Find Academic Supervisors

Markus ReichsteinView profile

Professor

• Biogeochemistry
• Climate Science
• Ecosystem Ecology
• +4 more

Markus Reichstein is a Professor for Global Geoecology at Friedrich Schiller University (FSU) Jena and Director of the Biogeochemical Integration Department at the Max Planck Institute for Biogeochemistry. His research focuses on ecosystem responses to climate variability, climate extremes, and the application of AI in Earth system science. He holds a PhD in Plant Ecology from the University of Bayreuth and has pioneered interdisciplinary approaches combining machine learning with environmental modeling. Key roles include leadership in the Michael-Stifel-Center Jena for Data-driven and Simulation Science and founding director of the ELLIS Unit Jena. He contributed to the IPCC Special Report on Climate Extremes and has received prestigious awards such as the Leibniz Prize. His work bridges ecology, hydrology, and atmospheric science, addressing critical global challenges like carbon cycle feedbacks and ecosystem resilience. Recent research emphasizes AI-driven early warning systems for climate risks, integrating observational data with mechanistic models. His team explores land-atmosphere interactions, soil-vegetation dynamics, and the impacts of climate extremes on societal systems. Notable projects include GartenDiv, a citizen science initiative for garden biodiversity, and advancements in global water cycle modeling using hybrid AI-physics frameworks. Awards include the Piers J. Sellers Award (2018), ERC Synergy Grant (2019), and Leibniz Prize (2020). He collaborates with international networks like ELLIS and Future Earth, advancing data-driven solutions for sustainability science.

Martin PeiferView profile

Professor

• Computational Cancer Genomics
• Tumor Evolution
• Genome Instability
• +5 more

Professor Martin Peifer is a computational cancer genomics researcher at the University of Cologne, where he leads the Department of Translational Genomics. He serves as Principal Investigator of the Peifer Lab, which focuses on developing computational methods to analyze cancer genome sequencing data. His work is deeply integrated with the Center for Data and Simulation Science and he is an active member of the International Cancer Genome Consortium and the Pan-Cancer Analysis of Whole Genomes project. Peifer's research interests center on computational approaches to understanding cancer biology, with particular emphasis on tumor evolution and genome instability mechanisms. His lab develops methods to analyze somatic genome alterations including point mutations, copy number changes, and rearrangements. They also create computational tools for integrative genome analyses, tumor evolution reconstruction, and single-cell sequencing data analysis (both RNA and DNA). His interdisciplinary team applies high-performance computing and machine learning to interpret complex cancer sequencing data, aiming to better understand tumorigenesis, clonal evolution, and therapy resistance. Analysis of Peifer's extensive publication record reveals a strong focus on neuroblastoma and lung cancer genomics, with particular attention to tumor evolution patterns and genomic instability mechanisms. His work spans multiple cancer types but maintains consistent themes of computational methodology development and application to understand cancer progression and treatment resistance. The publications demonstrate increasing sophistication in analyzing intra-tumor heterogeneity and clonal dynamics over time. Peifer leads an active research group including postdoctoral fellows (Joel Kaufmann, Dr. Stephanie Pabel, Agnieszka Rumińska) and PhD students (Magdalena Seiffert, Justinas Valiulis). His lab is involved in the Collaborative Research Center 1399 focused on Mechanisms of Drug Sensitivity and Resistance in Small Cell Lung Cancer, indicating significant grant funding and collaborative research efforts. The Peifer Lab operates at the intersection of computational biology and cancer research, maintaining an interdisciplinary approach that combines bioinformatics, machine learning, and high-performance computing to address complex questions in cancer genomics. Their work has significant implications for understanding cancer evolution and developing more effective treatment strategies.

