جست‌وجوی استاد و پژوهشگر

• Scientific Computing
• Numerical Linear Algebra
• Parallel Computing
• +۳ مورد دیگر

Michael T. Heath is a Professor and Fulton Watson Copp Chair Emeritus in the Department of Computer Science at the University of Illinois at Urbana-Champaign (UIUC). He holds a Ph.D. in Computer Science from Stanford University (1978). His research focuses on scientific computing, numerical linear algebra, optimization, and parallel computing with notable contributions to sparse matrix computations and parallel algorithm design. Heath has directed major initiatives such as the Computational Science and Engineering Program (1996–2012) and the Center for Simulation of Advanced Rockets (1997–2010), securing over $52M in research funding. He is an ACM Fellow, SIAM Fellow, and European Academy of Sciences member. Teaching excellence defines his career, highlighted by awards including the IEEE Taylor L. Booth Education Award (2009) and UIUC's Campus Award for Excellence in Graduate Teaching (2002). He developed interactive educational modules in scientific computing and teaches courses like CS 450 (Numerical Analysis) and CS 554 (Parallel Numerical Algorithms). His research spans parallel performance visualization, numerical optimization, and mathematical software, with over 50 years of contributions to computational science. Education: Ph.D. Computer Science, Stanford University (1978) Affiliations: Department of Computer Science, UIUC; former Interim Head (2007–2009) Key Roles: Director, Computational Science and Engineering Program; Director, Center for Simulation of Advanced Rockets His publications emphasize parallel algorithms, numerical methods, and computational frameworks for multiphysics simulations. Heath’s work bridges academic research and practical applications, exemplified by his leadership in high-performance computing and rocket propulsion modeling.

Jun Liuمشاهده پروفایل

استاد

• Computer Vision
• Machine Learning
• Digital Health
• +۳ مورد دیگر

Jun Liu is a Professor and Chair of Digital Health at Lancaster University's School of Computing and Communications. He holds a PhD from Nanyang Technological University (NTU), an MSc from Fudan University, and a BEng from Central South University. His research focuses on computer vision, machine learning, and digital health, with notable contributions to image segmentation, AI security, and multimodal learning. He leads the VL Group (https://wp.lancs.ac.uk/vl/) and supervises 5 postgraduate students. Education: PhD (NTU), MSc (Fudan), BEng (Central South University). Research Interests: His work spans AI-driven healthcare solutions, adversarial defense in vision-language models, and advanced computer vision techniques. He has pioneered methods like LLaFS++ for few-shot image segmentation and developed frameworks to combat jailbreak attacks in large models. Publications: Over 123 peer-reviewed articles, including high-impact work in IEEE Transactions and ACM journals. Recent trends focus on AI-generated content analysis, robust model security, and cross-modal learning. Awards: Best Paper Awards (PREMIA 2016/2019), IEEE VSPC Rising Star (2024), Stanford Top 2% Scientists. Editorial Roles: Senior Area Editor (IEEE T-IP), Associate Editor (IEEE T-CASVT, ACM Computing Surveys). Grants: Principal Investigator for the 'Unrestricted Gift' project (2025-2028). Labs/Teams: Leads the Vision & Learning (VL) research group, collaborating on digital health innovations and AI ethics challenges.

• Information Network Analytics
• Decentralized Machine Learning
• Data Mining
• +۵ مورد دیگر

Sarunas Girdzijauskas is a Professor at the Department of Computer Science within KTH Royal Institute of Technology's School of Electrical Engineering and Computer Science (EECS), where he leads the Graph Analytics and Network Learning group (GALE) . He also holds a Senior Researcher position at RISE (Research Institutes of Sweden) and has served as Program Director for EECS's doctoral program in Information and Communication Technology (2019-2022) and Deputy Director of Third-Cycle Education at EECS. PhD from Ecole Polytechnique Fédérale de Lausanne (EPFL) in 2016 Docent in Computer Science at KTH (2016) Coordinated multiple large-scale projects: H2020 Marie Curie RAIS, Marie Curie ITN iSocial Research Focus : His work spans decentralized machine learning systems, graph analytics, and blockchain infrastructure. Key areas include: Information network analysis for social and technical systems Federated learning with adaptive personalization Graph partitioning and distributed algorithms Privacy-preserving models with differential privacy Knowledge distillation for evolving graph representations Scalable solutions for big data and IoT botnet detection Article Trends : Recent work demonstrates convergence of graph neural networks with federated learning, emphasizing privacy (differential privacy in 5/15 articles), robustness (out-of-distribution detection in 3 articles), and decentralized infrastructure (blockchain, gossip protocols, and P2P overlays). The articles frequently address temporal modeling, knowledge distillation, and heterogeneous graph representations. Scientific Leadership : Coordinated H2020 Marie Curie European Training Network 'RAIS' (2018-2023) Coordinated Marie Curie ITN 'iSocial' (2012-2017) Activity Leader for EIT Digital Innovation Activities Teaching & Advising : Has supervised/examined over 60 master theses and currently advises 8 PhD students, including Adam Orucu (Main Supervisor, 2024-), Filip Cornell (Main Supervisor, 2020-), and Ahmed Emad Samy Youssif (Main Supervisor, 2019-). Former supervisees include 9 PhDs like Dr. Edvin Listo Zec (2025) and Dr. Debaditya Roy (2024).

