Chris Donahue is an Assistant Professor in the Computer Science Department at Carnegie Mellon University . He also serves as a part-time Research Scientist at Google DeepMind on the Magenta team. His work focuses on leveraging generative AI to enhance human creativity, particularly in music. Education: PhD in Computer Science (UC San Diego), Postdoctoral Scholar (Stanford University) His research spans controllable generative modeling of music and audio , with a focus on real-time interactive systems. Projects like Piano Genie , Beat Sage , and Copilot Arena demonstrate his commitment to real-world deployment. His Generative Creativity Lab (G-CLef) explores AI applications beyond music, including programming and natural language. Recent publications highlight advancements in multimodal music evaluation , real-time adaptation , and AI-driven sound morphing . He co-developed Magenta RealTime , an open-weight real-time music generation model, and MusicFX DJ Mode . Scientific Awards: Best Paper Award (top 1) at NAACL Student Research Workshop 2025 Best Paper Award (top 1% of submissions) at CHI 2025 Best Paper Runner-up at ISMIR 2021 He co-advises PhD students like Wayne Chi (NDSEG Fellow) and mentors Irmak Bukey . His lab receives support from the AIxArts incubator fund at CMU .
Prof. Matthias Nießner is a Professor at the Technical University of Munich , where he leads the Visual Computing Lab . Prior to this, he held a Visiting Assistant Professor position at Stanford University . His work bridges computer vision , graphics , and machine learning , focusing on 3D reconstruction , semantic scene understanding , and AI-driven video synthesis . Prof. Nießner has published over 150 works in top venues like SIGGRAPH , CVPR , and ECCV , with several receiving best paper awards (SIGCHI’14, HPG’15, SPG’18, SIGGRAPH’16 Emerging Tech). His research has garnered international media attention, including features in the New York Times , Wall Street Journal , and MIT Technological Review , as well as TV demonstrations (e.g., Jimmy Kimmel Live for Face2Face technology). Awards : TUM-IAS Rudolph Moessbauer Fellowship (2017–ongoing) Google Faculty Award (2017) Nvidia Professor Partnership Award (2018) ERC Starting Grant (2018, €1.5M) Eurographics Young Researcher Award (2019) Research Trends : 3D Gaussian Splatting for real-time rendering Neural Radiance Fields (NeRF) with mesh supervision Audio-driven facial animation via diffusion models Latent space diffusion for 3D scenes Self-supervised and zero-shot methods for 3D and image analysis As a co-founder and director of Synthesia Inc. , he drives democratization of synthetic media. His YouTube channel has over 5 million views, reflecting his impact beyond academia.
Professor Gabriel Brostow is a faculty member in the Department of Computer Science at University College London (UCL), where he leads research in Computer Vision and Human-Computer Interaction. He also serves as Chief Research Scientist and Senior Director of the R&D Team at Niantic, the company behind Pokémon GO. His work bridges academic research and industry applications, focusing on developing AI systems that enhance human capabilities through what he terms 'Human in the Loop AI'—now commonly referred to as Human-Centered AI. Brostow completed his BS in Electrical Engineering at UT Austin, followed by a PhD with Irfan Essa at Georgia Tech. He then pursued postdoctoral research with Roberto Cipolla's Computer Vision & Robotics Group at Cambridge University as a Marshall Sherfield Fellow, and with Marc Pollefeys in ETH Zurich's CVG Group. His research explores how AI, particularly Computer Vision, can serve as 'super-tools' for professionals across various domains including filmmaking, architecture, robotics, and scientific research. Specific interests include assistive technology for everyday life, authoring systems that maximize user effort, 3D reconstruction, depth estimation, and vision-language models. His work often involves creating systems that are validated through real-world human interaction to ensure practical utility. Analysis of his recent publications reveals a strong focus on practical applications of Computer Vision that directly interact with humans. His research spans 3D scene understanding, depth estimation, sketch-based interfaces, and multimodal AI systems. There's a clear emphasis on creating benchmarks and tools that facilitate human-AI collaboration, with applications in assistive technology, urban planning, filmmaking, and biodiversity monitoring. His work frequently appears at top conferences including CVPR, NeurIPS, ECCV, and CHI. Marshall Sherfield Fellowship Brostow actively mentors PhD students, with current advisees including Ross Murphy, Skanda Koppula, Gizem Unlu, Omiros Pantazis, and Jamie Watson. His alumni include numerous PhD graduates and MSc students who have gone on to successful careers in academia and industry. He emphasizes selecting students based on passion and potential rather than just academic credentials, valuing traits like helpfulness, drive, and hunger to learn. His research is supported through collaborations with major institutions and companies including DeepMind, MIT, and the University of Edinburgh. He leads a research group at UCL that collaborates closely with Niantic's R&D team, creating a unique bridge between academic research and industry application. His team's work frequently involves developing novel Computer Vision techniques that are validated through real-world human interaction, ensuring practical utility alongside technical innovation. The group explores blue-sky research problems with applications ranging from assistive technology to professional tools for filmmakers, architects, and scientists studying diverse environments.