Kevin BaumView profile

Researcher

• Explainable AI
• AI Ethics
• AI Fairness
• +4 more

Kevin Baum is a computer scientist currently serving as the deputy head of the Neuro-Mechanistic Modelling (NMM) department at the German Research Center for Artificial Intelligence (DFKI) since January 2023, and head of the Centre for European Research in Trusted AI (CERTAIN) at DFKI since December 2023. Based at the Saarland Informatics Campus in Saarbrücken, Germany, he completed his doctorate in philosophy in March 2024, combining technical expertise with philosophical depth. His work bridges computer science with ethics, focusing on making AI systems transparent and accountable to human users. Dr. Baum's research program centers on interdisciplinary questions concerning the explainability and transparency of AI systems. His work spans multiple significant projects including the Explainable Intelligent System (EIS) initiative and project E7 of the Transregional Collaborative Research Centre 248 "Foundations of Perspicuous Software Systems" (CPEC). He has developed frameworks for understanding stakeholder perspectives on explainable AI and investigated how different information types about automated systems affect user perceptions of fairness and justice. His approach consistently combines theoretical foundations with practical implementations across diverse contexts. Analysis of his publication trends reveals a clear trajectory from theoretical foundations in machine ethics toward practical implementations of explainability requirements in real-world contexts. His work demonstrates increasing focus on human oversight effectiveness, fairness monitoring, and ethical considerations across various AI applications. He has made significant contributions to both academic discourse and practical AI development guidelines, with publications spanning computer science, philosophy, psychology, and human-computer interaction venues. Award for Ethics for Nerds lecture series As a research leader, Dr. Baum contributes to shaping AI development practices through his departmental leadership and interdisciplinary collaborations. His current work with CERTAIN focuses on establishing European research standards for trusted AI development and deployment, emphasizing the practical implementation of ethical requirements in AI systems. He maintains active collaborations across multiple institutions and disciplines, reflecting his commitment to bridging technical and philosophical considerations in AI development. At DFKI, he leads research that combines neuroscientific insights with AI development to create more interpretable systems. The NMM department focuses on both theoretical research on explainable AI foundations and practical applications in various domains, with particular attention to how different stakeholders understand and require explanations from AI systems.

Maria Francesca SpadeaView profile

Professor

• Medical Image Processing
• Artificial Intelligence in Healthcare
• Radiomics
• +5 more

Prof. Dr.-Ing. Maria Francesca Spadea serves as Director of the Institute of Biomedical Engineering (IBT) at Karlsruhe Institute of Technology (KIT), part of the Helmholtz Association. Her leadership role includes overseeing research initiatives, teaching activities, and administrative responsibilities within the institute. Located in space 512, she maintains regular consultation hours on Wednesdays from 10:30-11:30 am by appointment. Professor Spadea's research spans several cutting-edge areas in biomedical engineering, with particular focus on medical image processing, artificial intelligence applications in healthcare, and radiomics. Her work bridges computational techniques with clinical applications, emphasizing practical solutions for medical imaging challenges. She has pioneered approaches in federated learning for medical image translation, particularly in CT/MRI synthesis for radiation therapy applications. Her research also extends to cancer cell analysis, vascular biomechanics, and medical robotics, demonstrating a broad yet cohesive research portfolio that addresses critical challenges in modern healthcare. Analysis of Professor Spadea's recent publications reveals a strong emphasis on AI-driven medical imaging solutions, particularly in the translation between different imaging modalities (like MRI-to-CT) using federated learning approaches that preserve patient privacy. Her work demonstrates growing specialization in radiation therapy applications, with multiple publications addressing synthetic CT generation for treatment planning. There's also a clear trajectory toward multi-institutional collaboration, as evidenced by her involvement in projects spanning multiple research centers across Europe. Professor Spadea actively mentors numerous students, including M. Krohmer Zabaleta, N. Skupien, and M. Destito, who have completed bachelor's and master's theses under her supervision. Her research group appears well-integrated within the broader Institute of Biomedical Engineering, collaborating extensively with colleagues like P. Zaffino and C.B. Raggio on multiple projects. The group maintains strong connections with clinical partners, as evidenced by publications addressing real-world medical challenges in radiation therapy, cardiology, and neurosurgery. The research activities of Professor Spadea's team are centered within the Institute of Biomedical Engineering at KIT, with particular focus on medical imaging processing and AI applications. Her laboratory appears to specialize in developing computational tools for medical image analysis, with recent work emphasizing privacy-preserving federated learning frameworks that enable multi-institutional collaboration without sharing sensitive patient data. The team maintains active collaborations with clinical departments, particularly in radiation oncology, as evidenced by numerous publications addressing CT synthesis for radiation therapy planning.

