Professor Qihao Weng is Chair Professor of Geomatics and Artificial Intelligence at The Hong Kong Polytechnic University, where he leads the Research Institute for Land and Space. A globally recognized scholar, he bridges geography, landscape ecology, and environmental science through innovative geospatial analytics, GeoAI, and big data methodologies. His work focuses on urban climatology, sustainability science, and human-environment interactions, with over 279 publications and 14 books. PhD, The University of Georgia MA, The University of Arizona MS, South China Normal University Professor Weng's research explores remote sensing applications for urban environmental challenges, including thermal comfort, heat islands, and land-use changes. He pioneered global-scale urban observation via the Group on Earth Observation (GEO) initiative and developed frameworks integrating geospatial technology with climate resilience strategies. Recent publications highlight advancements in GeoAI for urban thermal stress assessment, road extraction algorithms, and multi-temporal data fusion techniques. His work spans interdisciplinary domains, connecting remote sensing, urban science, and sustainability metrics across diverse climate zones. NASA Senior Fellowship (2008) Taylor & Francis Lifetime Achievements Award (2019) AAG Wilbanks Prize (2024) Lifetime Achievement in Remote Sensing Award (2024) Academia Europaea Foreign Member (2021) As Editor-in-Chief of the ISPRS Journal, Professor Weng has advanced global remote sensing discourse. His research has been supported by NSF, NASA, USAID, Microsoft, and Hong Kong Research Grant Council. He has delivered over 130 invited talks and established visiting professorships in Japan, France, and China.
Stefanie Jegelka is an Associate Professor (currently on leave) at the Massachusetts Institute of Technology's Department of Electrical Engineering and Computer Science, and a Humboldt Professor at Technical University of Munich. At MIT, she is a member of CSAIL (Computer Science and Artificial Intelligence Laboratory), IDSS (Institute for Data, Systems, and Society), the Center for Statistics and Machine Learning, and is affiliated with the Operations Research Center. Her educational background includes a PhD from ETH Zurich and the Max Planck Institute for Intelligent Systems, followed by postdoctoral research at UC Berkeley's AMPlab and computer vision group. Her research program focuses on algorithmic machine learning, with particular emphasis on exploiting mathematical structure for discrete and combinatorial machine learning problems, robustness in learning systems, and developing methods for scaling machine learning algorithms to large datasets. She has made significant theoretical contributions to submodular optimization and its applications in machine learning. Jegelka's publication record demonstrates a consistent focus on the intersection of discrete mathematics and machine learning. Her work spans theoretical foundations of optimization with discrete structures, applications in computer vision, and practical algorithms for submodular function optimization. Her research has evolved from foundational work on submodular functions to broader applications in deep learning and robust machine learning systems, showing increasing impact through numerous workshop best paper awards and high-impact conference publications. NSF CAREER Award Google Research Award German Pattern Recognition Award (Mustererkennngspreis) ICML Best Paper Award Sloan Research Fellowship DARPA Young Faculty Award NSF BIGDATA Award ONR MURI NSF AI Institute for Optimization Professor Jegelka has advised several successful students including Keyulu (recipient of MIT's George M. Sprowls Ph.D. Thesis Award), Derek (NSF Fellowship recipient), Ching-Yao (IBM Fellowship recipient), and Nisha (now Assistant Professor at Georgia Tech). Her research has been generously supported by multiple NSF grants, DARPA awards, and industry funding from Google, Two Sigma, and Adobe. She has also organized multiple workshops and tutorials on discrete optimization and submodularity in machine learning. At MIT, Jegelka is affiliated with the Center for Statistics and Machine Learning and collaborates with researchers across CSAIL. Her work bridges theoretical computer science, optimization, and practical machine learning applications, with recent focus on high-dimensional learning dynamics and in-context learning as evidenced by her group's multiple papers at leading conferences like ICLR.