Dr. Md Manjurul Ahsan serves as a Research Assistant Professor in the Department of Industrial & Systems Engineering at the University of Oklahoma, where he develops AI-driven solutions for healthcare diagnostics and advanced manufacturing optimization. His work bridges theoretical AI advancements with practical industrial and medical applications. Education: Ph.D. in Industrial and Systems Engineering, University of Oklahoma M.S. in Industrial Engineering, Lamar University B.S. in Industrial and Production Engineering, Shahjalal University of Science and Technology Research Focus: Dr. Ahsan specializes in Artificial Intelligence with technical depth in Machine Learning , Deep Learning , and Computer Vision to solve critical challenges in healthcare diagnostics and additive manufacturing . His research emphasizes Explainable AI to enhance model trustworthiness and deployment efficiency across Cyber-Physical-Social Systems, with significant contributions to Aerospace and Defense applications. Publication Trends: Recent work (2023-2025) reveals a strategic expansion from core manufacturing applications into medical AI (diffusion models for diagnostics), cultural preservation (NLP for Dravidian languages), and geopolitical AI analysis. His publications consistently address data imbalance challenges while advancing digital twin integration in quality control systems. Scientific Recognition: GCOE Dissertation Excellence Award (2023) International Student Scholarship (2022) Outstanding Academic Achievement in Engineering (2022) IEEE IEMCON Best Paper Award (2020) Netti Vincent Boggs Engineering Excellence Award (2020) Research Leadership: As director of the Sooner Additive Manufacturing Laboratory , Dr. Ahsan leads cross-disciplinary teams developing real-time monitoring systems using FARO arms and CMM metrology. His postdoctoral work at Northwestern University (2023-2024) advanced AI deployment frameworks, resulting in 60+ peer-reviewed publications with multiple papers ranking in engineering's top 1% for citations.
Toby Jia-Jun Li is an Assistant Professor in the Department of Computer Science and Engineering at the University of Notre Dame, where he leads the SaNDwich Lab. He also serves as the Director of the Human-Centered Responsible AI Lab in the Lucy Family Institute for Data & Society and is a Faculty Fellow at the Institute for Educational Initiatives (IEI). Previously, he was affiliated with Carnegie Mellon University's Human-Computer Interaction Institute (HCII) and GroupLens Research. Dr. Li's research spans the intersection of Human-Computer Interaction (HCI), End-User Software Engineering, Machine Learning (ML), and Natural Language Processing (NLP), with recent work focusing on addressing societal challenges in the future of work through human-AI collaborative approaches. His work has resulted in over 40 publications at premier venues including CHI, UIST, CSCW, ACL, and ICSE, with 8 papers winning Best Paper or Honorable Mention awards. His recent publications demonstrate a strong focus on human-AI collaboration across various domains, including code understanding, privacy, accessibility, and creative tools. The work shows a trajectory toward increasingly sophisticated integration of human-centered design with AI capabilities, particularly using large language models to enhance human productivity and address societal challenges. Google Research Scholar Award recipient Recipient of Yahoo! Fellowship ($100,000/year) Best Paper Award at UIST 2020 Best Paper Honorable Mention Award at CHI 2021 Best Paper Award at CSCW 2024 Best Paper Award at CHI 2025 Dr. Li actively mentors Ph.D. students and has established collaborations with Google, Microsoft Research, IBM Research, Adobe, Verizon, and J.P. Morgan. His research has been supported by NSF, Google Research Scholar Program, AnalytiXIN Initiative, Yahoo! InMind project, and J.P. Morgan. He is currently recruiting Ph.D. students and undergraduate researchers for his SaNDwich Lab, which focuses on developing interactive systems to empower individuals to create, configure, and extend AI-powered computing systems.