• Artificial Intelligence in Healthcare
• Medical Imaging
• Dermatology
• +۳ مورد دیگر

Ludovic Amruthalingam is a Lecturer and Senior Researcher at the Lucerne School of Computer Science and Information Technology, Lucerne University of Applied Sciences, Switzerland. He holds a PhD in Artificial Intelligence from the University of Basel, a Master of Science in Computer Science from ETH Zürich, and a Bachelor of Science in Computer Science from EPFL. His professional activities include co-founding the startup Intelligent Orthopaedics in Chennai, India (2017–present), and leading research projects such as the Health Innovation Transfer Study (HIT) , Derma consultation documentation with AI , and the HSLU Medtech Joint Venture . His work focuses on leveraging AI for medical applications, particularly in dermatology, teledermatology, and medtech innovation. Research interests include medical anomaly detection, self-supervised learning, hyperbolic neural networks, and overcoming data scarcity in healthcare. He has pioneered projects addressing skin condition analysis, automated anatomical mapping, and diversity-inclusive medical imaging datasets. His recent publications highlight advancements in AI for dermatological diagnosis (e.g., vulvar lichen sclerosus pilot studies), hyperbolic space applications for medical anomalies, and benchmarking frameworks for image data cleaning (e.g., CleanPatrick ). He also contributes to foundational AI tools for scalable digital dermatology and equitable healthcare access through global skin imaging initiatives. Ludovic’s work bridges academic research and industry, driving innovations in medtech through collaborations like the ABIZ MedTech Expansion and Counteracting Data Scarcity in MedTech projects. His research emphasizes clinical translation of AI systems for real-world healthcare challenges.

• Riemann Surfaces
• Teichmüller Theory
• Weil-Petersson Geometry
• +۵ مورد دیگر

Scott A. Wolpert is a Professor in the Mathematics Department at the University of Maryland, where he holds the distinguished title of Distinguished Scholar-Teacher. His academic career has been primarily focused on geometric analysis and complex geometry, with significant contributions to the understanding of Riemann surfaces and their moduli spaces. Wolpert's research centers on the intricate geometry of Riemann surfaces, particularly through the lens of Fuchsian groups, hyperbolic geometry, and Teichmüller theory. His work has significantly advanced our understanding of the Weil-Petersson geometry for Teichmüller space, including curvature properties, convexity, and the behavior of geodesics near the completion locus. He has also made important contributions to spectral theory of Riemann surfaces, exploring questions related to isospectrality ("Can you hear the shape of the drum?") and the nature of high-energy eigenfunctions. Analysis of his publication record reveals a consistent focus on the geometry of moduli spaces of Riemann surfaces, with particular emphasis on Weil-Petersson geometry. His work spans both theoretical developments and concrete calculations, often connecting differential geometry with complex analysis, topology, and mathematical physics. Over time, his research has evolved from foundational work on the symplectic geometry of deformations to more recent investigations of curvature properties and asymptotic behavior in degenerating families of Riemann surfaces. Among his notable achievements is being named a Distinguished Scholar-Teacher at the University of Maryland, recognizing his excellence in both research and teaching. Professor Wolpert has been actively involved in the mathematical community through organizing workshops and conferences, including the NSF CBMS Conference on Families of Riemann Surfaces and Weil-Petersson Geometry at Central Connecticut State University in 2009, and the Workshop on Dynamics of the Weil-Petersson geodesic flow at the American Institute of Mathematics in 2012. His collaborations include work with Carolyn Gordon and David Webb on isospectral domains, and his research has influenced prominent mathematicians including Maryam Mirzakhani and Jeff Brock.

