جست‌وجوی استاد و پژوهشگر

• Natural Language Processing
• Computational Linguistics
• Language Model Interpretability
• +۷ مورد دیگر

Anna Rogers is a leading researcher in Natural Language Processing (NLP), known for her foundational and critical work on language model interpretability, dataset quality, and the ethics of AI systems. She has published extensively at top-tier venues including ACL, EMNLP, and NAACL, often collaborating with prominent researchers like Anna Rumshisky and Isabelle Augenstein. Her research interests center on data curation , model generalization , responsible data use , and transparency in large language models . She has conducted influential surveys on community perspectives regarding intelligence in AI and has contributed to improving peer review practices in NLP conferences. Her work on BERTology, including papers like A Primer in BERTology and Revealing the Dark Secrets of BERT , has become key reading in the field. Recent publications highlight her focus on data transparency (e.g., the ROOTS Search Tool), synthetic content detection , and temporal annotation frameworks like NarrativeTime. She also investigates the robustness of models, probing techniques, and the limitations of current benchmarks. Her work consistently emphasizes methodological rigor and ethical considerations in NLP research. She has advocated for better data practices and more thoughtful evaluation paradigms across the community. Natural Language Processing Computational Linguistics Language Model Interpretability Dataset Curation and Quality Ethics in NLP Peer Review in Academic Conferences Anna Rogers has played a key role in shaping meta-discussions in the NLP field, including peer review reform and the societal impact of language technologies. She has co-organized workshops on negative results and contributed to tutorials on reviewing and data use. Her work bridges technical depth with critical reflection on the direction of the field. She has advised or collaborated with numerous researchers, though specific students are not listed in the available data. She has not received any explicitly mentioned scientific awards in the provided text. Anna Rogers leads or contributes to several open-source initiatives and shared resources, including the DECAF framework, the ROOTS Search Tool, and various datasets such as TimeBankNT and RuSentiment. Her work often includes released code and tools to promote reproducibility and further research.

David B Dunsonمشاهده پروفایل

استاد

• Bayesian Statistics
• High-Dimensional Data Analysis
• Nonparametric Bayes
• +۴ مورد دیگر

David B Dunson is a Professor in the Department of Statistical Science at Duke University, specializing in Bayesian statistics, high-dimensional data analysis, and computational methods. His research spans applications in genomics, environmental health, and machine learning, with a focus on nonparametric Bayes, factor models, and scalable inference algorithms. He has advised numerous PhD students, including Alexander Dombowsky and James Johndrow, contributing to advancements in statistical genetics and large-scale data problems. His recent publications address interpretable network discovery, robust covariance modeling, and environmental mixtures analysis. Dunson's methodological work includes empirical Bayes approaches, constrained Bayesian inference, and novel algorithms for handling imbalanced data. These methods have theoretical foundations and practical implementations in R packages like infinitefactor and bfa . Key Research Areas: Bayesian nonparametric modeling High-dimensional factor analysis Computational scalability in MCMC Environmental exposure interactions

• Biomanufacturing
• Biopreservation
• Microfluidics
• +۸ مورد دیگر

Li Zhan is an Assistant Professor of Mechanical Engineering and Biomedical Engineering at Purdue University, located in West Lafayette, Indiana. His research focuses on biomanufacturing, biopreservation, microfluidics, and biomedical device development, with expertise in thermodynamics, heat transfer, and advanced materials. He holds a B.Eng. from Xi’an Jiaotong University (2014), a Ph.D. from the University of Minnesota (2020), and completed a postdoctoral fellowship at Massachusetts General Hospital and Harvard Medical School (2024). Research Interests: Dr. Zhan’s work spans biomanufacturing, microfluidics, and diagnostics, with an emphasis on applications in healthcare and nanotechnology. His recent projects include improving cryopreservation techniques for biological materials and developing micro/nano biomedical devices. He also explores spatial statistical methods for public health challenges, such as vaccine hesitance during the pandemic. Publications: His research has been published in high-impact journals like Nature Communications , Advanced Science , and Nano Letters . Key themes include spatial transcriptomics analysis, machine learning for data clustering, and statistical modeling of heterogeneous systems. Labs and Groups: He leads the Zhan Research Group, which integrates engineering and biological sciences to solve complex biomedical challenges. The group collaborates on projects involving spatial analysis, biopreservation, and advanced manufacturing. Grants and Advising: No specific grants or advisees are listed in the provided materials, though his active research portfolio suggests ongoing collaborative projects. Students interested in his areas of focus are encouraged to contact him directly.