Ira Kemelmacher-Shlizerman is a Full Professor of Computer Science at the Paul G. Allen School of Computer Science & Engineering at the University of Washington and Director of the UW Reality Lab. She also serves as a Principal Scientist at Google, where she leads the Shopping Gen AI visuals teams focusing on Virtual Try-On, 3D, and product videos. Her research spans computer vision, computer graphics, and Generative AI, with particular contributions to virtual try-on technology, 3D modeling, and augmented reality applications. Professor Kemelmacher-Shlizerman's research interests focus on Generative AI applications in visual computing. Her work bridges the gap between theoretical computer vision and practical applications, particularly in e-commerce and virtual reality. She has made significant contributions to virtual try-on technology, 3D editing with generative models, and AI applications for shopping experiences. Her research combines deep learning with traditional computer vision techniques to solve challenging problems in image and video synthesis. Her recent publications demonstrate a strong trend toward Generative AI applications for visual shopping experiences, virtual try-on technology, and 3D content creation. The work spans multiple top conferences including CVPR, SIGGRAPH, and ICCV, with a focus on practical applications of computer vision and graphics. Her research has evolved from foundational work in face reconstruction and aging to current applications in virtual shopping and 3D content generation. Google faculty award Madrona prize GeekWire Innovation of the Year Award Covers of CACM and SIGGRAPH Best student paper honorable mention at CVPR'21 Best demo runner up MobiSys'22 Senior member of IEEE Distinguished Member of ACM Professor Kemelmacher-Shlizerman has successfully tech-transferred multiple research projects to industry. She founded Dreambit, a startup acquired by Meta, and previously built and launched the Face Movies feature at Google. She currently leads Google's Shopping Gen AI visuals teams, focusing on 10x improvements to shopping journeys. Her UW Reality Lab serves as a hub for AR/VR research with industry partnerships. She has mentored numerous PhD students who have become researchers in both academia and industry, with several publications featuring student co-authors receiving recognition at top conferences. Professor Kemelmacher-Shlizerman leads the Graphics and Imaging Laboratory (GRAIL) and the UW Reality Lab, which focuses on augmented and virtual reality research with industry partnerships including Google. The labs work on cutting-edge projects in virtual try-on, 3D modeling, and immersive experiences, bridging academic research with real-world applications.