Michael Strubeمشاهده پروفایل

استاد

• Natural Language Processing
• Computational Linguistics
• Semantics and Discourse Pragmatics
• +۷ مورد دیگر

Michael Strube is an Honorary Professor at the Department of Computational Linguistics at Heidelberg University and leads the Natural Language Processing (NLP) Group at HITS (Heidelberg Institute for Theoretical Studies) in Germany. He has been with HITS (previously EML Research and European Media Laboratory) since 2003 and became an Honorary Professor at Heidelberg University in 2010. He is also a Fellow of the Association for Computational Linguistics (2019). Dr. Strube received his PhD from the Computational Linguistics Department at the University of Freiburg in December 1996 under the supervision of Udo Hahn. Between 1997 and 1999, he was a postdoctoral fellow at the Institute for Research in Cognitive Science at the University of Pennsylvania, Philadelphia. Michael Strube's research focuses on semantics and discourse pragmatics, graph-based methods for text representation and analysis, extraction of world knowledge from Wikipedia for computational linguistics, and development of methods to synchronize multilingual content. His work spans coreference resolution, discourse processing, text summarization, entity linking, and natural language generation. He has made significant contributions to coherence modeling, anaphora resolution, and the application of geometric deep learning in NLP. His recent publications demonstrate strong trends in discourse processing, coreference resolution, and the application of geometric approaches to NLP problems. Strube has pioneered work in hyperbolic space for entity typing and graph embeddings, while maintaining his foundational work in discourse and coherence. His research bridges theoretical linguistics with practical NLP applications across multiple languages. Dr. Strube has received several prestigious awards, including: Fellow of the Association for Computational Linguistics (2019) Best Paper Award for "Fine-grained entity typing in hyperbolic space" (2019) Honorable Mention for the IJCAI-JAIR best paper prize 2010 for "Knowledge Derived from Wikipedia for Computing Semantic Relatedness" Professor Strube has advised numerous PhD students who have gone on to successful careers in academia and industry. His current PhD students include Yi Fan, Wei Liu, Haixia Chai, Mehwish Fatima, and Sungho Jeon, working on topics such as discourse structure, discourse relations, coreference resolution, and cross-lingual summarization. His former students include Federico Lopez, Benjamin Heinzerling, Mohsen Mesgar, and Nafise Moosavi, who now hold positions at institutions like Argo AI, RIKEN, Bosch Center for AI, and the University of Sheffield. As group leader of the NLP Group at HITS, Strube oversees a team focused on advancing natural language processing through research in discourse analysis, coreference resolution, text generation, and knowledge extraction. The group has been involved in numerous collaborative projects and has made significant contributions to the field through publications, shared tasks, and community building via workshops and conferences.

• Architectural Visualization
• Architectural Heritage Conservation
• Digital Reconstruction of Architectural Heritage
• +۴ مورد دیگر

Mariolly Davila Cordido is a Lecturer in the Department of Graphic Engineering and Design at the Universitat Politècnica de Catalunya (UPC), affiliated with the Barcelona School of Architecture (ETSAB) and the Barcelona East Engineering School (EEBE), where she specializes in architectural representation and visualization. She holds a Doctorate in Architectural Graphic Representation and a Master's degree in Secondary Education Teaching, complemented by specialized training in Installations and Services, and Design and Structural Calculation. Her research focuses on architectural visualization, heritage conservation, and digital reconstruction techniques, with particular emphasis on hyperbolic paraboloids in architecture, vernacular structures, and color values in architectural contexts. She has conducted extensive documentation of Venezuelan architectural heritage, especially religious buildings in Caracas and Wayúu indigenous architecture. Recent publications reveal expanding interests in architectural education methodology, including zero-semester programs for graphic expression courses and applications of generative AI through chatbot development for learning support. Davila Cordido actively participates in the International Research Group in Architecture and Society (GIRAS) and the ReDISSENY Research Group in Design, bridging historical architectural knowledge with contemporary digital technologies and educational innovation.