Yading Yuan, PhD is an Associate Professor of Radiation Oncology (Physics) at Columbia University Irving Medical Center and a member of the Data Science Institute. He holds a PhD in medical physics from the University of Chicago (2010) and completed clinical residency at Harvard Medical Physics Program (2013). His research focuses on AI-driven innovations in radiation oncology, including automated medical image analysis systems, federated learning frameworks for tumor segmentation, and data-driven approaches to personalized cancer treatment. He is certified by the American Board of Radiology and licensed in New York State. Education: PhD in Medical Physics (University of Chicago, 2010); Clinical Residency (Harvard Medical Physics Program, 2013). Research interests include: automated knowledge-based treatment planning, large-scale clinical AI systems, medical image reconstruction algorithms, and panomics integration for precision oncology. His work emphasizes translating data science advancements into clinical practice to improve patient outcomes. Key trends in his publications include federated learning for privacy-preserving medical AI, tumor segmentation in multi-modal imaging (PET/CT, MRI), and AI-driven prediction of treatment outcomes and recurrence risks. Recent work emphasizes decentralized learning architectures and cross-institutional collaboration systems. Scientific Awards: Distinguished Reviewers 2013 (selected by peer review committees) Advising/grants: No specific student names or grant details listed in provided text. His work is supported through institutional and collaborative research initiatives. Labs/teams: Active member of Columbia's Data Science Institute and Radiation Oncology department, contributing to interdisciplinary medical AI research groups.
Chen Sun is an Assistant Professor of Computer Science at Brown University and a part-time Staff Research Scientist at Google DeepMind . His research bridges computer vision, machine learning, and artificial intelligence , focusing on multimodal representation learning, visual commonsense, and controllable video generation . He directs the PALM🌴 research lab , which explores scalable models for robotic planning, video understanding, and human activity recognition . Chen Sun earned a Ph.D. in Computer Science from the University of Southern California (2016) , advised by Professor Ram Nevatia , and a Bachelor of Science in Computer Science from Tsinghua University (2011) . His lab's work has been supported by Adobe, Honda, Meta, NASA, and Samsung , and he is affiliated with the NSF AI Research Institute on Interaction for AI Assistants . His research spans multimodal transformers, embodied agents, and physics-informed video generation . Key trends include Learning from unlabeled videos for human activity recognition Developing controllable generation techniques using motion trajectories and physics-based signals Advancing scalable frameworks for video-language tasks Scientific awards include the Brown University Richard B. Salomon Faculty Research Award and Samsung Global Research Outreach Award . He has served as Workshop Chair (CVPR 2025) , Action Editor (TMLR) , and Area Chair for top conferences like ICLR, CVPR, and NeurIPS . Chen Sun mentors a dynamic team including Ph.D. students Apoorv Khandelwal (Presidential Fellow) Calvin Luo (Research Mobility Fellow) Nate Gillman (Math Department) Shijie Wang Tian Yun (co-advised with Ellie Pavlick) Yuan Zang Zilai Zeng Zitian Tang and alumni now pursuing Ph.D. programs at Princeton, Cornell, UBC, and UNC . His teaching portfolio includes graduate-level courses on Deep Learning (CSCI 2470) , Advanced Topics in Deep Learning (CSCI 2952N) , and a short course on Multimodal Transformers at ICASSP 2022 and AAAI 2023 .
Thomas Walter is a Professor at Mines ParisTech and Director of the Centre for Computational Biology (CBIO) , a research group affiliated with the Institut Curie and INSERM . His work focuses on applying Machine Learning and Computer Vision to biomedical image analysis, particularly in high-content screening and computational pathology . He also serves as Deputy Director of the Computational Oncology (U1331) unit and leads the Statistical Learning and Modeling of Biological Systems team. PhD in Medical Image Analysis (2003, Mines ParisTech) Postdoctoral work at EMBL (European Molecular Biology Laboratory) Director of CBIO since 2018 Holder of a PRAIRIE Chair (Paris Artificial Intelligence Research Institute) since 2019 Dr. Walter's research bridges biomedical imaging , machine learning , and cancer genomics . Key areas include: Statistical reconstruction of biological networks Prediction of tumor progression at genomic/transcriptomic levels Development of deep learning methods for cell cycle analysis Integration of multi-omics data for precision oncology Tools for spatial transcriptomics (e.g., autoFISH, RNA2seg) Recent publications highlight his work in spatial transcriptomics , immunotherapy outcome prediction , and deep learning for digital pathology . His team has developed open-source tools like FISH-quant and pyHiM for single-molecule RNA imaging analysis. Scientific Honors: PRAIRIE Chair (2019) for AI research in life sciences Dr. Walter actively contributes to teaching deep learning for image analysis in multiple graduate programs across France, including courses at Mines ParisTech , Université Paris-Saclay , and Institut Curie . His software tools (FISH-quant, pyHiM) and methodological frameworks (e.g., Cut-Detector, PointFISH) have become standard resources in bioimage informatics.