Matthias RareyView profile

Professor

• Bioinformatics
• Cheminformatics
• Algorithmic Molecular Design
• +5 more

Prof. Dr. Matthias Rarey is a computer scientist and Professor at the University of Hamburg's Center for Bioinformatics. He holds a Ph.D. in Computer Science from the University of Bonn (1996) and has been leading the Algorithmic Molecular Design working group since 2002. His research focuses on molecular design algorithms, cheminformatics tools, and 3D bioinformatics. Co-founder of BioSolveIT GmbH Former cheminformatics group leader at Fraunhofer SCAI Former researcher at SmithKline Beecham and Roche Bioscience Head of Helmholtz Data Science Graduate School DASHH Director of Center for Data and Computing in Natural Science (CDCS) Research interests span algorithmic molecular design, cheminformatics, structure-based drug discovery, and machine learning applications in bioactivity prediction. His group developed widely used tools like FlexX, PoseView, and SpaceLight for molecular modeling and fragment space analysis. Recent publications focus on geometric pattern matching in protein-ligand interfaces, combinatorial fragment space encoding, adverse drug reaction network analysis, and efficient shape-based virtual screening. The work emphasizes scalable algorithms for billion-sized compound libraries and integration of machine learning with traditional cheminformatics approaches. Scientific awards include: GMD Award 1996 (Best Dissertation) GMD Award 2000 (Best Project) NRW Wissenschaftspreis 2002 Corwin Hansch Award 2005 Emerging Technologies Award 2011 Norddeutscher Wissenschaftspreis 2020 Academic leadership roles: Founding director of Center for Bioinformatics Co-founder of M.Sc. Bioinformatics and B.Sc. Computing in Science programs Chair of doctoral committee at Faculty of Computer Science Member of EMBL-EBI's Molecular and Cellular Structure advisory board Former Associate Editor of Journal of Chemical Information and Modeling

Jörg HackermüllerView profile

Professor

• Bioinformatics
• Omics Data Analysis
• Toxicology
• +3 more

Prof. Dr. Jörg Hackermüller is a computational biologist with expertise in Omics data integration Toxicology Environmental risk assessment Non-coding RNA biology . He serves as Head of the Department of Computational Biology and Chemistry at the Helmholtz Centre for Environmental Research (UFZ) since 2024 and holds a Professorship at the Faculty of Mathematics and Computer Science at Leipzig University since 2021. His research focuses on Developing AI methods for chemical toxicity prediction Multi-omics integration for mechanistic toxicology Data standardization in environmental monitoring Non-coding RNAs as biomarkers in disease and toxicity and has produced 15+ recent publications spanning tools like multiGSEA and deepFPlearn+ . He collaborates with teams across UFZ Leipzig University Novartis Fraunhofer Institute and leads projects like InCeTo and SafePol , integrating exposome research with systems biology.

Andreas MaierView profile

Researcher

• Drug Repurposing
• Network Medicine
• Bioinformatics
• +3 more

Andreas Maier is a Researcher at the University of Hamburg's Faculty of Mathematics, Informatics and Natural Sciences, affiliated with the Computational Systems Biology department. He began his PhD in May 2021 with Cosy.Bio (Center for Systems Biology) at UHH, focusing on drug repurposing projects such as REPO-TRIAL. Previously, he completed a Bioinformatics master's thesis at TUM (Technical University of Munich), developing a web application for analyzing molecular disease networks. His research interests emphasize network medicine, drug repurposing, and computational tools for biomedical discovery. He has contributed to platforms like NeDRex-Web, Drugst.One, and BioCypher, which democratize access to systems medicine workflows. His work bridges heterogeneous data integration, federated learning for rare diseases, and quantum computing applications in genetics. Maier's publications highlight innovations in knowledge graph-based drug discovery, privacy-preserving federated learning, and single-cell network analysis. He actively develops open-source bioinformatics tools to address challenges in disease module identification and patient stratification. His projects align with the REPO4EU consortium and other collaborative initiatives in translational bioinformatics.

Beate EscherView profile

Professor

• Environmental Toxicology
• In Vitro Bioassays
• New Approach Methods (NAMs)
• +12 more

