جست‌وجوی استاد و پژوهشگر

Lawrence Snyderمشاهده پروفایل

استاد

• Neuroscience
• Cognitive Neuroscience
• Spatial Representation
• +۵ مورد دیگر

Lawrence Snyder, MD, PhD is a Professor of Neuroscience at Washington University School of Medicine with extensive research in cognitive neuroscience using non-human primate models. His work focuses on the neural basis of cognition, particularly examining how spatial information is processed and transformed into motor commands. Dr. Snyder received his AB in English from Princeton University in 1982, followed by both his MD and PhD (in Physiology) from the University of Rochester in 1992. His academic journey reflects a unique interdisciplinary approach combining humanities with advanced medical and scientific training. His research interests center on understanding small neural circuits underlying cognition, with specific emphasis on spatial representation, memory systems, eye-hand coordination, and functional connectivity. The Snyder laboratory investigates how sensory spatial information is transformed into motor commands, examining neural representations of space in parietal and frontal cortices. His work has contributed significantly to understanding effector-specific versus effector-general memory systems, bimanual coordination mechanisms, and the neural correlates of functional connectivity observed in fMRI studies. Analysis of his recent publications reveals a consistent focus on neural mechanisms of spatial cognition, memory processing, and motor control. His work bridges electrophysiological recordings with functional imaging techniques, demonstrating how slow rhythmic mechanisms underlie functional connectivity and how spatial memory representations evolve over time. His research increasingly incorporates sensorimotor integration aspects into perceptual decision-making frameworks. 1998-1999 Washington University/Howard Hughes Medical Institute Award 1998-2000 Sloan Foundation Research Fellowship 2001 Klingenstein Fellow 2000-2024 National Eye Institute Investigator 2004 EJLB Foundation Scholar Research Programme Award Recipient 2009-2019 National Mental Heath Institute Investigator 2012-2017 Co-Director, Washington University Neuroscience Program 2014-2019 Editorial Board, Journal of Neurophysiology 2015-2018 Program Committee, Society for Neuroscience Dr. Snyder has maintained continuous NIH funding throughout his career, serving as Principal Investigator on National Eye Institute grants from 2000-2024 and National Institute of Mental Health grants from 2009-2019. His laboratory has trained numerous graduate students and postdoctoral fellows who have gone on to establish independent research careers. The Snyder lab has developed innovative techniques including oxygen polarography to simultaneously record oxygen levels across brain networks alongside LFP and spiking activity. The Snyder laboratory maintains a strong presence in the neuroscience community through regular participation in the Society for Neuroscience meetings and editorial service on prominent journals. His research continues to push boundaries in understanding how neural circuits support complex cognitive functions, with recent work exploring how sensorimotor faculties bias perceptual decision-making and choice behavior.