• Graph Neural Networks
• Geometric Deep Learning
• Non-Euclidean Foundation Models
• +۳ مورد دیگر

Rex Ying is an Assistant Professor in the Department of Computer Science at Yale University's School of Engineering & Applied Science. His research focuses on developing expressive, scalable, and explainable algorithms for graph-structured data through graph neural networks and geometric learning. His work spans graph learning applications in recommender systems, anomaly detection, social network analysis, protein networks, drug discovery, and physical simulations. Key research thrusts include Non-Euclidean Foundation Models , Geometric Deep Learning , and Explainable AI for graph representations, with recent emphasis on hyperbolic geometry for hierarchical data modeling. Recent publications reveal strong trends in foundation models for scientific discovery (particularly spatial biology), hyperbolic adaptations of LLMs , and multimodal integration for biomedical applications. His lab actively bridges theoretical geometric learning with real-world applications in biology and physics. Baidu Scholarship 2019 Area Chair for LoG 2022 Conference Blue Sky Best Paper Award at ACM KDD 2025 NSF core program award on foundation models for scientific discovery Ying leads the Graph and Geometric Learning Lab, which develops open-source tools like PyTorch Geometric. He actively recruits PhD students for research on GNN frontiers, theoretical studies of graph learning, and applications in social/natural sciences. Recent grants include NSF funding for scientific foundation models and industry collaborations with Amazon/Ericsson. The lab maintains strong industry partnerships with telecom (Ericsson), healthcare (spatial omics), and social platforms, while organizing key workshops like Non-Euclidean Foundation Models at WebConf 2025 and Graph Signal Processing at GSP 2025.

Marc Poulyمشاهده پروفایل

استاد

• Artificial Intelligence
• Machine Learning
• Deep Learning
• +۶ مورد دیگر

Marc Pouly is a Professor of Artificial Intelligence at Lucerne University of Applied Sciences and Arts (HSLU), where he also serves as Co-Head of the Applied AI Research Lab. He holds a PhD in Artificial Intelligence from the University of Fribourg (2008) and has extensive industry experience as a Chief Data Scientist at Jaywalker AG and Scientific Advisor for Alpine AI and Artificialy SA. His research focuses on AI-driven solutions for healthcare, computer vision, natural language processing, and industrial optimization. Education: PhD in Artificial Intelligence (2004–2008), University of Fribourg MSc in Computer Science & Mathematics (2002–2004), University of Fribourg BSc in Computer Science (1999–2002), University of Fribourg Research Interests: His work spans Medical AI (e.g., dermatology diagnostics via computer vision), Generative Models , Recommender Systems , and AI Ethics . He co-developed the SkinApp for automated skin analysis and pioneered projects like CleanPatrick for image data quality audits. His expertise in self-supervised learning addresses data scarcity challenges in healthcare. Key Achievements: 2023: Best Paper Awards (IARIA, MICCAI) 2021: Research Mosaic recognition by swissuniversities 2017: Aha! Award for the SkinApp project Labs & Collaboration: He leads the Applied AI Lab and collaborates with institutions like ETH Zurich (co-supervising PhDs) and industry partners such as Prepress Media AG and the Swiss Allergy Centre. His work bridges academia and industry, emphasizing AI’s practical applications in healthcare, marketing, and cybersecurity.

Deep Rayمشاهده پروفایل

استادیار

• Scientific machine learning
• Hyperbolic conservation laws
• Shock-capturing algorithms
• +۷ مورد دیگر

Deep Ray is an Assistant Professor of Mathematics holding a joint position at the Department of Mathematics and the Institute for Physical Science and Technology at the University of Maryland, College Park. His research lies at the interface of conventional numerical analysis and machine learning, with a focus on developing computational methods that combine physics-based modeling with deep learning techniques. Dr. Ray's primary research interests include scientific machine learning and hyperbolic conservation laws. In scientific machine learning, he develops deep learning tools to overcome computational bottlenecks in existing numerical methods, with applications in shock-capturing algorithms for conservation laws, reduced order modeling for flow problems, acceleration of Monte-Carlo algorithms using deep surrogates, PDE constrained optimization, physics-based deep Bayesian inference, and operator learning for surrogate modeling. His work in hyperbolic conservation laws focuses on developing numerical methods that satisfy important physical model properties such as entropy stability and kinetic energy preservation, including high-order entropy-stable finite volume schemes for compressible Euler equations. His recent publications (2021-2024) demonstrate a strong focus on applying generative models, particularly GANs and related techniques, to solve physics-based inverse problems, medical imaging applications, and conservation laws. There's a clear trend toward developing physics-informed machine learning approaches that maintain the physical properties of the underlying systems while leveraging the representational power of deep learning. His work spans computational physics, fluid dynamics, medical imaging, and wildfire modeling. Dr. Ray has developed several computational tools including TENSUM (a parallelized finite volume solver for compressible flows) and DGANN (a MATLAB-based DG-solver for conservation laws that uses neural networks for troubled-cell detection and artificial viscosity estimation). His research represents a significant contribution to the emerging field of scientific machine learning, bridging traditional numerical analysis with modern deep learning techniques.