• Phylogenetics
• Bioinformatics
• Pathogen Evolution
• +۳ مورد دیگر

Mathieu Fourment is a Lecturer at the Australian Institute for Microbiology & Infection (AIMI) within the University of Technology Sydney's Faculty of Science. His research focuses on developing phylogenetic algorithms and software to study pathogen evolution, evolutionary processes, and infectious disease management. He holds a PhD in Bioinformatics from Macquarie University and has expertise in bioinformatics and computational biology. Education: PhD in Bioinformatics, Macquarie University (2010) Master by Research in Bioinformatics, University of Glasgow (2003–2004) Master in Computer Science, François Rabelais University (2002–2003) Research Interests: Phylogenetics, pathogen evolution, antimicrobial resistance, and real-time infectious disease tracking. He develops tools like Dodonaphy and Torchtree to analyze viral evolution and improve outbreak surveillance. Grants: Includes NIH-funded research on Bayesian phylogenetics and ARC grants for foodborne outbreak surveillance. Advising: Available for Masters and PhD supervision in computational biology and evolutionary genomics.

Paul Valiantمشاهده پروفایل

دانشیار

• Artificial Intelligence
• Machine Learning
• Natural Language Processing
• +۵ مورد دیگر

Paul Valiant is an Associate Professor of Computer Science at Purdue University, joining in Fall 2021. His research focuses on sublinear algorithms for big data analysis, statistical inference, and the 'unseen' portions of probability distributions. He explores machine learning methodologies, fluid dynamics structures, and cognitive neuroscience, investigating parallels between human brain functions and artificial intelligence. Education: Paul Valiant earned his PhD in Computer Science from MIT in 2008, focusing on testing symmetric properties of distributions. His academic background includes studies leading to his undergraduate degree, though specific details are not provided here. Research Interests: His work spans algorithms and computational complexity, sublinear algorithms for statistical inference, machine learning optimization, fluid dynamics analysis of vorticity and energy flow, and cognitive neuroscience exploring the cerebellum's role. He emphasizes algorithmic efficiency, instance optimality, and theoretical bounds in these domains. Key Contributions: Paul Valiant has developed instance-optimal algorithms, improved entropy estimation methods, and contributed to understanding neural network architectures. His fluid dynamics research employs computational simulations and mathematical analysis to uncover vorticity patterns. Awards: 2008 Best Student Paper Award (Theory of Cryptography Conference) 2019 Test of Time Award (for 'Incrementally Verifiable Computation') 2005 Best Student Paper Award (co-winner, FOCS) NeurIPS 2020 Oral Presentation ACM Best of Computing Notable Article (2014) Advising and Grants: While specific student names are not listed, his research has been supported by institutional grants and collaborations. His work bridges theoretical computer science with applied domains like neuroscience and fluid dynamics, reflecting interdisciplinary impact.

