Industry Expert Talks

IET #1

Title: How Generative AI Understands the Balance of Energy, Efficiency, and Human Experience

Speaker: Tomoya Sawada (Principal Researcher, Mitsubishi Electric Corporation, Japan)

Abstract:

Generative AI is rapidly moving beyond content creation to interact with and control the physical world. This talk presents “Office-in-the-Loop,” a pioneering cyber-physical system designed to bridge this gap. We developed this platform to test various generative AI paradigms—including LLMs, Multimodal Foundation Models (MFMs), and Agentic AI—in a live office environment.

We will explore how these different AI models can reason over a diverse set of real-time inputs, from environmental sensor data and occupancy patterns to subjective human comfort feedback, in order to dynamically optimize HVAC operations.

Our real-world deployment using LLMs successfully overturned the long-standing trade-off between energy and comfort, achieving up to a 48% reduction in energy consumption while simultaneously improving comfort by 26%. Furthermore, our simulations show that an Agentic AI approach holds the potential for an even greater 51% energy reduction.

A separate but crucial technical novelty of our work is “Data-Driven Reasoning.” This breakthrough prompt engineering technique addresses a fundamental challenge for industrial applications: the inherent instability of numerical predictions from generative AI. We will show how this method drastically improves prediction stability for critical tasks like optimal temperature forecasting, paving the way for reliable AI-driven control systems.

Attendees will gain practical insights into the challenges and opportunities of applying different generative AI models to real-world industrial systems. We will conclude by discussing the scalability of this approach to critical infrastructures like data centers, paving the way for the next generation of intelligent, autonomous systems.

Bio: Dr. Tomoya Sawada is a Principal Researcher at Mitsubishi Electric, where he pioneers the real-world application of Agentic AI. His work focuses on bridging the gap between cutting-edge AI research—including Transformers, LLMs, and Multimodal Foundation Models—and its deployment in critical domains like building automation, manufacturing, and automotive. His recent research project, “Office-in-the-Loop,” was recognized as a top-tier paper at ACM BuildSys 2024 and is slated for publication in the Data-Centric Engineering journal. Holding over 30+ patents and having collaborated with institutions like MIT, USC, and UTokyo, Dr. Sawada is dedicated to building the next generation of Cyber-Physical Systems (CPS). He is a member of IEEE and received his Ph.D. in Computer Science from the University of Yamanashi.

IET #2

Title: Will AI Make Agencies Obsolete? Rethinking the Future of Advertising

Speaker: Aleks Farseev (CEO, SOMIN.AI, Singapore)

Abstract: With the rise of generative AI, the advertising industry is undergoing one of the most radical transformations in its history. From Meta’s vision of fully automated ad pipelines – requiring no creatives, no targeting, and no human input – to Google’s more collaborative “AI as co-creator” model, the role of marketing agencies is under intense scrutiny. Are agencies at risk of extinction, or are they evolving into something even more valuable? In this talk, Prof. Aleks Farseev – entrepreneur, Marketing Community Leader @ Forbes Technology Councils, and CEO of SOMIN – examines three dominant paradigms shaping the future of AI in advertising: Replacement, Empowerment, and Insight. Drawing on real-world examples from Meta, Google DeepMind, and SOMIN’s own AI platform SOMONITOR, he explores how each model redefines creativity, strategy, and human input. While some platforms automate the entire creative and targeting process, others embed structure to enhance user agency and strategic thinking. And emerging solutions focus not on content generation, but on delivering data-driven insights to guide campaign design and positioning. Far from being rendered obsolete, agencies have a chance to redefine their purpose: moving from execution to orchestration. The agencies of the future will not just produce content – they’ll configure AI systems, curate AI outputs, and protect brand integrity, ethics, and cultural relevance. Ultimately, this talk is a call to action for agencies: embrace your new role as AI facilitators and strategic consultants. In an age of automation, creativity with context – and emotional intelligence – will become the new currency of value. Agencies won’t die. But they must evolve – or risk irrelevance.

Bio: Prof. Aleks Farseev is a distinguished luminary in both entrepreneurship and academia. Renowned as a top-tier researcher and international keynote speaker, he stands as the driving force behind SoMonitor.ai – a cloud platform leveraging AI and Large Language Models for Competitor Analytics and Ad Optimization. His expertise shines not only as CEO but also as a Research Professor, where he adeptly imparts wisdom on Digital Marketing, Large Language Models, and AI Technology. Through courses offered in esteemed universities across the Globe and over 30 publications in top-tier conferences, Prof. Farseev ensures that the path to mastery is both accessible and enlightening.

