Noah Snavely is a Professor of Computer Science at Cornell Tech and the Cornell Ann S. Bowers College of Computing and Information Science. His research spans computer vision and graphics with a focus on 3D scene understanding from image collections. He also works at Google DeepMind in NYC and leads the Cornell Graphics and Vision Group. His research interests include computer vision and computer graphics , particularly in recovering 3D structure from large photo collections, neural radiance fields, image-based rendering, and scene understanding. His work enables applications in mapping technologies, immersive VR experiences, and synthesizing 3D worlds from text prompts with implications for game design and filmmaking. Recent publications show a strong trend toward generative 3D modeling and neural rendering , with significant contributions in neural radiance fields, view synthesis, and dynamic scene reconstruction. His research group explores unstructured photo collections to develop new technology for 3D world modeling and image analysis. PECASE Microsoft New Faculty Fellowship Alfred P. Sloan Fellowship SIGGRAPH Significant New Researcher Award ACM Fellow (2023) IEEE Fellow NSF CAREER Award Helmholtz Prize Snavely has mentored numerous PhD students and postdocs including Ruojin Cai, Qianqian Wang, and Zhengqi Li. His teaching includes CS5670: Computer Vision across multiple semesters. He has received the Cornell College of Engineering Mr. and Mrs. Richard F. Tucker Teaching Excellence Award (2012). At Cornell Tech, his research group develops technology for modeling the world in 3D from online photo collections and analyzing images for computer graphics applications. His work has been featured in major news outlets including the New York Times, New Scientist, and MIT Technology Review.
Lior Wolf is a Professor at the School of Computer Science, Tel Aviv University. Previously, he was a postdoctoral researcher at MIT's Center for Biological and Computational Learning (CBCL) under Prof. Tomaso Poggio and earned his PhD from Hebrew University of Jerusalem with Prof. Amnon Shashua. His educational background includes: PhD in Computer Science, Hebrew University of Jerusalem Postdoctoral Research, MIT CBCL Prof. Wolf's research centers on artificial intelligence with seminal contributions to deep learning, computer vision, and natural language processing. His work bridges theoretical foundations (e.g., attention mechanisms, transformer analysis) with practical applications in medical imaging, speech processing, and sign language technology. He pioneered methods for neural network interpretability, efficient sequence modeling, and multimodal fusion. Analysis of his 2023-2025 publications reveals dominant trends in large language model optimization (neuron pruning, attention analysis), efficient video generation, and cross-modal learning. His work increasingly integrates medical applications (fMRI/EEG analysis) while maintaining theoretical rigor in model architecture design. His scientific achievements include: Best paper award at EMNLP 2024 for 'Backward Lens: Projecting Language Model Gradients into the Vocabulary Space' Best paper award at SCIA 2023 for 'Gradient Adjusting Networks for Domain Inversion' Best paper award at FG 2021 for 'Generating Master Faces for Dictionary Attacks' Prof. Wolf mentors graduate students in the School of Computer Science and leads research at the ICRC building laboratory. His team collaborates with 'the friends of TAU' on projects spanning biometric security, medical imaging, and generative AI. Current work focuses on efficient transformers, neural network interpretability, and multimodal medical diagnostics.
Jacky Bourgeois is an Assistant Professor of Data-Centric Design at Delft University of Technology's Faculty of Industrial Design Engineering (IDE), leading the Data-Centric Delft Design Lab. His work bridges Human-Computer Interaction, Data Science, and Participatory Design, focusing on methods like data donation to empower collaborative data exploration. He holds a computer science background, previously researching ubiquitous technologies for domestic energy practices of 'energy farmers' (solar households). Key projects include the PROMISE study on patient-led oncological care and the Data Donation initiative promoting ethical data practices. Education: Background in Computer Science; academic focus on sustainable design engineering and IoT. Teaching includes courses like 'Data-Centric Design for...' (2024) and 'Digital Product Development' (2023). Research Interests: Data as subjective inquiry material, data intimacy, data commons, and human-data interaction in home contexts. Notable contributions include PAIRcolator for collaborative data reflection and Tangi for 360° video insights. Awards include Best Paper at CHI 2025 and DIS '24 Best Paper. Grants & Collaborations: NWO-funded research on hospital sounds (2024), IoT Rapid Proto Labs for industry-academia partnerships, and ancillary role as a scientific employee at The Open University (2025–2027). Labs & Teams: Director of the Data-Centric Delft Design Lab; collaborates with the HCI Data & Design SIG. Current projects address ethical frameworks for data donation and patient-centered healthcare systems.