Gonzalo E. Menaمشاهده پروفایل

استادیار

• Statistics
• Data Science
• Machine Learning
• +۳ مورد دیگر

Gonzalo E. Mena is an Assistant Professor in the Department of Statistics and Data Science at Carnegie Mellon University. Previously, he held positions as a Florence Nightingale Bicentennial Fellow and Tutor in Computational Statistics and Machine Learning at the University of Oxford, and a Data Science Initiative Postdoctoral Fellow at Harvard University. He earned his PhD in Statistics from Columbia University and a B.Sc. in Mathematical Engineering from Universidad de Chile. His research focuses on developing robust statistical methods for life sciences, combining cutting-edge neuroscience data with epidemiological surveillance, and advancing statistical optimal transport theory. He is supported by NSF grant DMS-2412895 and actively seeks collaborations with students, emphasizing methodological contributions to accelerate scientific discovery and address biased data challenges. Education: - Ph.D. in Statistics, Columbia University (advised by Liam Paninski) - B.Sc. in Mathematical Engineering, Universidad de Chile. Research Interests: Dr. Mena’s work bridges statistical methodology with practical applications, particularly in neuroscience and epidemiology. He designs scalable techniques to extract meaningful signals from complex datasets, such as neural spike trains, while also developing frameworks to handle large, inherently biased datasets like epidemiological surveillance. Additionally, he explores theoretical aspects of statistical optimal transport, focusing on estimator properties and their application in computational statistics. His contributions aim to balance rigorous statistical foundations with real-world impact, addressing both data generation and inference challenges. Grants: NSF grant DMS-2412895 Awards: Florence Nightingale Bicentennial Fellowship Advising & Collaborations: He advises no listed students but actively seeks collaborations. The NSF grant supports his research, and his work at Harvard involved mentorship under Pierre Jacob. For more details on ongoing projects, visit his research page or Google Scholar profile.

Martin Mugnierمشاهده پروفایل

استادیار

• Econometrics
• Nonlinear Panel Data Models
• High-Dimensional Statistics
• +۳ مورد دیگر

Martin Mugnier is an Assistant Professor at the Paris School of Economics (PSE). He previously held postdoctoral positions at the University of Oxford (Nuffield College) as a Research Fellow. His research focuses on econometric methods, particularly nonlinear panel data models, high-dimensional statistics, and machine learning tools for estimation and identification. He earned his Ph.D. in Economics from Institut Polytechnique de Paris, completing his doctoral work at CREST and defending his thesis at ENSAE Paris in June 2023. His research interests emphasize grouped fixed effects models, binary choice models, and computational methods for handling unobserved heterogeneity. Key contributions include developing estimators for nonlinear panel models and advancing techniques for discretizing time-varying effects. Mugnier collaborates actively with scholars like Laurent Davezies, Xavier D'Haultfœuille, and Ao Wang on foundational econometric problems. His publications appear in leading journals such as the Journal of Econometrics and Quantitative Economics. He develops open-source implementations of his methods, including Python packages like nlmfe and BinLogitCMLE for conditional maximum likelihood estimation. His work bridges theoretical econometrics with practical computation, addressing challenges in modern high-dimensional data analysis.

Hongmei Jiangمشاهده پروفایل

استاد

• High-throughput genomic analysis
• Metagenomic data analysis
• Microbiome data normalization
• +۵ مورد دیگر

Hongmei Jiang is a Professor of Statistics and Data Science and the MS Program Director in the Department of Statistics and Data Science at Northwestern University's Weinberg College of Arts & Sciences. She holds a Ph.D. from Purdue University (2004). Her research focuses on statistical methodologies for genomic and metagenomic data analysis, including microbiome normalization, multiple comparisons, survival analysis, and precision medicine applications. She has contributed significantly to understanding microbial community dynamics and their implications in health and disease. Her work spans bioinformatics, epigenetics, and clinical statistics, with recent publications addressing microbiome data imputation, primate gut microbiota's role in metabolism, and cardiovascular disease risk prediction using neural networks. She has collaborated on studies involving epigenetic aging, HIV/HPV interactions in carcinogenesis, and forensic microbial source tracking. Dr. Jiang's methodological innovations include novel statistical frameworks for differential abundance testing, quasi-likelihood models for microbiome data, and graphical lasso extensions for omics network analysis. Her research emphasizes interdisciplinary applications across biology, medicine, and ecology, leveraging both frequentist and machine learning approaches. Education: Ph.D. in Statistics, Purdue University, 2004 Affiliations: Department of Statistics and Data Science, Northwestern University Labs/Teams: MS Program Leadership, Metagenomic Data Analysis Group

Thomas Severiniمشاهده پروفایل

استاد

• Likelihood-Based Methods
• Higher-Order Asymptotic Approximations
• Statistical Methodology in Finance
• +۳ مورد دیگر