IET #3

Title: MedAI Hub: A Multimodal Medical Data Platform with Evolutionary Image Enhancement and Graph-Driven Literature Retrieval

Speaker: Guoming Wang (Founder, Zhejiang Mingji Technology Co., Ltd., China)

Abstract: We present MedAI Hub, an integrated multimodal medical platform designed to bridge clinical practice and research by transforming patient-doctor interactions into structured scientific data. This platform supports comprehensive management of multimodal medical records—including clinical notes, medical images, and patient-reported outcomes—while implementing privacy-preserving data sharing mechanisms. Building upon this infrastructure, we introduce two novel AI-driven modules: (1) ITERATE (Image-Text Enhancement, Retrieval, and Alignment): An evolutionary algorithm inspired by Visual Genome that optimizes medical image-text alignment through iterative cross-modal refinement. Leveraging LLM-guided “DNA evolution” and multimodal feedback, ITERATE enhances ultrasound image quality for diagnostic tasks, achieving 3.5–7% accuracy gains on ScienceQA and ARC-Easy benchmarks.(2) MedQuery: A graph-driven literature retrieval system that constructs multimodal knowledge graphs from medical literature (text, figures, tables). By aligning PubMed documents with complex clinical queries through semantic relationship modeling, it achieves >90% answer quality win rates and 13–36% accuracy improvements on PubMedQA and MedInquiry datasets. MedAI Hub demonstrates that synergistic integration of clinical data platforms with evolutionary vision-language optimization and multimodal knowledge graphs significantly advances medical AI capabilities, enabling more accurate diagnostics and research insights. The platform and algorithms are publicly available to accelerate innovation in medical AI.

Bio: Dr. Wang Guoming, an Assistant Professor at Zhejiang University, specializes in multimodal intelligence, privacy-preserving machine learning, and ML applications; he earned his B.S./M.S. from Zhejiang University’s College of Computer Science and his Ph.D. (2020) from Nanyang Technological University (Singapore), where his doctoral research focused on cryptographic applications, differential privacy, homomorphic encryption, and privacy-preserving e-health systems. Since joining Zhejiang University in 2020, he has worked on multimodal machine learning and retrieval-augmented, reasoning-driven large language model applications, publishing 20+ papers in top venues (e.g., CVPR, AAAI, ACL, ACM MM, Coling, ICMR, GlobalCom, IEEE Transactions on Multimedia) over the past two years. As a key member of Zhejiang’s “Pioneer and Leading Goose” project and Ningbo Major Projects (leading sub-tasks), he now focuses on AI healthcare initiatives—including intelligent medication management and smart chronic disease systems—leveraging multimodal ML for disease prediction (e.g., migraines, pancreatic cancer, cardiovascular/pulmonary infections, diabetic nephropathy).

IET #4

Title: To Advance People’s Well-Being: Human health sensing, analysis, and applications

Speaker: Terumi Umematsu (Principal Researcher, NEC Corporation, Japan)

Abstract: This talk presents research on estimating health status from facial video analysis, focusing on non-invasive approaches to support well-being. The talk introduces robust estimation methods from facial videos for health- and well-being? related indicators and real-time systems capable of simultaneously estimating vital signs such as heart rate, respiration, blood oxygen level, blood pressure, and pulse variability. It also explains the feasibility of estimating states such as drowsiness and stress from facial videos. These techniques utilize widely available devices such as smartphones and PCs, enabling continuous and low-burden monitoring in daily life. By demonstrating the feasibility of vision-based health estimation across various contexts, this work highlights its potential for preventive healthcare, workplace well-being, and telemedicine applications.

Bio: Terumi Umematsu is a Principal Researcher at the Biometrics Research Laboratories of NEC Corporation. She joined NEC in 2013, where she has conducted research on speech recognition, physiological signal processing, and minimally invasive methods for estimating and forecasting stress levels using wearable sensors. Her current work focuses on modeling mental and physical states by analyzing biological data derived from facial videos. She has made significant contributions to the fields of affective computing, signal processing, and machine learning, authoring over 30 scientific publications. She received the Best Paper Award (1st Prize) at the 2019 IEEE International Conference on Biomedical and Health Informatics. She holds 24 registered patents. Dr. Umematsu earned her Doctor of Philosophy (Ph.D.) in 2024, her Master of Engineering (M.Eng.) in 2013, and her Bachelor of Engineering (B.Eng.) in 2011, all from Waseda University, Japan. She was a visiting researcher at the Massachusetts Institute of Technology (MIT) from 2017 to 2019. Since 2024, she has served as a visiting researcher at RIKEN. Since 2022, she has also served as Secretary and Committee Member of the IEEE Women in Engineering Tokyo Section, and a Committee Member of the Institute of Electronics, Information and Communication Engineers (IEICE) Technical Group on Signal Processing.