Prof. Dr. Beate Escher is Head of the Department of Cell Toxicology at the Helmholtz Centre for Environmental Research (UFZ) in Leipzig, Germany. She holds professorial positions at Eberhard Karls University of Tübingen , is a Privatdozent at ETH Zurich , and is affiliated with the University of Queensland and Griffith University in Australia. Her research program focuses on advancing in vitro bioassays and New Approach Methods (NAMs) for environmental and human health risk assessment of micropollutants. Her research interests lie at the intersection of environmental toxicology , molecular toxicology , and exposure science . She develops and applies bioanalytical tools for water quality assessment, with a focus on pharmaceuticals, pesticides, and transformation products. Her work includes mechanism-based toxicity assessment , toxicokinetic-toxicodynamic (TKTD) modeling , and the development of the CITEPro robotic bioassay platform for high-throughput screening. She integrates omics data , computational modeling , and machine learning to improve chemical hazard characterization. Recent publications highlight trends in chemical mixture toxicity , safe-by-design chemicals , ionic compound assessment , and machine learning applications in toxicology. Her work increasingly leverages data-driven approaches to prioritize contaminants and predict biological effects across species. Scientific Awards: Highly Cited Researcher (Web of Science/Clarivate, Top 0.1%, 2020) Outstanding Achievements in Environmental Science and Technology (ES&T & ACS ENVR, 2023) Advising and Grants: She supervises multiple doctoral students and leads major collaborative projects such as InCeTo, MibiTox, nanoINHALE, and SafePol. She received an Australian Research Council grant (2011–2014) and leads Swiss National Science Foundation-funded initiatives. She was a member of the German Science Council (2017–2024) and serves on the Board of Reviewing Editors of SCIENCE . Labs and Teams: She leads the Cell Toxicology team at UFZ, which includes researchers such as Dr. Luise Henneberger, Dr. Julia Huchthausen, and Dr. Haotian Wang. The team operates the CITEPro platform and contributes to international consortia focused on exposome research and chemical safety.

Hannah SpitzerView profile

Assistant Professor

• Computational Biology
• Machine Learning
• Spatial Omics
• +4 more

Hannah Spitzer is a Research Group Leader at the Institute for Stroke and Dementia Research (ISD) at Ludwig Maximilian University of Munich and an associated Research Group Leader at Helmholtz Munich's Computational Health Center. She leads the Spitzer Lab, focusing on computational analysis of multimodal brain datasets to advance understanding of neurovascular and neurodegenerative diseases. Her educational background includes: PhD in Computer Science from Heinrich-Heine University Düsseldorf and Research Center Jülich (2015-2020) Master's in Computer Science from RWTH Aachen (2013-2015) Bachelor's in Computer Science from RWTH Aachen (2009-2013) Dr. Spitzer's research integrates computational biology and machine learning to decode brain complexity, with emphasis on spatial omics analysis , interpretable image representation learning , and cross-modal data integration . Her group develops tools like squidpy and campa for spatial omics while applying graph neural networks to epilepsy lesion detection through the international MELD project, prioritizing biological interpretability in AI models. Recent publications reveal strong trends in leveraging graph neural networks for subtle brain lesion detection and creating computational frameworks for spatial omics integration. Her work consistently bridges advanced machine learning with clinical neuroscience to uncover disease mechanisms in neurodegeneration and vascular disorders. Dr. Spitzer actively mentors students including current PhD candidate Beatrice Guastella and alumni Deniz Fettahoglu (MSc) and Katia Berr (PhD). Her lab operates through major collaborations including the MELD epilepsy consortium and Helmholtz Imaging Project, with funding supporting computational pipeline development for small-vessel disease prediction and multimodal brain atlasing. The Spitzer Lab comprises postdoc Wasim Aftab and PhD student Beatrice Guastella, working on computational pipelines that integrate histology, spatial omics, and neuroimaging data to decode brain disease mechanisms through interpretable AI approaches.

• Natural Language Processing
• Explainable Artificial Intelligence
• Mechanistic Interpretability
• +3 more