Thomas Severini is a Professor of Statistics and Data Science at Northwestern University's Weinberg College of Arts & Sciences. He holds a Ph.D. from the University of Chicago (1987). His research focuses on likelihood-based statistical methods, including higher-order asymptotic approximations and applications in finance, econometrics, and sports analytics. He has authored influential works such as Introduction to Statistical Methods for Financial Models (2017) and Analytic Methods in Sports (2014). Key research interests include: (1) Development of statistical methodology for complex models, (2) Application of likelihood-based techniques in finance/econometrics, (3) Analysis of sports performance data. Notable contributions include work on integrated likelihood functions and jet lag effects on MLB performance. Publications span top journals like Biometrika , Journal of Econometrics , and Proceedings of the National Academy of Sciences . His work bridges theoretical statistics with practical applications in diverse domains.

Venugopal Veeravalliمشاهده پروفایل

استاد

• Signal Processing
• Machine Learning
• Statistical Inference
• +۶ مورد دیگر

Venugopal Veeravalli is a Professor in the Department of Statistics at the University of Illinois at Urbana-Champaign, with affiliations in Electrical and Computer Engineering, the Information Trust Institute, and the Coordinated Science Lab. He holds the Henry Magnuski Professorship in Electrical and Computer Engineering. His work bridges statistical signal processing, machine learning, and distributed systems. Research interests focus on quickest change detection , reinforcement learning , multi-armed bandits , sensor networks , and robust learning . His recent work addresses challenges in non-stationary environments, adversarial attacks, and distributed algorithms for dynamic systems. Key contributions include adaptive algorithms for anomaly detection, optimal resource allocation in networks, and theoretical foundations of robust learning. He collaborates across disciplines to advance applications in security, communications, and IoT systems. Publications emphasize methodological innovations with applications to real-world problems like network monitoring and distributed decision-making. Current projects explore resilient algorithms for adversarial scenarios and scalable solutions for high-dimensional data analysis.

Yun Yangمشاهده پروفایل

دانشیار

• Machine Learning
• Bayesian Inference
• High-Dimensional Statistics
• +۴ مورد دیگر

Yun Yang is an Associate Professor in the Department of Mathematics at the University of Maryland, College Park . Previously, he held positions as Associate Professor (2022–2022) and Assistant Professor (2018–2022) at the University of Illinois at Urbana-Champaign, and Assistant Professor at Florida State University (2016–2018). He earned a B.S. in Mathematics from Tsinghua University (2011) and a Ph.D. in Statistics from Duke University (2014). His research focuses on Bayesian inference , high-dimensional statistics , machine learning , and optimal transport . Recent work emphasizes applying optimal transport and Wasserstein gradient flows to statistical problems, including regression, clustering, and generative modeling. He also investigates algorithmic scalability and theoretical guarantees for modern statistical methods. Key contributions include advancements in diffusion models for manifold structures, minimax-optimal distribution estimation, and Bayesian model selection via variational approximations. His work bridges theoretical foundations with practical applications in data science and optimization. Service roles include Associate Editorships at Bayesian Analysis (2025–present) and Journal of Computational and Graphical Statistics (2023–present), and Area Chair for AISTATS (2022–present).

Oksana Chkrebtiiمشاهده پروفایل

دانشیار

• Bayesian Statistics
• Uncertainty Quantification
• Functional Data Analysis
• +۴ مورد دیگر

Oksana Chkrebtii is an Associate Professor in the Department of Statistics at The Ohio State University's College of Arts and Sciences, with courtesy appointments in Materials Science Engineering and affiliation with the HAMMER ERC. She holds a PhD from Simon Fraser University (2014) and specializes in Bayesian statistics, uncertainty quantification, and spatio-temporal modeling. Her research addresses inferential challenges in systems governed by differential equations, with applications ranging from invasive species dynamics to epidemic modeling. Her primary research areas include: Bayesian uncertainty quantification for differential equation models Functional data analysis under sparse sampling regimes Spatio-temporal statistics for environmental and biological systems Probabilistic numerical methods for inverse problems Her publication portfolio demonstrates consistent focus on developing Bayesian methodologies for complex dynamical systems, with recent emphasis on likelihood-free inference, functional data registration, and applications in climate science and epidemiology. Articles frequently integrate computational statistics with domain-specific challenges in oceanography, materials science, and public health. Dr. Chkrebtii actively mentors graduate students, including recent advisees Jake Roberts (MS) and Rui Zhang (PhD), and collaborates with NASA and NSF-funded projects. She leads the Digital Twins research group at Ohio State and serves as Associate Editor for the SIAM/ASA Journal of Uncertainty Quantification.