Dr. Zara Ersozlu is a Senior Lecturer in Mathematics Education within the School of Education at the University of Newcastle, Australia. With a distinguished international career spanning multiple continents, she has held academic positions at prestigious institutions including North Carolina State University (USA), Gazi and Gaziosmanpasa Universities (Turkey), National Taiwan Normal University (Taiwan), The University of Western Australia, Murdoch University, and Deakin University. Her academic journey includes tenured positions as an Associate Professor and leadership roles as Department Head and Chair in teacher education disciplines. Currently, she teaches undergraduate and postgraduate courses in mathematics education, including Effective Pedagogies in Primary Mathematics, K-6 Mathematics, K-6 Numeracy, and Digitally Supported Learning. Dr. Ersozlu earned her Doctor of Philosophy from Firat University in Turkey and her Master of Art from Sakarya University. Her extensive academic preparation is complemented by five years of practical teaching experience in public schools prior to entering academia. This blend of theoretical knowledge and practical classroom experience informs her approach to teacher education and educational research. At the broadest level, Dr. Ersozlu's research investigates solutions to real-life problems impacting people's well-being, success, and capacity to achieve. Her scholarly work spans primary and secondary mathematics education, the psychology of mathematics (including metacognition, self-regulation, and anxiety), cross-cultural educational studies, teacher education, virtual simulated learning environments, and educational assessment. She has increasingly focused on the transformative potential of AI and machine learning in education, exploring how these technologies alter teaching, learning, and research processes. Her methodological expertise encompasses both quantitative and qualitative approaches, allowing her to effectively analyze both small and large educational datasets. Analysis of Dr. Ersozlu's recent publications reveals a strong emphasis on mathematics anxiety, teacher education, and the integration of technology in learning environments. Her work demonstrates a consistent focus on practical applications of educational research to address real-world challenges in mathematics education. The interdisciplinary nature of her research connects educational psychology, technology integration, and cross-cultural perspectives, with particular attention to how these elements intersect in teacher preparation and student learning outcomes. 2023 ATEA Research Recognition Award from the Australian Teacher Education Association 2021 Fellow of the Higher Education Academy (Advance HE, UK) 2010 Fellowship Program for Postdoctoral Researchers from the Council of Higher Education of Turkey Dr. Ersozlu is deeply committed to mentoring the next generation of scholars, currently supervising four PhD students and having successfully guided ten students to completion. Her grant portfolio includes significant funding for projects such as Best Practice Guidelines for RPL in Initial Teacher Education Programs ($60,000), Exploring the Reciprocal Relationship Between Mathematics Anxiety and Mathematical Resilience ($2,599), and multiple conference travel awards. She serves as an Associate Editor for several prominent journals including the International Electronic Journal of Mathematics Education and as Editor for Interdisciplinary STEM Education. Her editorial work reflects her standing as a respected voice in mathematics education research. Dr. Ersozlu's academic leadership extends to her role in developing innovative teaching approaches that integrate virtual simulation technology and learning analytics. Her work with TeachLivE™, a mixed-reality classroom simulation platform, demonstrates her commitment to creating authentic learning experiences for teacher education students. Through these initiatives, she bridges the gap between educational theory and classroom practice, preparing future educators to effectively implement evidence-based teaching strategies in diverse learning environments.
Dr. Kanchana Thilakarathna is a Senior Lecturer in Distributed Computing at the University of Sydney's School of Computer Science, and a member of the Centre for Distributed and High Performance Computing. They hold a PhD from the University of New South Wales (UNSW) and a B.Sc. Eng (Hons) from the University of Moratuwa, Sri Lanka. Prior to academia, they worked as a Research Scientist at CSIRO/Data61 and had industry experience as a Mobile Radio Network Engineer. Research Interests : Dr. Thilakarathna focuses on cybersecurity, privacy in mobile and IoT systems, mixed reality privacy, and distributed computing platforms. Their work emphasizes user-centric solutions like the Yalut social media app, which enables decentralized data sharing. Key themes include privacy-preserving techniques, edge computing, and secure federated learning frameworks. Recent Work : Recent articles (2023–2025) explore machine unlearning for large language models, federated learning security, and IoT network slicing using P4 programmability. Their work on synthetic video traffic generation (VideoTrain++) and drone detection (DronePrint) demonstrates cross-disciplinary innovation. Awards : Malcolm Chaikin Prize (2015), Meta Research Awards (2020/2022), and Heidelberg Laureate Fellowship (2019). Grants : ARC Research Hub for Future Digital Manufacturing (2024), NSW Defence Innovation Network Projects (2024/2021), and Facebook Research Awards (2022/2020). Students : Advising 4 current PhD students on topics like wireless trust establishment and machine unlearning. Labs/Teams : Part of the Centre for Distributed and High Performance Computing and Sydney Nano Institute.