Simon Ostermann serves as a Senior Lecturer at Saarland University and Senior Researcher & Deputy Director at the Multilinguality and Language Technology (MLT) lab of the German Research Center for Artificial Intelligence (DFKI). He leads the Efficient and Explainable NLP (E&E) research group and contributes to major projects including lorAI (Low Resource AI), TRAILS (Trustworthy Machines), PERKS (Procedural Knowledge), DAM-S (Semantic Search), and DisAI (Disinformation Combat). His research centers on democratizing language technology through transparent, robust models—specializing in mechanistic interpretability to reverse-engineer LLM internals and enhance efficiency for low-resource languages. Key focus areas include reducing model size for constrained environments, improving cross-lingual transfer via adapters, and developing structured input techniques. His work bridges theoretical interpretability with practical applications in resource-limited settings. 2025 publications reveal concentrated efforts in low-resource adaptation (language adapters, graph-enhanced embeddings), explainable AI (counterfactual generation, conversational XAI datasets), and multilingual fact-checking systems. Notable trends include systematic neuron manipulation frameworks, rigorous evaluation of synthetic data strategies, and cross-lingual claim verification benchmarks. Ostermann advises six PhD candidates (Anikina, Oguz, Bäumel, al Ghussin, Gurgurov, Vykopal) and multiple MSc students on topics spanning RAG hallucinations, multilabel classification, and adapter interpretability. His research receives funding through DFKI-led consortia with European and international partners focusing on trustworthy, efficient AI deployment. The E&E group under his leadership drives innovation in efficient NLP through biweekly seminars, collaborative coding sessions, and partnerships with institutions like KInIT. Current initiatives prioritize green computing for language models and real-world deployment in industrial procedural knowledge systems.

Ana LucicView profile

Assistant Professor

• Interpretable Machine Learning
• Artificial Intelligence
• Earth System Science
• +3 more

Ana Lucic is an Assistant Professor in Artificial Intelligence at the University of Amsterdam , with a joint appointment between the Institute for Logic, Language and Computation and the Informatics Institute . Her research focuses on interpretable machine learning applications for scientific discovery and societal impact. Formerly at Microsoft Research AI for Science and Partnership on AI PhD in Explainable Machine Learning from University of Amsterdam (2022) BSc/MSc in Mathematics from McMaster University Research Highlights: Develops mechanistic interpretability methods for deep learning architectures. Created Aurora , a foundation model for Earth system forecasting outperforming traditional operational models in air quality prediction and tropical cyclone tracking. Pioneers Clifford-Steerable CNNs for geophysical data analysis. Actively hiring PhD students for AI transparency research . Collaborative Networks: Contributions to ELLIS Summer School and ICML workshops . Collaborates with Microsoft Research AI for Science team on climate-related ML projects. Involved in organizing TerraBytes workshop at ICML 2025. Recent Advancements: Key role in publishing Aurora model in Nature (2025), demonstrating superior performance in Earth system forecasting. Supervises Ege Erdogan , new PhD student focused on mechanistic interpretability. Actively contributes to open-source AI development through GitHub repositories and technical discussions.

• Agricultural Engineering
• Environmental Biotechnology
• Animal Husbandry
• +4 more

Thomas Amon is a Professor at the Free University of Berlin and Head of the Department of Sensor Technology and Modeling at the Leibniz Institute of Agricultural Engineering and Bioeconomy Potsdam (ATB) . He leads research in livestock-environment interactions , with a focus on reducing greenhouse gases, managing antimicrobial resistance, and optimizing dairy and pig production systems. Current Roles: Department Head (ATB), Professor (Free University Berlin) Research Pillars: Animal husbandry emissions, biogas systems, antibiotic resistance dynamics, climate-resilient farming His research interests span agricultural biotechnology, environmental microbiology, and sustainable systems engineering. Key projects include: LeibnizLabPP - Pandemic preparedness in animal-environment systems SMP4 - Antibiotic use modeling in livestock EmiMod - Emission quantification methods Using process-based models like Dutch Tier 3 and ManureDNDC, he quantifies whole-farm carbon and nitrogen cycles across confinement and pasture-based dairy systems. His work reveals: 63% of GHG emissions from confinement systems come from enteric methane Pasture systems show 18-69% soil organic carbon sequestration 19.9 tCO 2 -eq per cow in confinement vs 2.7-4.0 tCO 2 -eq in pasture systems His scientific contributions include: First mechanistic model linking diet composition to antibiotic resistance gene persistence Novel framework for dairy GHG accounting across barn-manure-soil interfaces Optimized ventilation models for pig housing with outdoor access

René PetersView profile

Professor

• Cooperative asymmetric catalysis
• Organometallic chemistry
• Stereoselective synthesis
• +3 more