Dani Byrdمشاهده پروفایل

استاد

• Linguistics
• Speech Science
• Phonetics
• +۶ مورد دیگر

Dani Byrd is a Professor of Linguistics at the University of Southern California's Dornsife College of Letters, Arts and Sciences. She has held significant administrative leadership roles including Interim Dean, Executive Vice Dean, and multiple Vice Dean positions focusing on research advancement, faculty affairs, and institutional matters. Her interdisciplinary research bridges linguistics, engineering, and neuroscience to investigate human speech production and articulatory coordination. Byrd earned her PhD in Linguistics from UCLA in 1994 with a dissertation on 'Articulatory Timing in English Consonant Sequences.' She received simultaneous MA and BA degrees from Yale University in 1990, graduating magna cum laude with Distinction in Linguistics. Following her PhD, she completed post-doctoral training at Haskins Laboratories in New Haven, Connecticut. Her research specializes in speech production and articulatory coordination, employing cutting-edge magnetometer and real-time MRI technologies to track vocal tract movements during speech. Byrd's work investigates language production from a dynamical systems perspective, examining how linguistic structures relate to temporal speech realization. She combines theoretical linguistics with experimental speech science to understand the cognitive representation of language through physical production. Byrd's recent publications demonstrate a strong interdisciplinary trajectory, integrating linguistics, neuroscience, and artificial intelligence. Her work increasingly focuses on mental health applications of speech analysis, using AI to detect depression and suicidal ideation from speech and eye movements. She continues advancing vocal tract imaging techniques while expanding into speech foundation models that characterize speaker traits and dialect variations across languages. USC Dornsife Dean's Award for Distinguished Service (2012) Fellow of the Acoustical Society of America (2008) R. Bruce Lindsay Award for scholars under 35 NSF Graduate Fellow (1990-1992) UCLA Graduate Woman of the Year Award (1994) Professor Byrd has chaired or served on numerous PhD thesis committees across Linguistics, Electrical Engineering, and Psychology departments at USC. Her research has been continuously funded for three decades by the National Science Foundation and NIH's National Institute on Deafness and Other Communication Disorders. Current major grants include NSF funding for structured variability in vocal tract articulation dynamics and an IARPA contract for spoken human signal anonymization, totaling over $5 million in active funding. Byrd's research takes place in the Dynamic Imaging Science Center at the USC Michelson Center for Convergent Bioscience. She leads the USC SPAN (Speech Production and Articulation kNowledge) Research Group, which combines real-time MR imaging, linguistic experimentation, and machine learning to advance understanding of spoken language. Her team includes engineers, linguists, and neuroscientists working collaboratively on speech production research.

Chulhee Yunمشاهده پروفایل

استادیار

• Deep Learning Theory
• Optimization
• Machine Learning Theory

Chulhee Yun is an Ewon Assistant Professor at KAIST Kim Jaechul Graduate School of AI (KAIST AI), with a joint affiliation starting September 2025 at KAIST Graduate School of AI for Math and a part-time Visiting Faculty Researcher position at Google Research. He directs the Optimization & Machine Learning (OptiML) Laboratory at KAIST AI. Education: PhD in Elec. Eng. & Comp. Sci., 2016–2021, Massachusetts Institute of Technology MSc in Electrical Engineering, 2014–2016, Stanford University BSc in Electrical Engineering, 2007–2014, KAIST Chulhee Yun's research focuses on deep learning theory, optimization, and machine learning theory. His work bridges theoretical foundations with practical applications in neural network training, addressing fundamental questions about optimization dynamics, generalization capabilities, and the mathematical properties of deep learning models. His research spans from theoretical analyses of gradient-based optimization methods to practical techniques for improving neural network training and performance. His recent publications demonstrate a strong focus on understanding the fundamental properties of neural network training dynamics, optimization algorithms, and generalization. The research spans theoretical analyses of stochastic optimization methods like SGD, investigations into the properties of transformers and language models, and practical techniques for improving neural network training efficiency. A notable trend is the combination of rigorous theoretical analysis with practical implications for deep learning systems. Scientific Awards: KAIA Outstanding Paper Award at KAIA Summer Conference 2025 (CKAIA 2025) KT Best Paper Award at KAIA Summer Conference 2025 (CKAIA 2025) Best Paper Award at KAIA Fall Conference 2024 (JKAIA 2024) KT Best Paper Award at KAIA Summer Conference 2024 (CKAIA 2024) KAIA Outstanding Paper Award at KAIA Summer Conference 2023 (CKAIA 2023) NAVER Outstanding Theory Paper Award at KAIA-NAVER Joint Fall Conference 2022 (JKAIA 2022) Honorable Mention at NYAS Machine Learning Symposium 2020 Poster Awards Notable AC for NeurIPS 2023 Top Reviewer at ICML 2025 Professor Yun actively mentors PhD, Master's, and undergraduate students through the OptiML Laboratory. His research group includes several PhD students (Jaeyoung Cha, Hanseul Cho, Yujun Kim, Junghyun Lee, Junsoo Oh, Baekrok Shin), Master's students, and undergraduate interns. He has successfully guided former students such as Geonhui Yoo, Jaewook Lee, and Dongkuk Si to completion. His service to the academic community includes serving as Social Chair for ICML 2026, Conference Area Chair for ICLR 2025-2026 and NeurIPS 2023-2025, and as a reviewer for numerous top conferences and journals. Chulhee Yun directs the Optimization & Machine Learning (OptiML) Laboratory at KAIST, which focuses on advancing the theoretical foundations of machine learning and optimization. The lab investigates fundamental questions about neural network training dynamics, optimization algorithms, and generalization properties, with the goal of bridging theoretical insights with practical applications in deep learning systems.

