جست‌وجوی استاد و پژوهشگر

Yuliang Xiuمشاهده پروفایل

استادیار

• Computer Vision
• Computer Graphics
• 3D Human Digitization
• +۷ مورد دیگر

Yuliang Xiu is a tenure-track Assistant Professor at Westlake University's AI department, leading the 远兮实验室 (endless.do) as PI. His research focuses on democratizing human-centric digitization through advancements in computer vision, graphics, and machine learning. Previously, he completed his Ph.D. at Max Planck Institute for Intelligent Systems under Prof. Michael J. Black, funded by the CLIPE Marie Sklodowska-Curie fellowship. His work bridges vision and graphics to achieve scalable, photorealistic 3D human digitization. Education: Ph.D., Max Planck Institute for Intelligent Systems (2025, advised by Michael J. Black & Dimitrios Tzionas) M.Sc., Shanghai Jiao Tong University (2019, advised by Cewu Lu) B.Eng., Shandong University (2016, advised by Lu Wang) Research Interests: His work emphasizes human-centric digitization , including 3D clothed human reconstruction, generative AI for garments, and training-free methods. His lab explores foundational models for scalable avatar creation, aiming to make human digitization accessible to all. Recent projects include Easi3R (dynamic motion estimation), ETCH (clothed body fitting), and ECON (explicit-implicit hybrid modeling). He advocates for generalizable, photorealistic systems that align with real-world constraints. Publications Trends: Over 15+ peer-reviewed papers, with 2025 highlights including ICCV and SIGGRAPH contributions. His work is characterized by innovations in: 3D reconstruction from single images/videos Implicit/explicit representation hybrids LLM-driven garment editing Efficient finetuning via butterfly factorization Awards & Recognition: 2025 China3DV Rising Star Award Best in Show (SIGGRAPH RTL 2020) CVPR Highlight 2023 Organized ECCV 2024 workshop on Foundation Models for 3D Humans Advising & Mentorship: Successfully mentored 3 master students into top PhD programs (TUM, MBZUAI, HKU). Actively hiring postdocs, PhDs, and researchers for lab expansion. Labs & Teams: Leads the 远兮实验室 (endless.do), focusing on democratizing human digitization through open-source tools and foundational research. Key contributions include the ECON, TADA, and TeCH frameworks.

Arjun Chandrasekaranمشاهده پروفایل

پژوهشگر

• Computer Vision
• Natural Language Processing
• Machine Learning
• +۴ مورد دیگر

Arjun Chandrasekaran holds dual roles as a Guest Scientist/Postdoctoral Researcher at the Max Planck Institute for Intelligent Systems (Tübingen, Germany) and Head of AI at CONXAI Technologies (Munich, Germany). His research bridges computer vision, natural language processing, and cognitive science, focusing on multimodal machine learning for understanding human actions, interactions, and behavior in 3D environments. Key areas include human-AI team dynamics, embodied AI, and humor/narrative modeling. Education: PhD in Computer Science (Georgia Tech, advised by Devi Parikh) Postdoc under Michael Black at MPI-IS Research Highlights: Developed the BABEL dataset for 3D human behavior analysis Explored Fermi problems as AI reasoning benchmarks Pioneered studies on humor perception in visual contexts Advocated for explainable AI through human-centric evaluation Publications emphasize interdisciplinary approaches, combining vision-language tasks with cognitive insights. Current work at CONXAI applies AI to transform the Architecture, Engineering, and Construction (AEC) industry through strategic AI solutions and team leadership.

Soumi Dasمشاهده پروفایل

پژوهشگر

• Large Language Models
• Machine Learning
• Computer Vision
• +۳ مورد دیگر

Soumi Das is a Researcher at the Max Planck Institute for Software Systems (MPI-SWS), Saarbrücken, advised by Professor Krishna Gummadi. Her current research focuses on understanding Large Language Models (LLMs), including knowledge estimation, privacy-utility trade-offs, and language learning. Previously, she conducted her PhD at IIT Kharagpur under Sourangshu Bhattacharya, focusing on data-centric AI algorithms for subset selection and data valuation in machine learning and computer vision. Education: PhD in Computer Science & Engineering (2017–2023), IIT Kharagpur M.Sc. Computer Science (2016), Banaras Hindu University B.Sc. Computer Science (2014), St. Xavier’s College, Kolkata Research Interests: Foundations of LLMs: Knowledge estimation, memorization dynamics, privacy Data-centric AI: Subset selection, data valuation, optimization Applications in autonomous systems and computer vision Key Contributions: Developed algorithms like CheckSelect and VTruST for efficient data valuation and subset selection Worked on defense mechanisms against adversarial attacks in federated learning Contributions to data-efficient autonomous driving through TMCOSS