IET #5

Title: Advancing Lung Cancer Diagnosis with eyonis®LCS

Speaker: Benoit Huet (VP, Median Technologies, France)

Abstract:

The integration of AI/ML technologies into medical imaging is revolutionizing radiology, offering transformative benefits in clinical workflows. AI-powered Software as a Medical Device (SaMD) solutions not only reduce workload and optimize image interpretation but also unlock critical insights previously undetectable by human eyes—catching the unseen and enabling earlier, more accurate diagnoses.

Lung cancer, the leading cause of cancer-related mortality worldwide, is often diagnosed at a late stage, when curative treatment is no longer viable. Early detection is paramount. Traditional screening methods rely heavily on nodule size and growth as indicators of malignancy. However, these criteria alone are insufficient for identifying cancer at its earliest, most treatable stage.

eyonis®LCS, the flagship clinical development program of Median Technologies, represents a next-generation AI/ML-based SaMD designed specifically for lung cancer screening [1][2]. It combines Computer-Aided Detection (CADe) and Computer-Aided Diagnosis (CADx) [3][4] capabilities to support clinicians in identifying malignant nodules with greater precision. By leveraging specified architectural choices and deep learning models, eyonis®LCS enhances diagnostic accuracy beyond the current standard of care [5], offering a paradigm shift in early lung cancer detection [6].

This presentation will delve into some of the architectural foundations of eyonis®LCS, highlight its clinical impact, and demonstrate how it empowers radiologists to diagnose lung cancer when patients can still be cured. Through this pioneering technology, Median Technologies is redefining the future of cancer screening and patient outcomes.

1. Baudot P., Voyton C., De Bie G., Le V.K., Francis D., Geremia E., Renoust B., Siot P.H., Liu Y., Huet B., “End to end model for nodule detection and characterization in lung cancer screening: performances and subpopulation analysis”, NACLC, Journal of Thoracic Oncology 19 (7),  https://doi.org/10.1016/j.jtho.2024.05.151
2. Baudot, P., Voyton, C., Francis, D., Baili-Laya, A., Bobin, V., Renoust, B., Liu, Y., Iannessi, A., Huet, B., “Development and Validation of a Machine Learning Based CADx Designed to Improve Patient Management in Lung Cancer Screening Programs” In: Proceedings of ECR 2023. Vienna
3. Huet B., Francis D., Baudot P., “Method and system for computer aided diagnosis using ensembled 2D and 3D neural networks based on medical images”, US Patent 11,810,299.
4. Munoz E., Baudot P., Le V.K., Voyton C., Renoust B., Danny Francis, Vladimir Groza, Jean-Christophe Brisset, Ezequiel Geremia, Antoine Iannessi, Yan Liu, and Huet B. “3D-Morphomics, Morphological Features on CT Scans for Lung Nodule Malignancy Diagnosis”. In Cancer Prevention Through Early Detection: First International Workshop, CaPTion 2022, Held in Conjunction with MICCAI 2022, Singapore, September 22, 2022, Proceedings. Springer-Verlag, Berlin, Heidelberg, 3–13. https://doi.org/10.1007/978-3-031-17979-2_1
5. Baudot P, C. Voyton, E. Geremia, P-H Siot, G. De Bie, V.K. Le, D. Francis, B. Renoust, B. Huet; “Performances Of An End-To-End AI Model For Nodule Detection And Characterization In Lung Cancer Screening On Independent Cohort And Comparison To Radiologists”, RSNA 2024, December 2024
6. Bodard S, P Baudot, B Renoust, C Voyton, G De Bie, E Geremia, V-K Le, D Francis, P-H Siot, Y Haddou, V Bourdès, and B Huet, “Rethinking Lung Cancer Screening: Longitudinal AI/ML Diagnostics Beyond Nodule Size Growth”, accepted for oral presentation at RSNA 2025, December 2025