• 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.

• Computer Vision
• Object Recognition
• Scene Understanding
• +۷ مورد دیگر

Derek Hoiem is a Professor in the Department of Computer Science at the University of Illinois Urbana-Champaign (UIUC), affiliated with the Siebel School for Computing and Data Science since 2009. He holds a PhD in Robotics from Carnegie Mellon University (2007) and completed a Beckman Postdoctoral Fellowship (2008). As co-founder and Chief Science Officer of Reconstruct, he develops AI-driven tools for construction progress monitoring. His research focuses on computer vision, object recognition, scene understanding, and graphics. Key honors include IEEE Fellow (2022), University Scholar (2022), and the Sloan Research Fellowship (2013). He has received NSF CAREER and Intel Early Career awards, alongside best paper awards at CVPR (2006) and WACV (2015). His teaching excellence is reflected in numerous 'List of Teachers Ranked as Excellent' accolades across multiple semesters. Research interests span 3D reconstruction, neural networks, and multimodal models. His work addresses challenges in visual program generation, neural radiance fields, and construction monitoring through photogrammetry. He leads projects in continual learning, efficient AI systems, and explainable multimodal interactions. Professional contributions include grants from NSF and industry partnerships. He advises on cutting-edge AI applications in construction, graphics, and vision-language integration. His lab’s innovations bridge theoretical advancements with real-world systems like Reconstruct’s Visual Command Center.

• Electrical Engineering
• Computer Engineering
• Smart Grids
• +۵ مورد دیگر

Muhammad Jawad is an Assistant Professor at COMSATS University Islamabad in the Department of Electrical and Computer Engineering. He previously completed his PhD at North Dakota State University in 2015 and has also been affiliated with the University of Manchester's Department of Electrical and Electronics Engineering. His academic career spans over a decade with continuous research contributions from 2013 to the present. Dr. Jawad's research focuses on the intersection of electrical engineering and computer science, particularly in smart grid technologies, energy management systems, machine learning applications for power systems, and IoT security. His work demonstrates strong interdisciplinary collaboration, with numerous publications in high-impact journals including IEEE Access, Future Internet, and Expert Systems with Applications. His research addresses critical challenges in modern power systems, renewable energy integration, and computational methods for electrical engineering applications. Analysis of his recent publications reveals a clear research trajectory focusing on applying advanced computational techniques to solve practical problems in power systems and energy management. His work spans machine learning for intrusion detection in IoT devices, optimization techniques for battery sizing and energy management, thermal-aware scheduling algorithms, and blockchain applications for distributed systems. The interdisciplinary nature of his research connects electrical engineering fundamentals with cutting-edge computer science methodologies. Dr. Jawad has established a strong collaborative network, frequently working with researchers from COMSATS University Islamabad, North Dakota State University, and international institutions. His collaborations span across multiple research areas, indicating his ability to bridge different technical domains. While specific grant information isn't detailed in the publication records, his consistent output suggests successful funding support for his research activities. Though specific laboratory affiliations aren't explicitly mentioned in the publication metadata, his research areas suggest involvement with power systems laboratories, smart grid research facilities, and possibly computer architecture labs focused on energy-efficient computing. His work on memristor modeling and thermal-aware scheduling indicates potential connections to hardware and VLSI research facilities as well.