Anand Bhattad is an Assistant Professor in the Department of Computer Science at Johns Hopkins University, starting Fall 2025. Previously, he held positions as a Research Assistant Professor at the Toyota Technological Institute at Chicago (TTIC) and a visiting scholar at UC Berkeley. His research focuses on the intersection of computer vision, generative modeling, and physical reasoning, aiming to develop perception-driven and physics-aware visual models. His academic journey includes a PhD in Computer Science from the University of Illinois Urbana-Champaign under David Forsyth, with mentorship from Derek Hoiem, Svetlana Lazebnik, Greg Shakhnarovich, and Shenlong Wang. Prior to his PhD, he earned dual master’s degrees in Computer Science and Civil and Environmental Engineering at UIUC and a bachelor’s in Civil Engineering from NITK Surathkal, India. Research interests center on how generative models encode physical and perceptual knowledge, with key contributions in intrinsic image emergence, projective geometry limitations, and physics-aware relighting techniques. His work bridges classical computer vision concepts with modern deep learning, producing state-of-the-art methods for 3D scene synthesis and image editing. Articles span topics like 3P Vision , diffusion models, and 360° video datasets, reflecting interdisciplinary approaches in computer graphics and computational photography. Scientific awards include Outstanding Reviewer at ICCV 2023, CVPR 2022 Best Paper Finalist, and multiple conference service roles as workshop organizer and area chair. He designed the TTIC course Past Meets Present: A Tale of Two Visions , teaching connections between historical and modern computer vision research.
Steven M. LaValle is a Professor at the University of Oulu's Faculty of Information Technology and Electrical Engineering since 2018. Previously, he held tenured positions at the University of Illinois Urbana-Champaign (UIUC) and was a Principal Scientist at Oculus VR. His research spans robotics, motion planning (notably pioneering RRT algorithms), virtual reality, and sensor fusion. He has authored influential textbooks like Planning Algorithms and Virtual Reality . Education: PhD (1995), MS (1993), and BS (1990) in Electrical Engineering from UIUC. Research Interests: Focuses on minimal information requirements for robots, perception engineering, and foundational VR/AR systems. His work integrates control theory, computational geometry, and human perception. Achievements: Recipient of the IEEE ICRA Milestone Award (2019), University Scholar (UIUC, 2012), and XTIC Award 2024 for Innovation. Leads the Perception Engineering Group at Oulu, advancing VR/AR and telepresence technologies. Grants & Industry: ERC Advanced Grant (2021–2026), former VP of Huawei's VR/AR division, and collaborator with institutions like IIT Madras. Advises startups in robotics and virtual reality.
Majed Elwardy is a Lecturer at the Department of Computer Science , Blekinge Institute of Technology , focusing on Computer Science , Virtual Reality , and Quality Assessment . He works at the Human-Centered Intelligent Realities Laboratory in Karlskrona, Sweden. Email: majed.elwardy@bth.se Phone: 0455-385801 His research investigates 360° video quality assessment in immersive environments using head-mounted displays (HMDs) , analyzing user behavior , quality perception , and subjective testing methodologies . He explores differences in standing vs. seated viewing and consistency of user feedback over time. Majed contributes to the HINTS project (Human-Centered Intelligent Realities) and has published datasets like RQA360 to advance immersive media research. His work includes studies on simulator sickness , VR experience levels , and scene exploration patterns in 360° video evaluation.