Bio: Dr. Benoit Huet joined Median Technologies in 2019 where he holds the position of VP AI Engineering and Research, managing a team of talented multicultural and multidisciplinary individuals composed of Clinical Data Managers, Data and Knowledge Engineers and Data Scientists. He was previously Assistant Professor in the Data Science Department of Eurecom (France) from 1999 to 2019.  During his academic career, he visited both IBM T.J. Watson and National University of Singapore as Visiting Researcher. He obtained the HDR (Habilitation to Direct Research) from the University of Nice Sophia Antipolis (France) in October 2012 on the topic of Multimedia Content Understanding: Bringing Context to Content. He received his DPhil degree in Computer Science from the University of York (UK) for his research on the topic of object recognition from large databases. He was awarded the MSc degree in Artificial Intelligence from the University of Westminster (UK) with distinction in 1993. He authored and co-authored over 200 publications in Books, Journals and Conferences, gave many keynotes and took part in several panels on AI and Multimedia at major international events. He chaired a number of international conferences: such as IEEE MIPR2021, ACM Multimedia 2019, MMM2019, PCM2014 and multiple workshops. Benoit was chairing the IEEE MMTC Interest Group on Visual Analysis, Interaction and Content Management from 2010-1014. He served as associate editor for several journals, IEEE Multimedia Magazine, IEEE Transaction on Multimedia, Multimedia Tools and Application (Springer) and Multimedia Systems (Springer). He regularly served on the technical program committee of the top conference of the field (ACM MM/ICMR, IEEE ICME/ICIP). His current research interests include AI for Healthcare, Multimodal Analysis and Fusion, Large Scale Medical Image Analysis, Mining and Indexing.

IET #6

Title: Spark LLM and the Scientific Research it empowers: Practice and Thoughts

Speaker: Xin Li (VP of AI Research Institute, iFLYTEK, China)

Abstract: The 2024 Nobel Prizes in Chemistry and Physics have once again drawn global attention to AI for Science. The rise of foundation models has further accelerated AI for Science across multiple disciplines. Scientific research is both a touchstone for advancing the intelligence of these models, and the models themselves are accelerators that empower scientific research. As a high-tech enterprise deeply engaged in artificial intelligence, iFLYTEK has in recent years made AI for Science (AI4S) a strategic priority and undertaken a series of initiatives. In this talk, Dr. Xin Li will provide a comprehensive overview of the iFLYTEK Spark Large Language Model and highlight its recent advances. He will outline two principal pathways through which AI accelerates scientific research—deep neural networks and LLM-based approaches—and present iFLYTEK’s work along both lines. In addition, he will discuss key challenges and the outlook for the future development of AI for Science. Attendees will gain insights into how AI empowers scientific research and gain inspiration in their own scientific field.

Bio: Xin Li, Ph.D. and the senior engineer, is the vice president of the AI Research Institute and the head of the R&D department of iFLYTEK. He obtained his Ph.D. degree from and served as postdoctoral researcher and associate professor at the University of Science and Technology of China (USTC), and was a visiting scholar at the University of Technology Sydney (UTS). He is also a researcher at the National Key Laboratory for Cognitive Intelligence, the life member of International Communication Association (ICA), the senior member of China Computer Federation (CCF), the member of the Executive Committee of the CCF’s Big Data Committee, the member of council in the China Association of Standardization (CAS), the deputy director of Brain-Computer Interface and Brain-inspired Intelligence Special Committee of CAS, and the vice chairman of the System and Industry Application Group in Brain-Computer Interface Alliance (BCIA). He is also a young expert of the China Internet Society, a standing director of Anhui Artificial Intelligence Society and a founding editor of the Journal of Natural Language Processing, and received “The Young 30” honor of Brain Science and Brain-like Intelligence, KSEM, CIKM, SDM best paper/runners up award. He is mainly responsible for the research and application of artificial intelligence technologies, including cognitive neuroscience and scientific intelligence (AI4S). He also serves as a reviewer for international conferences and journals such as KDD, AAAI, ACL, NeurIPS, and WWW. He has led and participated in over 10 research projects, including the strategic leading project of the CAS, 2030 Program and the key research and development programs of the Ministry of Science and Technology of China, along with several funds of Natural Science Foundation of China. He has published more than 60 papers in top international academic conferences and well-known journals, and filed over 60 patents.