Abhinav Shrivastava is an Associate Professor in the Department of Computer Science at University of Maryland, College Park, with a joint appointment in the Institute of Advanced Computer Studies (UMIACS). Previously, he served as an Assistant Professor at the same institution from August 2018 to June 2024, and spent one year as a Visiting Research Scientist at Google Research from September 2017 to August 2018. His educational background includes: PhD in Robotics and Artificial Intelligence from Carnegie Mellon University (2017), advised by Abhinav Gupta, with thesis titled 'Discovering and Leveraging Visual Structure for Large-scale Recognition' MS in Artificial Intelligence from Carnegie Mellon University (2011), supervised by Alyosha Efros and Martial Hebert BTech in Computer Science and Engineering from Jaypee Institute of Information Technology (2010) Professor Shrivastava's research focuses on computer vision and machine learning, with particular expertise in object detection, image recognition, and neural representations. His work bridges theoretical advances with practical applications, exploring how visual systems can discover and leverage structure in large-scale recognition problems. He has made significant contributions to understanding the role of supervision in vision transformers, developing novel approaches for object-state composition recognition, and creating efficient neural representations for videos and 3D scenes. His research often addresses fundamental challenges in visual recognition, including handling novelty in open-world environments and improving the efficiency of visual systems. An analysis of his recent publications reveals a strong emphasis on neural representations, particularly for dynamic content like videos and 3D scenes. His work demonstrates increasing sophistication in handling open-world vision problems, with research spanning object discovery, localization, and representation learning. The publications show a clear progression toward more efficient and scalable models, with recent work focusing on model compression, sparse representations, and addressing the challenges of working with limited annotations. His scientific contributions have been recognized with several prestigious awards: Best Paper Award (Applications) at IEEE Winter Conference on Applications of Computer Vision (2020) Microsoft Research PhD Fellowship (2014-2016) Best Student Paper Award at IEEE Winter Conference on Applications of Computer Vision (2014) Outstanding Reviewer Award at IEEE CVPR (2015) Professor Shrivastava has successfully mentored numerous graduate students, many of whom have become prominent researchers in computer vision. His Amazon Research Awards (2020 and 2023) have supported innovative projects including 'The pursuit of knowledge: discovering and localizing new concepts using dual memory' and 'Audio-conditioned Diffusion Models for Generating Lip-synchronized Videos.' He has served as Area Chair for major conferences including ICCV, CVPR, and AAAI, demonstrating his leadership in the computer vision community. His research has attracted significant funding from both academic and industry sources, supporting his exploration of fundamental questions in visual recognition and representation learning.
Nezihe Merve Gürel is an Assistant Professor in Computer Science at Delft University of Technology (TU Delft), affiliated with the Pattern Recognition & Bioinformatics Group within the Intelligent Systems Department of the Faculty of Electrical Engineering, Mathematics and Computer Science. Her research focuses on developing robust, reliable, and efficient machine learning methods with enhanced reasoning capabilities, bridging theoretical rigor and practical applications. She emphasizes data-centric approaches to improve ML systems. Education: PhD in Computer Science from ETH Zurich, MSc from EPFL (Switzerland). Research Interests: ML robustness, reliability, reasoning, data-centric ML, federated learning, and explainable AI. Her recent work includes certified robustness for retrieval-augmented models and time-efficient learning algorithms. She has contributed to the Journal of Data-centric Machine Learning Research as an executive editor and served as a reviewer for top ML conferences (NeurIPS, ICML, ICLR). She previously held roles at IBM Research, Stanford University's Human-Centered AI Lab, and Westlake Institute for Advanced Study. Her awards include the Generation Google Scholarship and Cisco Research Funding . Scientific Awards : Generation Google Scholarship (2021) Cisco Research Center University Funding Labs & Teams : She leads research in the Pattern Recognition Laboratory at TU Delft and collaborates with international institutions like Stanford and Westlake Institute for Advanced Study.