Professor Moncef Gabbouj is a distinguished academic and researcher currently serving as Professor of Signal Processing at the Department of Computing Sciences, Faculty of Information Technology and Communication Sciences, Tampere University, Finland. Previously, he held the same position at Tampere University of Technology before the merger in 2019. He has also held visiting professorships at prestigious institutions including Hong Kong University of Technology and Science, University of Southern California, and Purdue University. Ph.D. and MSc. in Electrical Engineering from Purdue University, USA (1989 and 1986) B.Sc. in Electrical Engineering from Oklahoma State University, USA (1985) Prof. Gabbouj's research spans multiple domains within signal and image processing, with a strong focus on machine learning applications. His primary research interests include artificial intelligence, machine learning, Big Data analytics, multimedia content-based analysis, indexing and retrieval, nonlinear signal and image processing, voice conversion, and video processing and coding. His work bridges theoretical advancements with practical applications across various industries, particularly in multimedia communications and biomedical applications. His extensive publication record demonstrates a clear evolution from traditional signal processing techniques toward more sophisticated machine learning and deep learning approaches. Recent work shows increasing focus on convolutional neural networks for various applications including ECG classification, video processing, financial time-series analysis, and image recognition tasks, reflecting the broader trend in the field toward deep learning methodologies while maintaining strong foundations in signal processing theory. IEEE Fellow (2011) Member, Finnish Academy of Science and Letters (2014) Knight, First Class, of the Order of the White Rose of Finland (2006) Nokia Foundation Recognition Award (2005) Nokia Foundation Visiting Professor Award (2012) Finnish Cultural Foundation for Art and Science Award (2017) TUT Foundation Grand Award (2015) Prof. Gabbouj has supervised 64 doctoral and 72 Master's theses, demonstrating his significant contribution to academic mentoring. His research has been supported by substantial funding, including research grants totaling 8.5 million Euro (2001-2015). He has served as Academy of Finland Professor during 2011-2015 and has been involved in numerous EU research projects including Horizon, ESPRIT, HCM, IST, COST, Tempus and Erasmus programs. As Editor, Guest Editor or member of the Editorial Board of 6 international scientific journals, he has significantly influenced the academic discourse in his field. He leads the Signal Analysis and Machine Intelligence (SAMI) research group at Tampere University and serves as the Finland Site Director of the NSF IUCRC funded Center for Visual and Decision Informatics. His research unit focuses on applying advanced machine learning techniques to solve complex problems in signal processing, computer vision, and multimedia analytics, with applications ranging from healthcare to multimedia communications and financial analysis.
Anna Abrahams is a Senior Programmer Artist Film and Artistic XR at Eye Filmmuseum in Amsterdam and teaches Moving Image at the Royal Academy of Art, The Hague, within the Photography department. She has been active in experimental film since 1989 as a co-founder of Rongwrong, an independent production foundation. Education: Studied film theory at the University of Amsterdam. Her research and practice focus on experimental film, virtual reality (XR), and moving image art. She bridges traditional film techniques (35mm, 16mm) with digital innovations, emphasizing immersive storytelling and artistic exploration of landscapes, urban spaces, and sociocultural themes. The films she has directed or co-directed, spanning 1995–2022, explore topics like psychogeography, counterculture, and digital experimentation. Her 2022 VR work Angels of Amsterdam highlights her engagement with extended reality technologies. As a co-author, she contributed to publications including Warhol Films , mm2. Experimental Film in the Netherlands , and film³ [kyü-bik film] , documenting avant-garde film practices and theoretical frameworks.
Ana Serrano is an Associate Professor at Universidad de Zaragoza, Spain, where she is affiliated with the Graphics & Imaging Lab in the EINA (Edificio Ada Byron) school. She earned her PhD at the same institution under the supervision of Prof. Diego Gutierrez and Prof. Belen Masia, and completed a postdoctoral fellowship at the Max-Planck-Institute for Informatics under Prof. Karol Myszkowski. Her research focuses on visual computing , particularly in computational imaging , material appearance perception and editing , and virtual reality . She is especially interested in developing perceptually-driven methods that leverage knowledge of the human perceptual system to enhance user experiences and assist content creation in immersive environments. Her recent publications (2023–2025) span top-tier venues such as SIGGRAPH, CVPR, IEEE TVCG, and Eurographics. These works explore topics like saliency prediction in 3D and 360° video, crossmodal perception in VR, gloss modeling, radiance fields, and perceptual evaluation of immersive content. The research demonstrates a strong integration of machine learning, human perception, and computer graphics to solve real-world problems in visual computing. She has received several prestigious awards, including: Eurographics 2023 Young Researcher Award VGTC VR 2024 Significant New Researcher Award Eurographics 2020 PhD Award Adobe Research Fellowship (honorable mention, 2017) NVIDIA Graduate Fellowship (2018) Ana Serrano actively supervises PhD and Master’s students and has taught courses such as Virtual Reality, Computational Imaging, and Deep Learning applications. She serves as an Associate Editor for Computer Graphics Forum , ACM Transactions on Applied Perception , and Computers and Graphics , and has held leadership roles in major conferences including Eurographics (Tutorials co-chair, 2023), ACM SAP (Program co-chair, 2022), and CEIG (Program co-chair, 2022). Her professional service includes extensive program committee and reviewer roles for SIGGRAPH, IEEE VR, ISMAR, and others. She leads a vibrant research group focused on human perception in virtual environments, with current projects on computational models of attention and perception, integrated with physiological signals. Her lab, the Graphics & Imaging Lab, fosters interdisciplinary collaboration and innovation in visual computing.