Tameem Albashمشاهده پروفایل

عضو هیئت علمی

• Quantum Information Science
• Quantum Computing
• Quantum Annealing
• +۷ مورد دیگر

Tameem Albash is a Research Associate Professor at the University of New Mexico , affiliated with the Department of Physics and Astronomy in the College of Arts and Sciences . His research focuses on quantum information science, quantum computing, and quantum annealing. He holds a PhD from the University of Southern California (2010). Education: PhD in Physics, University of Southern California, 2010 Research interests include quantum annealing optimization, quantum simulation, noise mitigation in quantum systems, and the interplay between quantum error correction and classical computational methods. His work explores topics like non-stoquastic Hamiltonians, many-body localization, and the application of machine learning to quantum systems. Recent studies investigate the efficiency of quantum annealing hardware for combinatorial problems, decoherence effects in quantum simulations, and the use of neural networks for state approximation. His articles highlight advancements in classical simulation techniques for quantum phenomena, such as analyzing macrostate vs. microstate dynamics in 1D Ising models. He also examines hybrid approaches combining quantum and classical methods to address limitations in current quantum hardware. Despite no listed awards, his contributions to quantum computing benchmarks and hardware validation are notable. Labs/Teams: Albash's research aligns with UNM's Quantum Information Science initiatives, though specific lab affiliations are not detailed in the provided text.

Matthias Zwickerمشاهده پروفایل

استاد

• Computer Graphics
• Artificial Intelligence
• Point-Based Graphics
• +۷ مورد دیگر

Matthias Zwicker is the Elizabeth Iribe Chair for Innovation and the Phillip H. and Catherine C. Horvitz Professor of Computer Science at the University of Maryland, where he currently serves as the Chair of the Department of Computer Science. He joined UMD in March 2017 as the Reginald Allan Hahne Endowed E-Nnovate Professor in Computer Science. Prior to UMD, he was a professor at the University of Bern, Switzerland (2008-2017), Assistant Professor at UC San Diego (2006-2008), and a post-doctoral associate at MIT (2003-2006). PhD from ETH Zurich, Switzerland (2003) Matthias Zwicker's research focuses on the intersection of artificial intelligence and computer graphics, with the goal of enabling next-generation AR/VR and computer graphics applications. His work spans several key areas including point-based graphics, gradient-domain rendering, image processing, and 3D reconstruction. He has made significant contributions to surface splatting, texture synthesis, and denoising techniques. His recent work increasingly integrates deep learning approaches with traditional computer graphics techniques. Zwicker's recent publications (2021-2022) show a strong trend toward integrating deep learning with computer graphics, particularly in 3D reconstruction, rendering, and animation. His work increasingly focuses on neural radiosity, point cloud processing, and differentiable rendering techniques. There's a clear emphasis on improving perceptual quality in graphics applications, with many papers addressing challenges in AR/VR systems. His research group frequently publishes at top venues including SIGGRAPH, CVPR, and ICCV. BEST STUDENT PAPER AWARD! at VISAPP 2018 As an active member of the UMD community, Zwicker has served as a University Senator for the CS department, as a faculty co-lead in developing the new Immersive Media Design major, and as a faculty mentor in the Gemstone Honors Program. His service includes conference leadership roles such as papers co-chair for IEEE/Eurographics Symposium on Point-Based Graphics, Eurographics, and Eurographics Symposium on Rendering. Zwicker leads research in the Brendan Iribe Center for Computer Science and Engineering at UMD (room 5244). His work builds on his previous leadership of the Computer Graphics Group at the University of Bern, where he served as head of the group and as director of undergraduate and graduate studies. His research continues to push boundaries in the integration of AI and graphics for next-generation visual computing applications.