Paarijaat Adityaمشاهده پروفایل

استاد

• Algorithms
• Theory & Logic
• Programming Languages & Verification
• +۴ مورد دیگر

Paarijaat Aditya is a faculty member at the Max Planck Institute for Software Systems (MPI-SWS) , focusing on interdisciplinary research at the intersection of theoretical computer science and applied systems. Their work spans algorithms, programming languages, security, and distributed systems , with a particular emphasis on serverless computing, federated learning, and privacy-preserving urban sensing. Research Areas : Machine Learning Security (e.g., model hijacking, federated learning) Serverless Computing (e.g., GPU sharing, high-performance frameworks) Privacy Engineering (e.g., urban sensing, image capture, mobile compliance) Distributed Systems (e.g., NFV, peer-assisted content delivery) Their publications reflect a trajectory of advancing scalable AI training, secure collaborative systems, and privacy-compliant infrastructures. Recent works address challenges in public cloud adaptability, while earlier contributions explore mobile privacy risks and secure resource management.

• Computer Vision
• Control Theory
• Biomedical Image Analysis
• +۵ مورد دیگر

Zhen Tang is an active researcher with a prolific publication record spanning from 2007 to 2025, primarily in computer science and engineering disciplines. Their work appears consistently in high-impact venues including IEEE Access, IEEE Transactions, and major conferences in computer vision and systems engineering. Research interests span computer vision, control theory, biomedical image analysis, machine learning, and multi-agent systems. Tang's work demonstrates a strong interdisciplinary approach, connecting theoretical control systems with practical applications in medical imaging, distributed computing, and emerging technologies like DNA computing. Recent publications show a growing interest in large language models, blockchain applications, and ethical considerations in technology design. The publication trends reveal an evolution from foundational work in image processing and pattern recognition (2010-2015) to more complex systems involving multi-agent control and deep learning (2016-2020), and most recently expanding into large language models, blockchain healthcare applications, and technology ethics. The research shows strong connections between theoretical control systems and practical applications across multiple domains. Zhen Tang has established long-term collaborations with researchers including Yanli Wan, Zhenjiang Miao, Wei Wang, and others, suggesting stable research group affiliations. The consistent publication output across 18 years indicates an established academic career with significant contributions to multiple subfields within computer science and engineering.

• Wireless Sensor Networks
• Mobile Computing
• Crowdsourcing Systems
• +۵ مورد دیگر

Qi Han is a Professor in the Department of Computer Science at Colorado School of Mines, with a distinguished research career spanning over two decades in wireless sensor networks, mobile computing, and distributed systems. Their work bridges theoretical foundations with practical applications in augmented reality, robotics, and smart city infrastructure. Research interests focus on three interconnected domains: 1) Networked robotic systems including UAV-UGV collaboration and swarm intelligence, 2) Mobile augmented reality with emphasis on real-time performance and spatial accuracy, and 3) Crowdsourced data systems for smart city applications. Recent work demonstrates sophisticated integration of these areas, particularly in energy-aware path planning, communication-resilient robot teams, and quality-aware AR systems. Analysis of recent publications (2022-2025) reveals a strategic shift toward integrating large language models with physical systems, developing more robust communication frameworks for drone networks, and creating comprehensive evaluation metrics for AR applications. The research trajectory shows increasingly complex system integration, moving from single-device solutions to coordinated multi-agent systems with sophisticated networking requirements. Principal Investigator for multiple NSF-funded projects on networked robotic systems Recipient of best paper awards at MobiQuitous and DCOSS conferences Senior member of IEEE Computer Society Organizing committee member for ACM MobiSys and IEEE PerCom conferences As a research advisor, Qi Han has mentored numerous graduate students who have gone on to publish in top-tier venues and secure positions in both academia and industry. Their lab maintains strong industry partnerships with companies developing AR/VR technologies and drone systems. Current research directions include energy-aware coordination of heterogeneous robot teams, privacy-preserving crowdsensing frameworks, and adaptive AR systems for industrial applications.