• Computational Social Science
• Natural Language Processing
• Social Network Analysis
• +۳ مورد دیگر

Roshni Chakraborty is an Assistant Professor at the Institute of Computer Science, University of Tartu, Estonia, where she leads research in the Computational Social Science Group. Her work bridges natural language processing, social network analysis, and machine learning to address challenges in social media analytics, disaster response, and misinformation detection. Research Interests: Her expertise spans: Computational Social Science : Analyzing social dynamics via digital footprints. Disaster Informatics : Developing NLP tools for crisis-related tweet summarization (e.g., ATSumm, IKDSumm). Political & Media Analysis : Detecting biases in community-driven fact-checking and news stance. Network Science : Advancing signed network modeling (SigGAN) and cross-network alignment (HCNA). Publication Trends: Recent articles (2022-2025) focus on generative AI for fact-checking, disaster tweet summarization benchmarks, and political bias analysis. Her work emphasizes practical NLP solutions for social good, leveraging transformer models, adversarial learning, and ontology-driven approaches. Academic Activities: She actively recruits PhD students and research interns for projects in social computing. Her group collaborates on datasets like BD2TSumm and Adsumm, fostering open research in crisis informatics.

Anastasis Kratsiosمشاهده پروفایل

استادیار

• Machine Learning
• Artificial Intelligence
• Statistical Learning
• +۵ مورد دیگر

Anastasis Kratsios is an Assistant Professor in the Department of Mathematics and Statistics at McMaster University. His research focuses on the analytic and statistical foundations of deep learning, particularly in encoding structures from natural and social sciences like stochastic processes, games, and PDEs. He teaches courses including Computational Finance, Mathematical Reasoning, and Calculus for Science. Research interests span machine learning theory, approximation methods, and their applications in finance and geometry. Notable work includes neural operator design for PDEs, causal deep learning models, and federated learning frameworks. He frequently publishes in top venues like NeurIPS, ICLR, and Journal of Machine Learning Research. Teaching responsibilities include MFM 713 (Computational Finance II), MATH 1C03 (Introduction to Mathematical Reasoning), and MATH 1A03 (Calculus for Science I). He has developed innovative curricula blending theoretical rigor with practical computational finance tools. Publications emphasize theoretical guarantees for neural networks, kernel methods, and geometric deep learning. Recent work explores universal approximation under constraints, adversarial learning in market models, and scalable graph representation techniques. His research bridges mathematical foundations with real-world applications in finance, physics, and engineering.

• Reinforcement Learning
• Artificial Intelligence
• Computer Vision
• +۶ مورد دیگر

C. H. T. Child is an Associate Professor in the Department of Computer Science at City, University of London, with a distinguished research career spanning over two decades. The academic maintains an active research profile with publications extending through 2025, demonstrating continued scholarly contributions across multiple domains of computer science and artificial intelligence. Child's primary research interests center around Reinforcement Learning , Artificial Intelligence , and Computer Vision , with specialized expertise in non-Euclidean geometry applications for gaming environments, medical informatics, and human-computer interaction. The research portfolio reveals a consistent trajectory from foundational work in reinforcement learning algorithms to applied research in game AI, medical informatics, and scene representation learning. A notable research thread involves the application of non-Euclidean geometry to create novel gaming experiences, while another significant strand focuses on developing advanced AI systems for non-player characters with personality modeling capabilities. Analysis of the most recent publications (2019-2025) shows an evolution toward more sophisticated deep learning architectures applied to complex problems in medical informatics and scene representation. The work has increasingly incorporated transformer networks, attention mechanisms, and advanced feature extraction techniques, reflecting broader trends in the field while maintaining the researcher's distinctive focus on reinforcement learning fundamentals. The publication record demonstrates successful translation of theoretical AI concepts into practical applications across gaming, healthcare, and computer vision domains. Child has supervised multiple doctoral students and research collaborators, with several co-authors appearing consistently across publications as first authors on significant works. The research has been supported through university resources and likely external funding, though specific grant details are not provided in the available materials. The academic maintains an active presence in both theoretical and applied research communities, with publications spanning top conferences and journals in computer science and AI. The researcher leads work in the Extreme AI Personality Engine project and contributes to computer vision research with applications in hand pose estimation and medical imaging. These research streams are well-integrated, with reinforcement learning principles providing a unifying theoretical framework across diverse application domains.