Robert Bamlerمشاهده پروفایل

استاد

• Deep Generative Models
• Machine Learning
• Probabilistic Inference
• +۳ مورد دیگر

Robert Bamler is a Professor of Data Science and Machine Learning at the University of Tübingen, Germany , and a member of the Cluster of Excellence "Machine Learning: New Perspectives for Science" and the Tübingen AI Center . Current affiliation: University of Tübingen (since November 2020) Prior roles: Postdoctoral Scholar at UC Irvine (with Stephan Mandt), Machine Learning Researcher at Disney Research (Pittsburgh/Los Angeles) Education: PhD in Theoretical Statistical and Quantum Physics from University of Cologne (2016), advised by Achim Rosch Research Focus : Algorithm development for deep generative models (including large language models) Resource-efficient inference and model compression Probabilistic machine learning applications in natural sciences Theoretical foundations in statistics, information theory, and physics Scientific Contributions : German Telekom Foundation PhD scholarship awardee Co-founder of the BamlerLab reading group on probabilistic modeling and compression Key Collaborations : Stephan Mandt (UC Irvine) Bernhard Schölkopf (MPI-IS) Cluster of Excellence "Machine Learning" (Tübingen) Teaching : Lecturer for "Data Compression With and Without Deep Probabilistic Models" (2021-2025) Organizer of weekly reading groups on function-space inference and compression algorithms

• Computer Vision
• Deep Learning
• Remote Sensing
• +۵ مورد دیگر

Lin Xiong is a Professor at Xidian University's School of Artificial Intelligence, Department of Computer Science, with an extensive publication record spanning from 2008 to 2025. His research primarily focuses on computer vision, deep learning, and remote sensing applications, with significant contributions to SAR image processing, domain adaptation techniques, and environmental monitoring systems. Dr. Xiong's educational background includes advanced studies in computer science and artificial intelligence, though specific details of his degrees are not readily available in the publication record. His research interests span multiple domains including computer vision (particularly facial recognition and person re-identification), deep learning architectures, domain adaptation methods, and remote sensing applications for environmental monitoring. His publication trends reveal a strong focus on practical applications of deep learning, with recent work emphasizing class-incremental learning, SAR image registration, and environmental monitoring using lidar technology. The research spans both theoretical advancements in neural network architectures and practical implementations in fields ranging from renewable energy forecasting to coastal ecosystem monitoring. Knowledge distillation techniques for continual learning Advanced SAR image processing algorithms Domain adaptation methods for computer vision tasks Environmental monitoring using remote sensing technology Dr. Xiong has established significant collaborations with researchers from NASA (notably on mangrove ecosystem monitoring projects) and maintains strong connections within China's academic community, particularly with Xidian University colleagues. His work demonstrates both theoretical depth and practical applicability across multiple domains requiring advanced computer vision and machine learning solutions.

Edoardo Barbaمشاهده پروفایل

پژوهشگر

• Natural Language Processing (NLP)
• Lexical Semantics
• Entity Linking
• +۵ مورد دیگر

Edoardo Barba is a full-time Researcher (RTDA) in the Department of Computer, Control and Management Engineering (DIAG) at Sapienza University of Rome. He is a core member of the Sapienza NLP group led by Professor Roberto Navigli, focusing on Lexical Semantics, Entity Linking, and Word Sense Disambiguation. His recent work explores descriptive modeling applications in Language Modeling, Semantic Role Labeling, and Machine Translation. He co-founded Litus AI, an NLP-focused startup in Rome. Barba holds a Ph.D. in Computer Science from Sapienza University (2023), with a thesis on 'Descriptive Modeling: Capturing Semantics in Neural Models via Natural Language Descriptions'. His research emphasizes innovative architectures like ReLiK (entity linking/relation extraction) and ExtEnD (extractive entity disambiguation), achieving state-of-the-art results. He has published extensively in top conferences like ACL, EMNLP, and IJCAI, focusing on semantic grounding, metric evaluation, and efficient NLP systems. His work on ConSeC (continuous sense comprehension) and DMLM (descriptive masked language modeling) highlights contributions to semantic understanding and knowledge-enhanced models. Selected Awards: None explicitly mentioned, though his publications reflect significant academic recognition. Grants/Advising: Not detailed in the provided text. Barba collaborates on multilingual resources like MOSAICo and explores Italian-specific LLM optimizations. His research bridges theoretical advancements with practical applications in startups and open-source tools.