• Natural Language Processing
• Machine Learning
• Biomedical Informatics
• +۷ مورد دیگر

Ning An is an active academic researcher primarily affiliated with Hefei University of Technology in China, with additional connections to Shandong University and Xi'an Jiaotong University. With over two decades of publication history spanning from 1998 to 2025, Dr. An maintains a highly productive research trajectory, particularly evident in the substantial publication output in recent years (2023-2025). Dr. An's research spans multiple interdisciplinary domains at the intersection of computer science and health informatics. Key research interests include natural language processing (particularly few-shot learning and named entity recognition), multimodal sentiment analysis, time series forecasting, causal inference, and health monitoring technologies. A significant portion of recent work focuses on applications in elder care technology and medical diagnostics, demonstrating a commitment to translating technical innovations into practical healthcare solutions. The publication trends reveal a strong focus on few-shot learning approaches for natural language processing tasks, with numerous 2024-2025 papers addressing nested named entity recognition. There's also a notable thread of research in multimodal sentiment analysis and time series forecasting, particularly using frequency domain approaches. The consistent collaboration pattern with researchers like Jiaoyun Yang, Lian Li, and Lili Jiang suggests a well-established research group or laboratory environment. Dr. An's work demonstrates significant impact across multiple venues including top conferences like ACL, NeurIPS, and IJCAI, as well as prestigious journals such as Engineering Applications of Artificial Intelligence and Expert Systems with Applications. The research has practical applications in healthcare, particularly in elder care monitoring, depression assessment, and non-invasive health monitoring systems. As a mentor, Dr. An has guided numerous researchers including Jiaoyun Yang, Lian Li, and Lili Jiang, who frequently appear as co-authors on publications. The collaborative nature of the work extends to international partnerships, with publications involving researchers from institutions across China and potentially beyond.

• Computer Science Education
• Culturally Responsive Computing
• Augmented Reality for Education
• +۴ مورد دیگر

Dr. Wei Yan is an Associate Professor in the Department of Computer & Information Science & Engineering at the University of Florida's Herbert Wertheim College of Engineering. With an extensive publication record spanning computer science education, augmented reality applications, and culturally responsive computing, Dr. Yan has established a significant research presence with numerous publications in top-tier conferences and journals from 2023-2025. Dr. Yan's research interests focus on culturally responsive computing education, particularly with Indigenous communities including the Navajo Nation. Their work bridges the gap between technical computing concepts and culturally relevant pedagogy, with a special emphasis on spatial reasoning and mathematics education through augmented reality technologies. The research program has produced innovative AR classroom applications that help students understand complex spatial transformations and matrix algebra through interactive 3D visualizations. Through collaborations with researchers like Ashish Amresh, Paige Prescott, Maya Israel, and Heather Burte, Dr. Yan has developed several educational technology interventions that address inclusion in computer science education. Their publications reveal a strong commitment to broadening participation in computing, particularly among underrepresented groups, with a focus on teacher professional development and curriculum design that respects cultural contexts. Dr. Yan's technical expertise spans both educational technology development and core computer science topics, as evidenced by publications ranging from spatial reasoning in AR classrooms to advanced topics in integer coding and neural image compression. This interdisciplinary approach allows for the development of sophisticated educational tools grounded in solid computer science principles. Current research directions include AI-enhanced educational applications, culturally responsive computing curriculum development, and the integration of conversational AI with augmented reality for improved learning experiences. The work has significant implications for how computing education can be made more accessible and relevant to diverse student populations.

• Named Data Networking
• Mobile Ad Hoc Networks
• Pervasive Computing
• +۴ مورد دیگر

Vaskar Raychoudhury is a Professor in the Department of Computing at Hong Kong Polytechnic University's Faculty of Engineering. With an extensive publication record spanning from 2007 to 2024, he has established himself as a leading researcher in pervasive computing, networking, and accessible technology systems. His research interests focus on Named Data Networking, Mobile Ad Hoc Networks, and accessible routing systems, with recent work emphasizing machine learning applications for wheelchair navigation and transportation optimization. Professor Raychoudhury's work bridges theoretical computer science with practical applications that address real-world accessibility challenges. His publication trends over the past five years show a strong emphasis on accessible routing systems for wheelchair users (using sensor data and vibration patterns), machine learning applications for transportation (taxi ride sharing and food delivery optimization), and open-world machine learning approaches. His work often combines multiple disciplines including computer networking, machine learning, and human-centered design. Professor Raychoudhury has supervised numerous graduate students including Haoxiang Yu, Ashman Mehra, and Aditi Seetha, who have co-authored multiple publications with him. His research has been supported by grants focused on smart city applications and accessibility technology. He leads research in the Smart Mobility and Accessibility Lab, which develops technologies to improve urban mobility for people with disabilities. The lab employs a multidisciplinary approach combining networking, machine learning, and human-computer interaction to create practical solutions for real-world accessibility challenges.