Stefano Grivet-Talocia is a Full Professor at the Department of Electronics and Telecommunications at the Polytechnic University of Turin, where he also serves as Director of the Doctoral School and President of the Doctoral School Council. He is a member of the Interdepartmental Center SmartData@PoliTO - Big Data and Data Science Laboratory, the University Committee for Research, Technology Transfer and Services to the Territory, and the Commission for the Promotion of Library, Archive and Museum Heritage. His academic career spans over two decades at Politecnico di Torino, where he has established himself as a leading researcher in electromagnetic modeling and signal integrity. Grivet-Talocia earned his Laurea degree (summa cum laude) in Electronic Engineering in 1994 and his Ph.D. in Electronic and Communication Engineering in 1998, both from the Polytechnic University of Turin. Between 1994 and 1996, he conducted research at NASA/Goddard Space Flight Center in Greenbelt, Maryland. His educational background laid the foundation for his expertise in electromagnetic modeling, wavelet analysis, and signal processing. His research focuses on behavioral modeling, electromagnetic compatibility, macromodeling, model order reduction, numerical modeling, passivity, power integrity, signal integrity, transmission lines, and wavelets . Grivet-Talocia is particularly renowned for his work on passive macromodeling of interconnect structures, development of the TOPLine technique for transmission line simulation, and pioneering contributions to passivity enforcement algorithms. He has co-authored the first book entirely dedicated to Macromodeling (2016) and developed innovative approaches to waveform relaxation and wavelet-based signal processing. His recent publications (2024-2025) demonstrate continued leadership in model order reduction, with significant contributions to data-driven modeling of linear and nonlinear systems, power integrity analysis, and electromagnetic compatibility. His work spans both theoretical advances in numerical methods and practical applications in circuit design, with strong industry relevance particularly for semiconductor and electronic design automation companies. IEEE Fellow (2018-present) Three Intel SRS Grants (2022-2024) Three IBM SUR Grant Awards (2007-2009) Best Associate Editor Award - IEEE Transactions on Components, Packaging and Manufacturing Technology (2020) Multiple Best Conference Paper Awards (2006-2020) URSI Young Scientist Awards (1999) Ranked among the "top 2% worldwide researchers" (Stanford) since 2019 Grivet-Talocia actively supervises doctoral students including Michele Cusano, Sara Paknezhad Panahi, Antonio Carlucci, and Kun Zhao. He has secured numerous research grants from competitive national calls (PRIN) and commercial contracts with industry partners including Intel, IBM, Nokia, Hitachi, Infineon, and Cadence. His technology transfer activities include co-founding the spin-off IdemWorks (2007-2016), which was acquired by CST in 2016. He also developed the autoCircuits web service for automated circuit problem generation, widely used in electrical engineering education. He leads the EMC Group (Electromagnetic Compatibility) at DET and has been instrumental in establishing the Compact Dynamical Modeling research area. His work has practical applications in high-speed electronics design, with algorithms embedded in commercial tools like IBM PowerSPICE. Grivet-Talocia maintains strong industry connections through his research projects and serves as Associate Editor for IEEE Transactions on Components, Packaging and Manufacturing Technology.
Byron Boots is the Amazon Professor of Machine Learning in the Paul G. Allen School of Computer Science and Engineering at the University of Washington, where he directs the UW Robot Learning Laboratory. He also serves as a Principal Research Scientist in the Seattle Robotics Lab at NVIDIA Research and co-chairs the IEEE Robotics and Automation Society Technical Committee on Robot Learning. Dr. Boots received his Ph.D. from the Machine Learning Department in the School of Computer Science at Carnegie Mellon University, where he was a member of the Sense, Learn, Act (SELECT) Lab co-directed by Carlos Guestrin and his advisor Geoff Gordon. Prior to joining the University of Washington faculty, he was an Assistant Professor in the School of Interactive Computing within the College of Computing at Georgia Tech, and before that, he completed a post-doc in the Robotics and State Estimation Lab directed by Dieter Fox at the University of Washington. Professor Boots' research focuses on the intersection of machine learning, artificial intelligence, and robotics, with particular emphasis on developing theory and systems that tightly integrate perception, learning, and control. His work spans computer vision, state estimation, localization and mapping, high-speed navigation, motion planning, and robotic manipulation. His group develops algorithms drawing from deep learning and neural networks, nonparametric statistics, graphical models, nonconvex optimization, quantum physics, online learning, reinforcement learning, and optimal control. The research demonstrates a strong theoretical foundation while maintaining practical relevance to real-world robotic systems. His recent publications reveal a clear trend toward integrating advanced machine learning techniques with robotics, particularly in model predictive control, motion planning, and learning-based approaches to robot control. His work shows increasing focus on developing theoretically grounded methods that can handle the complex, nonlinear dynamics of real-world robotic systems while maintaining computational efficiency. The publications span top venues including ICRA, CoRL, IROS, and NeurIPS, demonstrating broad impact across multiple subfields of robotics and AI. Finalist for Best Systems Paper at Conference on Robot Learning (CoRL-2021) Multiple papers selected for oral presentations at top robotics conferences Work recognized for theoretical contributions and practical applications in robot learning As director of the UW Robot Learning Laboratory, Boots leads a vibrant research group focused on fundamental and applied research in robot learning. The lab maintains strong collaborations with NVIDIA Research and has produced numerous high-impact publications that bridge theory and practice. Professor Boots teaches courses in autonomous robotics, machine learning, and reinforcement learning, contributing to both undergraduate and graduate education at the University of Washington.