Saeed Sametمشاهده پروفایل

استاد

• Cybersecurity
• Privacy-Preserving Data Mining
• Federated Learning
• +۵ مورد دیگر

Dr. Saeed Samet is a Professor in the School of Computer Science at the University of Windsor. His research focuses on cybersecurity, privacy-preserving data mining, federated learning, blockchain technology, and healthcare informatics. He has led projects such as the privacy-preserving personal health record system (P3HR) and the decentralized electronic health records (DEHR) model leveraging blockchain. Samet actively engages in interdisciplinary collaborations, including developing frameworks like SEERa for community prediction and RNBFT for scalable Byzantine consensus. He advises students like Saghi Khani on topics such as social isolation detection algorithms. Notably, his work addresses adversarial attacks in machine learning and federated learning security. Samet has contributed to initiatives like the International Collegiate Programming Contest and the WE-Spark Health Institute grants. Education While formal academic credentials are not explicitly detailed in the text, Samet holds a professorship, indicating advanced qualifications in computer science or related fields. His extensive publications suggest doctoral-level expertise. Research Interests Samet’s research spans cybersecurity mechanisms, privacy-preserving methodologies (e.g., homomorphic encryption, federated learning), blockchain applications in healthcare, and machine learning robustness. Recent work emphasizes scalable consensus algorithms (RNBFT), adversarial defense in federated learning, and frameworks for decentralized data evaluation. His projects often integrate real-world challenges, such as combating fake news via generative AI and enhancing pandemic response through blockchain-based patient tracking. Awards & Grants Recipient of a WE-Spark Health Institute grant for innovative research in Windsor-Essex (2021). His work on social isolation algorithms (2020) and privacy-preserving statistical analysis (2019) underscores sustained funding support for impactful projects. Advising & Grants Advises Saghi Khani on machine learning algorithms for social isolation detection. Collaborates on grants involving interdisciplinary teams, such as the $287,000 WE-Spark Health Institute award. His research often bridges academia and industry, addressing practical challenges in healthcare and cybersecurity. Labs & Teams Leads initiatives in the School of Computer Science’s research groups, focusing on privacy-preserving systems and distributed learning. Collaborates with organizations like the WE-Spark Health Institute and the University of Windsor’s interdisciplinary teams on projects such as the DEHR blockchain model and federated learning frameworks.

Wei Luمشاهده پروفایل

استاد

• Memristors
• Neuromorphic Computing
• In-Memory Computing
• +۳ مورد دیگر

Wei Lu is the James R. Mellor Professor of Engineering at the University of Michigan with joint appointments in the Department of Electrical Engineering & Computer Science (EECS) and Materials Science & Engineering. He directs the Solid State Electronics Laboratory and leads the Lu Research Group. Lu completed his BS in Physics at Tsinghua University (1996), PhD at Rice University (2003), and postdoctoral research at Harvard University. Research Focus: Lu's work bridges nanoelectronics, materials science, and computing architectures. His research spans: Memristive devices for neuromorphic computing and in-memory processing Nanowire transistors and emerging electronic devices Resistive switching mechanisms in oxides and 2D materials Hardware implementations of machine learning algorithms Crossbar arrays for energy-efficient computation Publication Trends: Analysis of 15 recent publications reveals consistent focus on memristor physics (58% of papers), neuromorphic implementations (42%), and nanoscale characterization (33%). Key evolution includes increased emphasis on full system integration (20%) and commercial applications. Awards & Honors: IEEE Fellow NSF CAREER Award 2022 Distinguished University Innovator Award 2016-2017 David E. Liddle Research Excellence Award 2014-2015 Rexford E. Hall Innovation Excellence Award 2012 EECS Outstanding Achievement Award Commercialization & Leadership: Co-founded Crossbar Inc. (resistive RAM technology) and MemryX Inc. (edge AI chips). Currently advises PhD candidates and postdocs in nanoelectronics and neuromorphic systems, with active NSF and industry-funded projects in memristive computing platforms.