Marco Pedersoli serves as an Assistant Professor at École de technologie supérieure (ETS) in Montreal since February 2017, where he leads research in computer vision and machine learning. His work focuses on reducing computational costs and annotation requirements for deploying vision algorithms on embedded devices, positioning ETS at the forefront of Montreal's AI ecosystem. His academic journey includes: Ph.D. from Autonomous University of Barcelona (UAB) under Jordi Gonzàlez and Juan José Villanueva Post-doctoral research at INRIA Grenoble with Cordelia Schmid and Jakob Verbeek (2015-2016) Research at KU Leuven with Tinne Tuytelaars (2012-2015) Dr. Pedersoli's research tackles deep learning bottlenecks through weakly-supervised methodologies and computational efficiency innovations . His three core projects address: Reduced Supervision : Developing weakly/semi-supervised learning for images, video, audio and text Exploration Learning : Optimizing data selection in unstructured environments Efficient Computation : Accelerating deep learning training and inference These efforts enable vision algorithms to run on resource-constrained portable devices. Publication trends (2014-2022) reveal consistent focus on weak supervision (60% of works) and computational efficiency (30%), with recent expansion into medical imaging and multimodal emotion recognition. Key venues include CVPR, ICCV, NeurIPS and ECCV. His accolades include: Best Paper Award at ICIAR 2019 NVIDIA Titan X Pascal hardware donation Dr. Pedersoli actively mentors 18 graduate students across PhD and MSc programs, with notable placements at Huawei and Radio Canada. His lab secures competitive tax-free funding for projects with international collaborations, including Element AI and European institutions. Current openings emphasize Python/C++ proficiency and deep learning expertise. He leads a dynamic research group at ETS developing open-source tools for Roi-Pooling, weakly-supervised detection, and 3D object recognition, maintaining active GitHub repositories with community contributions. Recent WACV 2023 acceptances demonstrate ongoing productivity following medical leave.
Dr. Martha Sidury Christiansen is a Professor of Applied Linguistics/TESOL at the University of Texas at San Antonio , where she serves in the College of Education and Human Development . She is the Principal Investigator of Project RESPETO , a NSF-funded initiative exploring racial equity in engineering education. Her work spans sociolinguistics, digital literacies, and raciolinguistic analysis, with a focus on transnational multilingual communities. Born in Veracruz, Mexico Ph.D. in Foreign/Second Language Education (Ohio State University, 2013) M.A. in English Composition (Indiana University, 2007) B.A. in English Language Teaching (Universidad Veracruzana, 2002) Her research examines how transnational youth navigate digital spaces through multiliteracies , challenges Western academic writing norms via Mexican decolonial methodologies , and investigates raciolinguistic intersections in identity formation. The 15 most recent publications reveal a strong focus on digital communication , transnationalism , and critical pedagogy across journals like TESOL Quarterly and Language@Internet . 2023-2025: Expanding raciolinguistic frameworks in digital contexts 2021-2022: Analyzing multimodal identity construction 2019-2020: Exploring Mexican bilinguals' online language use She has received multiple honors including ACUE Fellow (2023), Fulbright Scholar (2017), and Faculty Leadership Fellow (2021-2022). Her presentations at conferences like ICOLLITE and DDVM Lab highlight her expertise in critical sociolinguistic awareness and digital discourse analysis . Dr. Christiansen actively consults for nonprofits on linguistic equity and multilingual education .
Professor David Taubman is a distinguished academic serving as Professor and Deputy Head of School (Research) at the School of Electrical Engineering and Telecommunications (EE&T) at the University of New South Wales (UNSW) in Sydney, Australia. He is also co-director of Kakadu Software Pty. Ltd. and its affiliates Kakadu R&D and Kakadu GPU. With a career spanning over three decades, Professor Taubman has made significant contributions to the field of image and video compression, most notably as the author of the EBCOT coding algorithm adopted in the JPEG2000 international standard. Professor Taubman earned his B.Sc. in Mathematics and Computer Science (1986) and B.E. (Medal) in Electrical Engineering (1988) from the University of Sydney, followed by an M.Sc. (1992) and Ph.D. (1994) in Electrical Engineering from the University of California at Berkeley. His professional journey includes engineering work at the Electricity Commission of N.S.W. (1988-1990), research positions at Hewlett-Packard Laboratories in Palo Alto (1994-1998), and an academic career at UNSW where he progressed from Senior Lecturer (1998-2003) to Associate Professor (2004-2009) and finally to Professor (2009-present). He has held various leadership roles including Head of the EE&T Telecommunications Research Group (2003-2014), Head of the EE&T Signal Processing Research Group (2014-present), Director of Research for the School of EE&T (2011-2016), and Deputy Head of School (Research) since 2017. Professor Taubman's research interests center on image and video compression, with particular expertise in JPEG2000 standards and implementations. His work spans signal processing, wavelet transforms, scalable video coding, motion modeling, and multimedia systems. He has pioneered numerous compression algorithms and frameworks, including the EBCOT coding algorithm that became central to the JPEG2000 standard. His recent research focuses on efficient motion modeling with cuboidal partitioning, learned lifting-based transform structures, and high-throughput implementations of JPEG2000 for video applications. His work bridges theoretical foundations with practical implementations, as evidenced by the commercially successful Kakadu Software tools that have garnered around 500 commercial licensees. Analysis of Professor Taubman's recent publications reveals a consistent focus on advancing compression technologies with particular emphasis on scalability, efficiency, and adaptability. His work spans traditional image compression (JPEG2000 extensions), video coding (cuboid-based partitioning for UHD/360-degree video), and emerging applications (nanopore sequencing data compression). A notable trend is the integration of machine learning techniques with traditional compression frameworks, as seen in his work on learned lifting-based transform structures. His research maintains strong connections to real-world applications across diverse domains including medical imaging, astronomical data processing, and genomic sequencing. IEEE Fellow Engineers Australia Fellow (by invitation) Professor Taubman has served as Associate Editor for the IEEE Transactions on Image Processing for two four-year appointments (2003-2005 and 2010-2013). He has been actively involved in numerous research grants focused on image and video compression technologies, particularly those related to the JPEG2000 standard and its extensions. His work has received significant industry support, reflected in his consultancy with various U.S., Japanese, and Australian corporations. He has also contributed to international standards development as a member of Standards Australia Technical Committee MS-065 (mirroring ISO TC42 on Digital Photography) and as a constitutional member of Standards Australia Technical Committee IT-029 (Coded Representation of Picture, Audio and Multimedia/Hypermedia Information). Professor Taubman co-directs Kakadu Software Pty. Ltd. and its research affiliates Kakadu R&D and Kakadu GPU, which have developed the commercially successful Kakadu Software tools for JPEG2000. His research group at UNSW focuses on advanced image and video compression techniques, with particular expertise in wavelet-based methods, scalable coding, and motion modeling. The group maintains strong industry connections and has contributed significantly to the development and standardization of image compression technologies worldwide.
Can Güler is an Assistant Professor in the Department of Lifelong Learning and Adult Education at the Faculty of Education, Anadolu University, Turkey. Previously, from 2002 to 2023, he served as a Lecturer in the Department of Distance Education at the Faculty of Open Education, Anadolu University. His academic career spans over two decades with continuous contributions to open and distance education systems. His educational background includes: Bachelor's degree in Computer and Instructional Technologies Education, Anadolu University (2002) Master's degree in Distance Education, Institute of Social Sciences, Anadolu University (2007) Ph.D. in Distance Education, Institute of Social Sciences, Anadolu University (2022) Güler's research centers on open and distance learning methodologies, educational technology integration, and instructional material development. He specializes in video-based learning systems, interactive media design, and gamification strategies for enhancing learner engagement. His work addresses practical challenges in digital content creation and accessibility for diverse learner demographics, particularly adult populations. Analysis of his publication trajectory reveals consistent innovation in multimedia applications for distance education, with recent emphasis on generative AI awareness among educators and interactive video transformation techniques. His research frequently employs design-based methodologies and institutional case studies from Anadolu University's open education infrastructure. Scientific Awards: None mentioned in available sources. Advising and Grants: No information provided regarding student supervision or research funding in current documentation.