• Vision-Language
• Multimodal Deep Learning
• Semantic Segmentation
• +۳ مورد دیگر

Philipp Jonas Rösch is a Researcher and PhD Candidate at Bundeswehr University Munich, holding the position of Research Head for Artificial Intelligence at the Institute for Distributed Intelligent Systems (VIS). He is affiliated with the Chair of Data Science under Prof. Michaela Geierhos at the Research Institute CODE. He holds a Master's degree in Statistics from Ludwig-Maximilians-Universität München and has industry experience prior to academia. His research focuses on Vision-Language systems, Multimodal Deep Learning, and Damage Recognition, with notable contributions to datasets like dacl10k and InpaintCOCO . He co-organizes the Machine Learning Interest Group (MLIG), a platform for researchers at UniBw M and HSU focusing on ML/AI topics. Rösch manages the GPU cluster 'Monacum One' and advises students on Bachelor's/Master's theses in Deep Learning or Vision-Language domains. His work emphasizes real-world applications in infrastructure inspection and military vehicle detection, leveraging both academic and industrial perspectives.

• Computer Vision
• Machine Learning
• Rail Transportation Systems
• +۵ مورد دیگر

Yu Qian is a Professor in the Department of Electrical and Computer Engineering at the University of Southern California's Viterbi School of Engineering, with extensive research contributions spanning computer vision, machine learning, and transportation systems. Their work bridges theoretical advances with practical applications, particularly in railroad safety and ferroelectric computing architectures. Research interests focus on computer vision applications for transportation safety, including railroad inspection systems and pedestrian behavior analysis at grade crossings. Additional expertise includes ferroelectric computing-in-memory architectures, micro-expression recognition, and multimodal sentiment analysis. The research program demonstrates strong interdisciplinary collaboration across engineering disciplines. Recent publications (2023-2025) show a clear trend toward hardware-algorithm co-design for specialized computing, particularly using ferroelectric devices for optimization problems, alongside continued work in transportation safety applications. The research spans both theoretical contributions to neural network architectures and practical implementations for real-world problems. While specific awards aren't documented in the provided records, the extensive publication record in high-impact venues demonstrates significant scholarly contribution to the field. The research program appears well-funded, supporting numerous collaborative projects across multiple institutions.

• Computer Vision
• Deep Learning
• Object Detection
• +۴ مورد دیگر

Zheng Ge is an active researcher specializing in computer vision and deep learning, with a prolific publication record spanning from 2018 to 2025. They have authored or co-authored 81 publications in top-tier venues including CVPR, ICLR, ECCV, and NeurIPS, demonstrating consistent research productivity and impact in the field of artificial intelligence. Dr. Ge's primary research interests focus on computer vision with particular emphasis on object detection, 3D perception, and multimodal learning systems. Their work bridges theoretical advancements with practical applications, especially in video understanding, image generation, and large vision-language models. Recent research directions show a strong focus on developing more efficient and capable multimodal systems that can handle complex visual tasks with human-like understanding. The analysis of their recent publications reveals a clear trend toward building more sophisticated multimodal systems that integrate vision, language, and temporal understanding. Their work on video generation, perception modeling, and instruction tuning demonstrates a strategic focus on advancing the capabilities of multimodal large language models while addressing practical challenges in scalability and robustness. While specific awards are not documented in the available publication records, Zheng Ge's consistent presence in top-tier computer vision and machine learning conferences indicates significant recognition within the research community. Their work has contributed to advancing state-of-the-art techniques in multiple subfields of computer vision. Dr. Ge appears to be actively collaborating with a large research team, frequently working with researchers such as Xiangyu Zhang, Jianjian Sun, Chunrui Han, and Liang Zhao. These collaborations span multiple institutions and research groups, suggesting a well-integrated position within the computer vision research ecosystem. While specific grant information isn't available in the publication metadata, the scale and scope of their projects indicate substantial research funding support. Based on publication patterns and technical focus, Zheng Ge appears to be part of a large research organization or lab specializing in computer vision and multimodal AI systems. Their work on technical reports for video foundation models and large-scale multimodal systems suggests involvement in industry-leading AI research initiatives with strong engineering capabilities.