Simone Rossiمشاهده پروفایل

استادیار

• Machine Learning
• Deep Learning
• Generative Models
• +۳ مورد دیگر

Simone Rossi is an Assistant Professor in the Data Science department at EURECOM. His research focuses on Bayesian methods, generative models, and deep learning, with particular emphasis on uncertainty quantification, diffusion processes, and scalable probabilistic models. He has contributed to foundational work on functional priors for Bayesian neural networks, conformal prediction for in-context learning, and optimization of diffusion models. Education: Not explicitly mentioned in the provided text. His research interests span machine learning, probabilistic modeling, and theoretical computer science. He explores topics like score-based generative models, continuous-time diffusion processes, and efficient Bayesian inference techniques. Recent work includes analyzing scaling laws for uncertainty in deep learning and improving LLM reasoning capabilities for Text2SQL tasks. His publications reflect contributions to top conferences like NeurIPS, ICML, and AABI, with a focus on both theoretical advancements and practical applications. Notable achievements include a Runner-up Best Paper Award at PAM 2024 for work on data augmentation in traffic classification. Scientific Awards: Runner-up Best Paper Award at PAM 2024 Dr. Rossi collaborates actively with industry and academia, contributing to open-source tools and foundational research in probabilistic deep learning. His work bridges theory and practice, addressing challenges in scalable Bayesian methods and generative model efficiency.

Stefano Melacciمشاهده پروفایل

دانشیار

• Machine Learning
• Artificial Intelligence
• Computer Vision
• +۱۴ مورد دیگر

Stefano Melacci is an Associate Professor in the Department of Information Engineering and Mathematics (DIISM) at the University of Siena, Italy. He is a core member of the Siena Artificial Intelligence Laboratory (SAILab), where his research centers on Machine Learning and Artificial Intelligence, particularly in foundational and applied aspects of Computer Vision and Natural Language Processing. Department: Department of Information Engineering and Mathematics (DIISM) Institution: University of Siena Research Group: Siena Artificial Intelligence Laboratory (SAILab) He holds a PhD in Machine Learning from the University of Siena (2010), with prior research experience at Ohio State University. His career includes academic positions and industrial research at QuestIT, where he led NLP and conversational AI initiatives. His research interests lie at the intersection of deep learning and symbolic reasoning, particularly through the framework of Learning from Constraints . He investigates Kernel Machines, Regularization Theory, and cognitive models such as Developmental Visual Agents (DVA) and Cognitive Action Laws (CALs) . His work emphasizes motion invariance, visual attention, and continual learning. The recent publications highlight a strong trend in neurosymbolic AI, constraint-based learning, and biologically inspired neural computation. Key themes include explainability, adversarial robustness, graph neural networks, and efficient temporal modeling. His collaborative work with Marco Gori, Andrea Betti, and others demonstrates sustained innovation in hybrid AI systems. Scientific Contributions and Recognition: Author of foundational work on Laplacian SVMs trained in the primal (JMLR 2011) Co-author of the book Machine Learning: A Constraint-Based Approach (Elsevier, 2nd ed. 2024) Developer of PyTorch and MATLAB libraries for LapSVMs and cognitive vision models Active contributor to top-tier venues: NeurIPS, ICML, AAAI, IJCAI, IEEE TPAMI Stefano Melacci has advised numerous students in deep learning, continual learning, and neurosymbolic AI. His research is supported by sustained publication output and integration of theoretical and applied work. He teaches courses such as Neural Networks and Fondamenti di Programmazione at the University of Siena. He leads research within SAILab, focusing on cognitive vision, constraint propagation, and hybrid learning systems. His lab develops models that combine data-driven learning with symbolic knowledge, aiming to create more robust, interpretable, and human-like AI systems.