Dr. Daphné Chopard is a Researcher affiliated with the Professorship for Medical Data Science at ETH Zürich. Her work focuses on advancing medical data science through machine learning, clinical informatics, and multimodal learning applications in healthcare. She specializes in areas such as time-series analysis in critical care, generative models for medical data, and natural language processing for clinical texts. Her research emphasizes improving healthcare outcomes through innovative data-driven approaches, including projects like the SwissPedHealth pediatric data network and foundational work on multimodal variational autoencoders. Dr. Chopard’s contributions span clinical decision support systems, adverse event detection in trials, and acronym disambiguation in medical narratives. Her recent projects include studies on ventilation protocols in pediatric critical care and weakly-supervised learning applied to medical imaging datasets like MIMIC-CXR. She collaborates on initiatives to enhance representation learning in multimodal healthcare contexts, reflecting her commitment to bridging AI advancements with practical clinical applications.
Ina Fiterau Brostean is an Assistant Professor in the College of Information and Computer Sciences at the University of Massachusetts Amherst, where she leads the Information Fusion Lab. Previously, she was a Postdoctoral Fellow at Stanford University's Mobilize Center (2015–2018) and earned her PhD in Machine Learning from Carnegie Mellon University (2015). Her research focuses on hybrid systems for multimodal data integration, particularly in healthcare, aiming to develop predictive models for clinical outcomes using time series, text, and images. Key areas include disease trajectory modeling, weakly-supervised transfer learning, and adaptive representation learning. Education: PhD in Machine Learning (Carnegie Mellon, 2015), MSc in Machine Learning (Carnegie Mellon, 2012), BEng in Computer Engineering (Politehnica Timisoara, Romania, 2009). Professional roles include teaching COMPSCI 651 (Optimization in Computer Science) and organizing NeurIPS workshops on Machine Learning in Healthcare. Research interests span machine learning methodologies for healthcare applications, including interpretable models, time series analysis, and dimensionality reduction. Notable achievements include the Marr Prize (ICCV 2015) and Star Research Award (SCCM 2016). Her lab collaborates on projects like predicting Alzheimer's disease progression and surgical outcomes using Bayesian networks and deep learning. Awards and recognitions include Rising Stars Workshop (2016), Manning IALS Research Award (2019), and GE Foundation Scholar Leader Award (2007). She actively contributes to the ML4Health community through leadership roles and workshop organization.
Yu Meng is an Assistant Professor in the Department of Computer Science at the University of Virginia (UVA), part of the School of Engineering and Applied Science. He joined UVA in 2024 as a tenure-track faculty member. His research focuses on machine learning, natural language processing (NLP), and data mining, with recent emphasis on large language models (LLMs), alignment, reliability, and ethical AI development. Educated at the University of Illinois Urbana-Champaign (UIUC), Meng earned his Ph.D. in 2023 under advisor Jiawei Han. His doctoral thesis, Efficient and Effective Learning of Text Representations , received the ACM SIGKDD 2024 Dissertation Award. He also held a visiting researcher position at Princeton University under Danqi Chen and was a Google PhD Fellow. His work has been recognized with awards including the Superalignment Fast Grant from OpenAI and notable publications at venues like NeurIPS, ICLR, and ACL. Meng’s research explores topics such as preference optimization (SimPO), retrieval-augmented generation (InstructRAG), and zero-shot learning. He actively serves on program committees for top conferences (ICLR, ICML, NeurIPS) and as an action editor for Transactions of Machine Learning Research (TMLR) . He teaches graduate-level courses on NLP, emphasizing cutting-edge LLM topics like architecture design, instruction tuning, and ethical considerations. Key achievements include contributions to LLM alignment via retrieval optimization, efficient pretraining techniques, and foundational work on weakly supervised learning. His research bridges theory and practice, addressing both technical challenges and societal impacts of AI systems.