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.
Ariel Rogers serves as an Associate Professor in the Department of Radio/Television/Film at Northwestern University's School of Communication, where her research investigates the historical and theoretical dimensions of cinema and emerging media technologies with critical attention to spectatorship and technological change. Her academic credentials include a PhD in Cinema and Media Studies from the University of Chicago and a BA in Film Studies and Philosophy from Columbia University. Rogers' scholarship interrogates how historical contexts shape technological adoption and cinematic experience, challenging assumptions about media evolution through case studies spanning 1950s widescreen systems, digital cinema transitions, and contemporary virtual reality. Her work bridges film history, media archaeology, and screen theory to analyze dynamic relationships between technology, form, and audience engagement across diverse media landscapes. Publication trends reveal a sustained trajectory from historical analyses of screen technologies (2013-2019) toward immersive media frameworks, with recent scholarship (2022-2024) focusing on VR's reconfiguration of cinematic framing and spatial mediation—demonstrating continuity in examining how technological shifts redefine perceptual and narrative paradigms. Her research excellence has earned significant recognition: NEH Fellowship from the National Endowment for the Humanities (2022-2023) Clarence Simon Award for Outstanding Teaching and Mentoring (2019) ACLS Fellowship from the American Council of Learned Societies (2016-2017) Professor Rogers teaches foundational courses including RTVF 220 (Analyzing Media Texts), RTVF 312 (History of Film I), and RTVF 413 (Cultural History of New Media), integrating her research into undergraduate and graduate curricula. Her Clarence Simon Award highlights exceptional mentorship, while NEH/ACLS fellowships provided critical support for her monograph research. Current projects include a third book examining cinematic framing in virtual reality contexts. Affiliated with Northwestern's School of Communication, Rogers contributes to the Radio/Television/Film department's academic mission. The available documentation indicates no specific laboratory affiliations or team-based research initiatives beyond departmental collaborations.
Andrea Stevenson Won is a researcher at Cornell University in the Department of Communication , focusing on virtual reality (VR), human-computer interaction, and social dynamics in immersive environments. Her work explores avatar embodiment , nonverbal behavior , and accessibility in VR for users with disabilities. Research Themes : Virtual embodiment and its psychological effects Accessibility solutions for blind and low-vision users in social VR Nonverbal communication analysis in immersive environments Pro-social behavior through VR interventions Collaborative VR systems and AI integration Recent Article Trends : 2024: Investigated avatar behavior transformation in mixed reality ( MRTransformer ), AI-guided accessibility tools, and nonverbal cue adaptations 2023-2022: Focused on educational VR applications, 360° video narratives, and longitudinal team dynamics 2021-2014: Pioneered avatar embodiment studies, anxiety detection via movement tracking, and homuncular flexibility in VR
Roozbeh Mottaghi is a Senior AI Research Scientist Manager at Meta's Fundamental AI Research (FAIR) division and an Affiliate Associate Professor at the Paul G. Allen School of Computer Science & Engineering, University of Washington. His career spans roles as Research Manager at the Allen Institute for AI and Postdoctoral Researcher at Stanford University. He holds a Ph.D. in Computer Science from UCLA, advised by Alan Yuille, and advanced degrees from Simon Fraser University, Georgia Tech, and a B.Sc. from Sharif University of Technology. Ph.D., Computer Science, UCLA (2016) M.Sc., Computer Science, Simon Fraser University M.Sc., Electrical Engineering, Georgia Institute of Technology B.Sc., Computer Engineering, Sharif University of Technology His research focuses on Embodied AI, Robotics, Computer Vision, and Multimodal Learning, with key contributions to human-robot collaboration benchmarks (PARTNR), 3D scene understanding, and adaptive navigation systems. Recent work explores zero-shot manipulation via video tracking (Track2Act) and lifelong navigation benchmarks (GOAT-Bench). Publications span 3D vision, reinforcement learning, and visual reasoning, including NeurIPS 2022 Outstanding Paper Award for "Ask4Help" and leadership in organizing challenges at CVPR and ICCV workshops. He advises students and interns who have transitioned to leading institutions like AI2, Stanford, and Brown University.