René Peters is Professor and Head of the Examination Committee for Chemistry programs at the University of Stuttgart's Institute of Organic Chemistry. His research focuses on developing innovative cooperative asymmetric catalysis methods inspired by enzymatic processes, aiming to solve long-standing synthetic challenges with high efficiency and stereocontrol. Peters' group specializes in designing bifunctional and polyfunctional catalysts that activate both nucleophiles and electrophiles simultaneously through Lewis acid/base cooperativity. This biomimetic approach enables enantioselective transformations under mild conditions, including 1,4-additions, allylations, cycloadditions, and fluorinations. Recent work explores zwitterionic catalysts, palladacycle architectures, and gold nanoparticle systems for challenging bond formations. His publications demonstrate progressive refinement of cooperative catalyst systems, with recent advances in stereoretentive allylations, enantiodivergent syntheses, and computational-experimental integration for reaction optimization. The group maintains strong emphasis on practical methodologies with potential industrial scalability. Laboratory facilities support advanced synthesis, catalyst characterization (X-ray crystallography, NMR), and computational modeling. Peters leads collaborative projects on catalytic C-C bond formation and stereoselective fluorination. As Head of Examination Committee, he oversees chemistry curriculum development and assessment. Key innovations include planar chiral palladacycles for efficient enantioselective arylations and novel gold nanocatalysts for Stille couplings. Future work expands cooperative catalysis to underrepresented transformations and develops machine learning approaches for catalyst optimization.

Johannes NeugebauerView profile

Professor

• Quantum Chemistry
• Computational Chemistry
• Theoretical Organic Chemistry
• +3 more

Professor Johannes Neugebauer serves as University Professor of Theoretical Organic Chemistry at the Institute of Organic Chemistry, University of Münster, where he leads a research group dedicated to developing quantum chemical methodologies for complex chemical environments including solvents, proteins, molecular crystals, and surfaces. His work bridges theoretical predictions with experimental validation through extensive collaborations across multiple disciplines. Neugebauer's research focuses on advanced computational approaches including subsystem-based Density Functional Theory (DFT) and density-based embedding methods for both ground and excited electronic states. His group has pioneered subsystem methods for excited states and linear-response properties, developed theoretical frameworks for light-driven processes, and created multi-level electron-correlation techniques. Key contributions include the Subsystem Quantum Chemistry Program SERENITY and insights into light-enabled deracemization of cyclopropanes through collaborations with experimental groups. The research spans applications in molecular spectroscopy, catalytic processes, and materials science, with emphasis on selective and efficient calculations for complex systems. Analysis of recent publications reveals a consistent trajectory toward increasingly sophisticated computational models for chemical reactivity, with growing emphasis on interdisciplinary applications in photochemistry, surface science, and catalytic reaction mechanisms. The work demonstrates strong integration between method development and practical applications across organic chemistry, materials science, and spectroscopy. Professor Neugebauer has mentored numerous doctoral students who have established careers at prestigious institutions worldwide, including ETH Zurich, University of Basel, Rutgers University, and University of Bristol. His research is supported by major collaborative initiatives including CRC 1459 "Intelligent Matter", IRTG 2678 Münster-Nagoya on Functional Pi-Systems, CMTC (Center for Multiscale Theory and Computation), SoN (Center for Soft Nanoscience), and BACCARA (International Graduate School of Battery Chemistry). The Neugebauer group operates within the University of Münster's Institute of Organic Chemistry while maintaining active participation in multiple interdisciplinary research centers. The group collaborates extensively with experimental chemistry teams both within Münster and internationally, particularly in the areas of photocatalysis, surface chemistry, and molecular modeling. Current research directions include advancing quantum chemical methods for machine learning integration and developing computational tools for next-generation materials design.

• Artificial Intelligence
• Multi-Agent Systems
• Social Network Analysis
• +5 more

Gita Reese Sukthankar is a Professor at the University of Central Florida, specializing in artificial intelligence, multi-agent systems, and social network analysis. Her work integrates machine learning, human-robot interaction, and collaborative systems to address challenges in decentralized task allocation, online community dynamics, and human-machine teaming. She has contributed to projects involving agent-based modeling, reinforcement learning, and ethical AI applications in open-source software and policy discourse moderation. Affiliations: University of Central Florida Key Research Areas: Multi-Agent Systems, Social Network Analysis, Reinforcement Learning, Human-Computer Interaction Her research explores topics such as conflict prediction in team dialogues, bot impact on GitHub workflows, and chess mastery analysis using language models. She has co-authored over 185 publications in top venues like AAAI, AAMAS, and IROS, often collaborating with researchers like Rahul Sukthankar, Katia Sycara, and Kiran Lakkaraju. Her work bridges theoretical AI advancements with practical applications in robotics, software development, and policy analysis, emphasizing ethical considerations and scalable solutions.