Joseph Johnson is an Associate Professor in the Marketing department at the Miami Herbert Business School, University of Miami. His research spans multiple domains of marketing with a particular focus on the intersection of artificial intelligence and marketing strategy, demonstrating significant scholarly productivity with publications from 2017 through 2023. Professor Johnson's research interests include: Marketing Strategy and Business Turnaround Artificial Intelligence Applications in Marketing Healthcare Service Quality and Patient Satisfaction International Business Expansion Strategies Mutual Fund Advertising and Consumer Perception Organizational Process Optimization Social Media and Multimedia Content Analysis His publication record reveals a consistent trajectory toward integrating advanced analytical methods with traditional marketing challenges. Johnson has published extensively on applying predictive analytics to email marketing effectiveness, healthcare service quality improvement, and organizational process efficiency. His work bridges theoretical marketing concepts with practical business applications across diverse industries including finance, healthcare, and international business, with several publications appearing in top-tier journals such as Journal of the Academy of Marketing Science and Marketing Science. Johnson's research has garnered attention across academic and professional platforms, with his publications being referenced in patents and discussed on social media and news outlets. His collaborative approach is evident through co-authorship with researchers from healthcare, computer science, and neuroscience fields.
Koray Tahiroglu is a University Lecturer at Aalto University's School of Arts, Design and Architecture, specializing in Sound and Music Computing. His work bridges artificial intelligence, digital musical instruments, and embodied interaction, with a focus on deep learning applications in audio synthesis and human-AI creative collaboration. His research explores New Interfaces for Musical Expression (NIME), sonic interaction, and physical computing. He collaborates with SOPI Research Group and Google Brain Team (Magenta) on AI-driven artistic innovation. Recent Publications : 2024 studies on dance-sound cross-correlation and intra-action frameworks; 2023 work on AI-terity and deep learning syllabi; 2022 explorations of GAN synthesis, musical expectations, and lifeworld sonification. Scientific Awards : Co-Creative Artificial Intelligence of Music (2022) 2010 grant for scientific publications and artistic activities 2017 Honorable Mention for mobile cultural heritage research Tahiroglu contributes to digital art education and leads projects at Media Lab Helsinki, advancing sonic interaction and generative audio systems.
Sophie Seita is a London-based artist, researcher, and Lecturer in Fine Art & History of Art at Goldsmiths, University of London, where she also serves as Director of Critical Studies for the BA Fine Art Extension Degree and Deputy Director of Research for the Department of Art. Her interdisciplinary practice spans performance, video, sound, textiles, books, and installations, with language as a central material. Previously, she was a tenure-track Assistant Professor at Boston University (2019-2022) and a Junior Research Fellow at Queens' College, University of Cambridge (2016-2019). Seita's research interests encompass lecture-performances, poetic essays, video essays, practice-based research, queer studies, trans studies, affect theory, disability studies, deaf studies, creative access, experimental captions and audio descriptions, speculative approaches to archives, fictional collectives, concepts of play, difficulty, opacity, absurdity, ornamentation, deep listening, histories of avant-garde group formation, translation studies, multilingualism, queer ecology, decolonial ecology, and experimental pedagogy. Her creative curiosities include opacity, playfulness, difficulty, artifice, queer abstraction, minor genres, ornamentation, materiality beyond objects, the materiality of language, listening beyond hearing, ambiguity, non-linear narratives, and provisional ideas. Her recent publications demonstrate strong trends in examining the intersections of performance, language, and experimental publishing, particularly focusing on lecture-performances as critical knowledge production, the materiality of language, and speculative approaches to archives. Her work consistently engages with queer and feminist perspectives on avant-garde practices while exploring experimental forms of documentation and presentation. Werner Düttmann Fellowship at Akademie der Künste Berlin (2024) Vice-Chancellor's Public Engagement Award (University of Cambridge) Eccles Centre Fellowship (British Library) PEN/Heim Translation Award Wonder Book Prize Dorothea Schlegel Artist in Residence Seita supervises and examines PhD projects at Goldsmiths and has secured numerous research grants, including funding from the British Academy, Arts Council England, Canada Council for the Arts, and the Early Career Research Fund Award from Goldsmiths. She is co-founder of The Hildegard von Bingen Society for Gardening Companions, an ongoing queer collaborative project with musician Naomi Woo that explores speculative archives and queer ecology through sound, performance, and publications. Her artistic practice often involves collaborative work across disciplines, particularly with The Hildegard von Bingen Society for Gardening Companions, which creates experimental pedagogical frameworks and community-based environmental projects.
