustAinability Lab) 12-partner project co-PIs: L. Berti-Equille (IRD ESPACE-DEV, France) and Rafael L.G. Raimundo (Federal Univ. of Paraiba, Brazil) IRD IJL Role: PI [info]  
MOSAIC Multi-site application of Open Science in the creAtion of healthy environments Involving local Communities 15-partner project, PI: E. Roux (IRD, France) European Union   HORIZON-HLTH-2023-ENVHLTH-02-01, Jan. 2024 – Dec. 2027. Role: Participant [info]  
ECO2ADAPT: Ecosystem-based Adaptation and Changemaking to Shape, Protect and Maintain the Resilience of Tomorrow’s Forests 31-partner project, PI: A. Stokes (INRAE, France) European Union   HORIZON-CL6-2021-CLIMATE-01-10, Sept. 2022 – Aug. 2027. Role: Participant [info]  

Patents

Awards

Press

Talks

Mentoring

@ESPACE DEV, Montpellier, France

Biographical Sketch

Laure Berti-Equille is a Research Director (DR1) at IRD, the French Research Institute for Sustainable Development. Before, she was a Full Professor in Computer Science at Aix-Marseille University (France), a senior scientist at Qatar Computing Research Institute (Qatar), an associate professor at University of Rennes 1 (France), and a 2-years visiting researcher at AT&T Labs Research in New Jersey (USA), as a recipient of the prestigious European Marie Curie Outgoing Fellowship. In 2022, she was a visiting scientist at Massachusetts Institute of Technology LIDS (Laboratory for Information & Decision Systems) in the DataToAI group. Her current research interests are on the inter-play of data management, data analytics, and machine learning with a focus on anomaly detection, data cleaning and preparation, and multimodal data fusion and learning with main applications in medical and environmental domains in-line with SGDs. She has more than 120 publications in major conferences or journals along with two books, and 10 co-edited proceedings. She has co-organized numerous workshops on data quality in conjunction with top conferences such as SIGMOD, VLDB and AAAI (2025). She has given several tutorials and keynote talks on data preparation, analytics, and engineering for applied machine learning (KDD'22 & '21, ICDE'18 & '16, CIKM'15, KDD'09, ICDM'09). She served in many program committees of international conferences and was an Associate Editor of the VLDB Journal and the ACM Information and Data Quality Journal. She has been leading projects with grants funded by the French National Agency of Research (ANR), the French National Research Council (CNRS), Belmont Forum, and the European Union. She is a IEEE and ACM senior member.

Contact

IRD ESPACE-DEV Maison de la télédétection
500, rue Jean-François Breton
34093 MONTPELLIER cedex 05, France

laure DOT berti AT ird DOT fr

©Laure Berti-Equille, Nov. 2024