Nikita Araslanovمشاهده پروفایل

پژوهشگر

• Computer Vision
• 3D Reconstruction
• Semantic Segmentation
• +۳ مورد دیگر

Dr. Nikita Araslanov is a Postdoctoral Researcher at the Technical University of Munich (TUM) in the School of Computation, Information and Technology, Department of Informatics 9 (Computer Vision Group). He also serves as a visiting faculty member at Google. His research focuses on semantic and 3D visual inference from video data, aiming to bridge perception and understanding in complex visual scenes. Dr. Araslanov earned his PhD in Computer Science from TU Darmstadt in the Visual Inference Lab, graduating with highest distinction. He holds a Master's degree in Computer Science from the University of Bonn, where he graduated with distinction in 2016. His research spans multiple areas of computer vision, with a particular emphasis on 3D reconstruction, semantic segmentation, and deep learning approaches for visual understanding. His work often combines theoretical insights with practical applications, addressing challenges in dynamic scene understanding, vision-language correspondence, and unsupervised learning paradigms. He has made significant contributions to bundle adjustment for dynamic scenes, hierarchical semantic segmentation using hyperbolic geometry, and novel approaches to unsupervised panoptic segmentation. Dr. Araslanov's research has been recognized with several prestigious awards, including being selected as a Best Paper Candidate at ICCV 2025 for his work on dynamic scene reconstruction, and having his Scene-Centric Unsupervised Panoptic Segmentation paper designated as a Highlight Paper at CVPR 2025 (top 3% of submissions). He has also received multiple oral presentation awards at major computer vision conferences including GCPR 2024, CVPR 2024, and ICLR 2024. Actively involved in the academic community, Dr. Araslanov serves as an Area Chair for CVPR 2025. He is committed to mentoring the next generation of researchers and regularly supervises master's theses, guided research projects, and research assistant positions (HiWi). His teaching includes courses on Deep Learning for Spatial AI (Summer Semester 2025) and Computer Vision 3: Segmentation, Detection and Tracking (Winter Semester 2024/25). As a member of the Computer Vision Group led by Prof. Dr. Daniel Cremers at TUM, Dr. Araslanov collaborates with a diverse team of researchers working on cutting-edge computer vision problems. The group maintains strong connections with industry partners and contributes significantly to the advancement of computer vision research through publications at top-tier conferences and journals.

Kai Hanمشاهده پروفایل

استادیار

• Computer Vision
• Machine Learning
• Artificial Intelligence
• +۶ مورد دیگر

Kai Han is an Assistant Professor at The University of Hong Kong's School of Computing and Data Science, where he directs the Visual AI Lab. His research focuses on computer vision, machine learning, and artificial intelligence with specific interests in open-world learning, 3D vision, generative AI, and foundation models. He aims to achieve principled visual understanding and build reliable AI systems that close the intelligence gap between machines and humans. Dr. Han's research interests span multiple areas in visual AI, with particular emphasis on developing methods for open-world visual understanding. His work addresses fundamental challenges in category discovery, visual correspondence, 3D reconstruction, and generative modeling. He has made significant contributions to novel category discovery, open-set recognition, and visual correspondence problems, with his AutoNovel framework being particularly influential in the field. His current research explores the intersection of generative models and visual understanding, particularly focusing on how foundation models can be leveraged for comprehensive visual analysis. His publication record demonstrates a clear evolution from traditional computer vision problems toward more challenging open-world scenarios and generative approaches. Early work focused on 3D reconstruction of transparent and mirror surfaces, while more recent publications explore category discovery, visual correspondence, and generative AI. The trend shows increasing focus on foundation models, large language model integration with vision systems, and creating more robust visual understanding systems that can handle real-world open-set scenarios. Best Paper Runner-Up Award at CVPR Workshop on Continual Learning in Computer Vision, 2022 Outstanding Reviewer for ICCV 2021 (top 5%) Outstanding Reviewer for CVPR 2021 Outstanding Reviewer for CVPR 2020 Travel Award, ICLR 2020 Doctoral Consortium Travel Grant, ICCV 2017 Dr. Han actively mentors PhD students and postdocs, with numerous students appearing as first authors on his publications. His lab has secured multiple funding opportunities including HKU-PS, HKPFS, PGS, HKU-BICI, and HKU-ASTRI scholarships. He serves as Area Chair for major conferences including CVPR 2026, ICLR 2026, and AAAI 2026, demonstrating his standing in the research community. His lab, the Visual AI Lab, focuses on creating robust visual understanding systems that can handle real-world scenarios beyond closed-set recognition.