Professor Adrian Hilton is a distinguished faculty member at the University of Surrey, serving as Director of the Centre for Vision, Speech and Signal Processing (CVSSP) and Director of the Surrey Institute for People-Centred AI. He is affiliated with the School of Computer Science and Electronic Engineering and leads the Visual Media Research Lab (V-Lab). His research focuses on pioneering next-generation 4D computer vision technologies that enable machines to understand and model dynamic real-world scenes. Key areas include 3D/4D shape capture, computer vision, machine learning, graphics, and animation for applications in sports analysis, film/TV production, virtual reality, and medical imaging. His work bridges the gap between real and computer-generated imagery, with notable contributions in volumetric capture, motion capture, and free-viewpoint video. Hilton's recent publications demonstrate a strong trend toward multimodal integration, particularly combining audio and visual processing for spatial audio applications, while advancing 4D reconstruction techniques for human performance capture. His work increasingly incorporates transformer architectures and neural rendering techniques for improved illumination estimation, shadow modeling, and multi-view consistency. Scientific Awards and Recognition Two EU IST Innovation Prizes Manufacturing Industry Achievement Award Royal Society Industry Fellowship (2008-2011) Royal Society Wolfson Research Merit Award in 4D Vision (2013-2018) Fellow of the Royal Academy of Engineering (FREng) Fellow of the International Association for Pattern Recognition (FIAPR) Fellow of the Institution of Engineering and Technology (FIET) Hilton actively mentors PhD and post-doctoral researchers through his leadership of CVSSP, which has a grant portfolio exceeding £31M and comprises 170 researchers. He has successfully commercialized several technologies, including systems used by the BBC for sports commentary visualization. His research collaborations span major industry partners including BBC, BT, Sony, Framestore, and The Foundry. He co-founded the G3 Games forum and the CVMP Conference on Visual Media Production, demonstrating strong engagement with the creative industries. Current research projects include the S3A Programme Grant in Future Spatial Audio and InnovateUK's ALIVE project for 360 video reconstruction.
Paolo Prandoni is a Lecturer at École Polytechnique Fédérale de Lausanne (EPFL) in the School of Computer and Communication Sciences (IC). He serves as a Scientist in the Audiovisual Communications Laboratory (LCAV) and teaches in the SSC-ENS and SIN-ENS units, focusing on signal processing theory and practical applications in audiovisual communications. He earned his PhD from EPFL after completing all prior education there, driven by childhood fascination with long-distance telephony. His doctoral work established foundations in communication systems that continue to inform his research. Prandoni's research spans audio/image processing, machine learning for media analysis, and DSP education. Key areas include computational photography (e.g., spectral imaging, stained glass rendering), speech quality assessment via transfer learning, music information retrieval (e.g., fingering prediction), and audience analytics through his company Quividi. His work consistently bridges theoretical signal processing with real-world implementation. Recent publications reveal a strategic shift toward machine learning integration in signal processing tasks, particularly non-intrusive speech assessment and lensless imaging reconstruction. Simultaneously, he advances DSP pedagogy through MOOC development and hands-on teaching tools using off-the-shelf hardware, emphasizing accessibility and practical skill development. No scientific awards are documented in the provided materials. He has advised PhD student Thanikachalam Niranjan (thesis: Image Based Relighting of Cultural Artifacts , 2016) and teaches Communication Systems and Computer Science courses. His educational impact extends through the open-access textbook Signal Processing for Communications (2008) and tools like MultiPub for maintainable online classes. Industry engagement includes Quividi co-founding (2006) and ongoing CSO role in attention analytics. As a core LCAV laboratory member, he collaborates on interdisciplinary projects including cultural heritage digitization, embedded signal processing systems, and real-time audience measurement, leveraging EPFL's infrastructure for both academic and commercial applications.