Professor Daniel Catchpoole serves as Deputy Head of School (Research) at the School of Computer Science, University of Technology Sydney (UTS), holding dual appointments at UTS and The Children's Hospital at Westmead. With over 20 years of research experience, he bridges computational sciences and pediatric cancer research through the Biomedical Data Science Lab in the Australian Artificial Intelligence Institute. His work integrates data analytics, artificial intelligence, and software development with molecular cancer biology to transform pediatric cancer treatment pathways. PhD in Cancer Cell Biology, University of New South Wales (1991-1995) Founding Fellow, Royal College of Pathologists Australasia (2010-present) Head, Children's Hospital at Westmead Tumour Bank (2001-present) Professor Catchpoole's research focuses on translational applications of genomics in childhood cancers, particularly acute lymphoblastic leukemia and neuroblastoma. His work combines high-throughput genomic technologies with advanced computational analysis to develop systems biology approaches for cancer patient assessment. Recent projects explore virtual reality applications for complex genomic data visualization and copper chelation therapies to enhance neuroblastoma immunotherapy. His research has received significant funding from Cancer Institute NSW, Sony Foundation, ARC, and NHMRC. His publication record spans biomedical data science, cancer genomics, and virtual reality applications in oncology. Recent work demonstrates leadership in 3D latent diffusion models for tumor segmentation, biobank economics, and innovative immunotherapies. His research consistently addresses the critical need for actionable knowledge from complex multidimensional biomedical data. Editorial Board Member, Cancers (2023) Associate Editor, Innovations in Digital Health, Diagnostics and Biomarkers (2019) Founding member and first President, Australasian Biospecimens Network Association Professor Catchpoole has supervised 17 Honours students (including 6 First Class Honours), 3 MSc students, and 12 PhD candidates across multiple institutions, with 6 current PhD students. His collaborative research bridges UTS's Faculty of Engineering and IT with The Children's Cancer Research Unit at The Children's Hospital at Westmead. Significant research funding includes Cancer Institute NSW grants, Sony Foundation VR projects, and ARC Discovery Projects focused on genomic data analysis and clinical decision support systems. His leadership extends to building frameworks for translational research, managing biobanks and clinical data linkages, and navigating governance requirements for cancer research. The Tumour Bank at Kids Research, CCRU, represents his long-standing commitment to pediatric cancer infrastructure development.
Ario Sadafi is a researcher at the Technical University of Munich (TUM) , affiliated with the Chair of Computer Science Applications in Medicine under Prof. Nassir Navab. His work spans medical image analysis , machine learning , and computational pathology , with a strong focus on developing AI-driven solutions for microscopic imaging in hematology and oncology. Research Focus: Multiple Instance Learning for weakly supervised medical image classification. Explainable AI for biomedical single-cell imaging. Continual and cross-domain learning for robust diagnostic models. Microscopic image analysis for blood cell disorders and leukemia subtyping. Teaching Contributions: Sadafi has been actively involved in teaching courses such as Computer Aided Medical Procedures , Medical Augmented Reality , and Deep Learning for Medical Applications . He also supervises practical courses and seminars in 3D Computer Vision and Machine Learning in Medical Imaging . Labs & Collaborations: He works closely with the MEDIA (Medical Image Analysis) and NARVIS labs at TUM, contributing to projects in surgical data science , generative models , and robotics & ultrasound . Publications Impact: His research output (2018–2025) emphasizes AI-driven hematology , with applications in red/white blood cell classification, leukemia subtype diagnosis, and interpretable deep learning models for clinical use.
Dr Vu Minh Hieu Phan is a Research Fellow at the Australian Institute for Machine Learning , University of Adelaide. His work focuses on foundational models, multimodal learning, and medical image analysis, leveraging deep learning and large language models. Research Interests : Medical Image Analysis, Vision-Language Models, Generative AI, Semantic Segmentation, Continual Learning, Knowledge Distillation. Key Venues : CVPR, ACL, EMNLP, IJCAI, MICCAI, NeurIPS, TPAMI, and IJCV. Notable Contributions include advancements in multimodal learning for medical imaging, explainable AI frameworks, and efficient knowledge distillation techniques. He serves as a reviewer for top-tier journals and conferences. Email : vu.minhhieu.phan@adelaide.edu.au