IET #7

Title: Sovereign & Shared: Frugally Scalable Multilingual–Multimodal AI for Bharat

Speaker: Maneesh Singh (Director of Research, BharatGen, USA)

Abstract: The movement for Sovereign AI is accelerating. Meeting its promise requires vertically integrated AI stacks—spanning data, models, and reasoning systems—that remain sovereign while adhering to shared scientific principles around which global research communities can coalesce. This talk presents BharatGen as a sovereign-yet-shared effort to make AI work for the many: creation of datasets, benchmarks, and models that natively support Indian languages, dialects, and code-mix across text, speech, and vision; data pipelines grounded in local realities; and frugal methods that reduce cost and lower barriers. We outline our journey to date across language infrastructure, efficient training and distillation, and early sector pilots. The R&D deep dive will draw from some of our recent work on cross-lingual knowledge distillation for low-resource languages, tokenization/phonetic design for code-mix robustness, or trustworthy document AI with visual grounding focusing on robustness under dialect/code-mix shift, and latency/cost trade-offs. We hope to inspire other Sovereign-AI efforts, especially in the low-resource ecosystems of the Global South and close by inviting international collaborations toward principled research to build people-serving AI.

Bio: Dr. Maneesh Kumar Singh is a senior AI researcher and innovation leader with over 25 years of experience spanning industrial R&D labs and startups. He is currently the Director of Research (act.) at BharatGen, focusing on building frugally scalable, multilingual–multimodal AI systems. He previously served as the founding Head of AI Research at Spector.AI and SnowMountain.AI.  He’s also the founder and President of an AI collaborative called Indic AiDias where he provides pro bono research mentoring to young professionals and graduate students, and guidance to corporate leadership on AI strategy. From 2016–2022 he was Head of AI & Global Research at Verisk, where he built enterprise-scale AI programs across vision, language, audio, and simulation. Dr. Singh’s R&D spans robust perception, vision and language, generative modeling, and trustworthy agentic AI. He has built and deployed AI systems for multiple business sectors: Industrial AI, fintech (insurance, banking, energy sectors), security and surveillance, medical imaging and diagnostics, automatic driver-assistance and intelligent traffic systems. He has authored over 65 research articles and has 40 patent filings. He is a senior member of the IEEE, a senior program committee member at several AI conferences, and has served on the NSF SBIR/STTR panels. He has provided guidance on 10+ graduate theses and has mentored 50+ graduate students. He received his Ph.D. from UIUC and has previously held senior R&D roles at Siemens, SRI International, and Comcast.

IET #8

Title: Toward Fast and Exact Machine Learning Platform for Big Data

Speaker: Yasuhiro Fujiwara (Distinguished Researcher, NTT, Inc., Japan)

Abstract: Data has become the foundation of knowledge, and many companies are growing interested in harnessing AI-based data analysis to unlock its value. The volume of digital data is increasing at an unprecedented pace: market research reports estimate that global data volume, approximately 12.5 zettabytes in 2014, will reach around 180 zettabytes by 2025. Extracting patterns and trends from such big data is crucial for enabling data-driven decision-making. However, a key challenge lies in the enormous computational costs required for large-scale analysis, due to the inherent complexities of the task. Approximate methods are often employed to reduce these costs, but they inevitably trade exactness for efficiency. To overcome this limitation, our research aims to develop a machine learning platform that delivers both speed and accuracy. The core of our platform is computational pruning. This talk will introduce three representative pruning strategies. Specifically, it first introduces a pruning method that uses upper and lower bounds to omit computations. This method efficiently identifies unnecessary processes by using upper and lower bounds of scores to skip unnecessary computations. Next, this talk introduces a method to terminate computations that cannot yield solutions. This method maintains patterns that failed during the search process to avoid repeated futile searches. This talk finally introduces a method that prunes computations through optimistic processing. This method temporarily removes a constraint to find a solution quickly and then verifies if the obtained solution meets the constraint. These strategies open the path to data analysis techniques that are both efficient and exact, ultimately empowering companies to make more reliable and timely decisions in today’s increasingly data-driven world.

Biosketch: Dr. Yasuhiro Fujiwara is a Distinguished Researcher at NTT Communication Science Laboratories. He received his B.E. and M.E. degrees from Waseda University in 2001 and 2003, respectively, and his Ph.D. from the University of Tokyo in 2012. He joined NTT Cyber Solutions Laboratories in 2003 and is leading the Recognition Research Group in the Media Information Laboratory at NTT Communication Science Laboratories. His research interests include databases, data mining, artificial intelligence, and machine learning. He is a member of IEICE, IPSJ, and DBSJ.