• Computer Vision
• Deep Learning
• Neural Network Acceleration
• +۵ مورد دیگر

Kaisheng Ma is a Professor in the Department of Computer Science and Technology at Tsinghua University's School of Information Science and Technology. With an extensive publication record spanning from 2013 to 2025, he has established himself as a leading researcher in computer vision, deep learning, and computer architecture. His work bridges theoretical advances with practical applications in neural network acceleration and hardware-software co-design. Professor Ma's research interests focus on advancing the frontiers of computer vision and deep learning systems. His work in knowledge distillation has significantly improved the efficiency of neural networks, while his contributions to hardware acceleration have enabled more powerful AI systems. His recent research demonstrates a growing emphasis on 3D vision, embodied AI, and the intersection of language and vision systems. He has pioneered techniques in frequency domain analysis for image processing and developed novel approaches for neural network acceleration through hardware-software co-design. Analysis of Professor Ma's recent publications (2023-2025) reveals a strong research trajectory with increasing focus on multimodal learning, 3D scene understanding, and efficient neural network deployment. His work spans both theoretical advances in machine learning (particularly knowledge distillation and continual learning) and practical hardware implementations for AI acceleration. The publications show consistent collaboration with a core group of researchers while expanding into new areas like brain-computer interfaces and language-grounded spatial reasoning. Professor Ma has successfully mentored numerous PhD students who have become active contributors to the field, including Linfeng Zhang, Runpei Dong, and Zekun Qi. His research has been supported by significant grants that enable cutting-edge work in neural network acceleration and 3D vision systems. His students have published in top-tier conferences including CVPR, NeurIPS, and ICCV, demonstrating the strength of his research group. Professor Ma leads a research group focused on the intersection of computer vision, deep learning, and computer architecture. His lab investigates efficient neural network deployment, hardware acceleration techniques, and novel computer vision algorithms. The team maintains strong collaborations with industry partners working on AI hardware and has developed several innovative approaches to neural network acceleration and efficient model deployment.

• Artificial Intelligence
• Machine Learning
• Federated Learning
• +۳ مورد دیگر

Yifei Zhang is an Assistant Professor in the Department of Computer Science at Northeastern University's School of Computer Science and Engineering, with extensive research collaborations including the University of Hong Kong (notably with Irwin King). Active since 2009, Zhang has produced 257 publications through 2025, demonstrating sustained research productivity across artificial intelligence domains. Zhang's research spans Artificial Intelligence , Machine Learning , and Computer Vision , with recent focus on federated learning systems, multimodal AI, and security applications. The work shows strong technical depth in developing novel algorithms for personalized learning, anomaly detection, and efficient model training. Recent publications reveal increasing specialization in privacy-preserving machine learning and cross-modal understanding, particularly for Chinese language and cultural contexts. Publication trends indicate growing influence in AI conferences (CVPR, ACL, NeurIPS), with 61 publications in 2024 alone. The research demonstrates practical applications in cybersecurity, education technology, and urban planning, while maintaining theoretical rigor in model architecture and optimization techniques. Zhang frequently collaborates with Neng Gao and Shuang Song on security-related AI projects. Zhang serves on program committees for major AI conferences and has contributed to workshop organization including FL@FM-TheWebConf'25: International Workshop on Federated Foundation Models for the Web. The research has attracted significant attention in the AI community, particularly in federated learning and multimodal systems.

• Artificial Intelligence
• Machine Learning
• Computer Vision
• +۴ مورد دیگر

Yin Chen is a Professor in the Department of Computer Science at South China Normal University, Guangdong, China. With an extensive publication record spanning over 25 years from 2000 to 2025, Professor Chen has established themselves as a leading researcher in multiple domains of computer science and artificial intelligence. Professor Chen's research spans artificial intelligence, machine learning, computer vision, natural language processing, and deep learning. Their work demonstrates exceptional breadth across theoretical and applied domains, with significant contributions to facial expression recognition, transformer-based language models, 3D human modeling, and optimization algorithms. Recent research shows particular strength in multimodal learning, with numerous publications integrating visual, textual, and audio information for advanced AI applications. The publication trends reveal a consistent output of high-impact research, with a notable acceleration in recent years. Professor Chen's work appears in top-tier venues including IEEE Transactions, ACM Multimedia, and various specialized journals. Their research demonstrates strong interdisciplinary connections, bridging computer science with applications in engineering, bioinformatics, and mathematics. Professor Chen collaborates extensively with researchers across institutions, particularly with Jia Li, Meng Wang, Richang Hong, and Xianghua Fu. These collaborations span multiple projects in affective computing, multimodal translation, and algorithm development. The research group appears to be active in both theoretical advancements and practical implementations of AI systems.