Radu Herbeiمشاهده پروفایل

استاد

• Statistical Inference for Stochastic Processes
• Monte Carlo and MCMC Methods
• Inverse Problems
• +۳ مورد دیگر

Radu Herbei is a Professor of Statistics at The Ohio State University, affiliated with the Department of Statistics. He joined the faculty in 2006 and has been funded by NSF and ONR. His research focuses on statistical inference for stochastic processes, including stochastic differential equations and stochastic partial differential equations, with an emphasis on 'exact' inference methods that avoid user-selected grids or approximations. He develops exact Markov chain Monte Carlo (MCMC) techniques using approximations of intractable probability density functions and explores high-performance GPU computing to address computational challenges. His education includes a PhD in Statistics from Florida State University (2006). Research areas include Bayesian statistics, Monte Carlo methods, inverse problems, and uncertainty quantification. Notable contributions include work on the Bernoulli factory algorithm for exact Bernoulli random variates and applications in phylogenetics and environmental modeling. Collaborations span computational biology, oceanography, and ecological systems. Key publications include developments in taxicab MCMC samplers for discrete spaces, Bayesian function registration, and statistical inference for stochastic differential equations. His work bridges theoretical advancements with computational tools, addressing complex modeling challenges in diverse scientific domains.

Jaehan Baeمشاهده پروفایل

استادیار

• Planet Formation
• Protoplanetary Disks
• Hydrodynamic Simulations
• +۵ مورد دیگر

Jaehan Bae is an Assistant Professor in the Department of Astronomy at the University of Florida. His research focuses on understanding planet formation through numerical simulations and observational studies of protoplanetary disks using facilities like ALMA. He holds a Ph.D. from the University of Michigan (2017) and prior degrees from Seoul National University (B.S. 2006, M.S. 2008). Education: Ph.D., University of Michigan, 2017 M.S., Seoul National University, 2008 B.S., Seoul National University, 2006 Research Interests: Bae investigates planet-disk interactions, hydrodynamic instabilities, and gas dynamics in protoplanetary disks. His work integrates observations (e.g., ALMA), simulations, and machine learning to uncover planet formation mechanisms. Key areas include disk evolution, gap opening, and embedded planet detection through substructures like spiral arms and asymmetries. Grants & Advising: No specific grant details or students are listed. His research is supported through observational projects like exoALMA and theoretical collaborations.

Leo Duanمشاهده پروفایل

دانشیار

• Statistical Methodology
• Bayesian Statistics
• Combinatorial Optimization
• +۳ مورد دیگر

Leo Duan is an Associate Professor with Tenure in the Department of Statistics at the University of Florida since 2018. His research focuses on developing statistical methods, computational tools, and Bayesian frameworks to address challenges in neuroscience, engineering, and transportation science. He specializes in combinatorial structures like tree graphs, clustering, and signal pathways, integrating optimization and probabilistic techniques. Dr. Duan’s recent work includes advancements in Bayesian inference using optimization, such as bridged posteriors and gradient-based methods. He co-teaches a short course on optimization in Bayesian inference at JSM 2025. His funded projects include NSF-ATD grants for geospatial modeling and hurricane risk mitigation, alongside other institutional awards. His advising spans doctoral students in optimization and diffusion models. Past trainees include Edric Tam (Stanford Postdoc) and Maoran Xu (Indiana University faculty). Current students Zeyu Yuwen and Yu Zheng are nearing graduation. Dr. Duan’s lab actively recruits new graduate researchers. Key achievements include the 2018 NeurIPS Bayesian Non-parametrics Award and a series of high-impact publications in JASA, JMLR, and Biometrika. His research bridges theory and application, with contributions to spanning trees, graphical models, and Bayesian vector autoregression.