IET #9

Title: Video Content Restoration in the Wild: Challenges and Opportunities

Speaker: Guan-Ming Su (Director, Dolby Labs, USA)

Abstract: This industry expert talk will discuss the challenges and opportunities for video content restoration in the real world. Owing to the limitations of content creation devices (such as camera types, sensor, spatial resolution, frame rate, color gamut, etc) and content delivery systems (such as transmission bandwidth and storage capacity) from the past different decades, the perceived video content by end users suffers different levels of quality degradation. Restoring the video content to high fidelity quality in a modern look is highly desired for both professional (e.g. archival content) and personal (e.g. user generated content) usages. However, existing video restoration solutions often focus on the well-defined single degradation model and the corresponding developed tools can only manage the restoration to certain level. In real-world applications, most video contents suffer multiple unknown types of degradation, and more often unknown order of encountered degradation, which makes developing practical video restoration tools much more difficult. This talk will first review the latest technologies for single degradation solutions, such as film grain management, video compression artifact reduction, and color transfer. Then, we will examine the current “all-in-one” solutions for a multi-degradation scenario.  With those contexts, we will highlight the future directions for a practical video restoration framework.  In summary, the goal of this talk is to enable the MM’25 attendees to understand the latest technology for video restoration applications. The other goal is to enable more discussion for the video restoration works in MM’25, and hope this talk can assist attendees to identify the potential research topics along those directions and inspire more innovative solutions and technical papers to MM’26.

Bio: Guan-Ming Su received the Ph.D. degree from the University of Maryland, College Park. He is currently the Director of Image Tech Dev with the Dolby Laboratories, Sunnyvale, CA, USA. Prior to this, he has been with the Research and Development Department, Qualcomm Inc., San Diego, CA; ESS Technology, Fremont, CA; and Marvell Semiconductor Inc., Santa Clara, CA. He is the inventor of more than 210 U.S./international patents and pending applications. He is one of the recipients of 2020 (72nd) Technology and Engineering Emmy Award and 2021 (73rd) Engineering Emmy Award Philo T. Farnsworth Award for the contribution to high dynamic range (HDR) and wide color gamut (WCG) video as Dolby Vision format.  He was the Director of the review board and R-Letter in IEEE Multimedia Communications Technical Committee. He also served in multiple IEEE international conferences, such as the TPC Co-Chair in ICME 2021, the Industry Innovation Forum Chair in ICIP 2023 and 2025, and the General Co-Chair in MIPR 2024 and 2025. He served as a VP for industrial relations and development in APSIPA, from 2018 to 2019. He has been serving as the Vice Chair for Conference in IEEE Technical Committee on Multimedia Computing (TCMC), since 2021. He served as an Associate Editor for Asia Pacific Signal and Information Processing Association (APSIPA) Transactions on Signal and Information Processing, and IEEE MultiMedia Magazine.

IET #10

Title: Research and Standardization Trends in Compression and Transmission Technologies for 3D Point Cloud

Speaker: Keisuke Nonaka (Senior Manager, KDDI Research, Inc., Japan)

Abstract: The demand for 3D spatial information is rapidly increasing across a wide range of industrial fields. For instance, 3D point cloud data is being actively adopted in sectors such as construction, civil engineering, and disaster prevention to enhance work efficiency and safety. However, 3D point cloud data typically involves extremely large data volumes, which presents a significant challenge; as a result, rapid sharing and utilization over public networks have yet to be fully realized. To address these issues, we are engaged in research and development of compression and transmission technologies for 3D point clouds, as well as contributing to international standardization. In this talk, as part of our initiatives aimed at industrial applications, we will present the latest trends in the international standardization of 3D point cloud compression technologies, such as Geometry-based Point Cloud Compression, and introduce case studies from demonstration experiments utilizing these technologies.

Biosketch: Keisuke Nonaka received his Ph.D. in Information Processing from the Tokyo Institute of Technology, Japan, in 2014. He joined KDDI Corporation in the same year and has since worked as a researcher in the fields of image processing and computer vision. In 2019, he was a visiting scholar at the University of Southern California, where he conducted research on graph signal processing. He is currently a Senior Manager at the 3D Space Transmission Laboratory, KDDI Research, Inc. His research interests include immersive video experiences, point cloud compression, and computer-generated holograms.

IET #11

Title: Multimodal Content Creation, Consumption and Distribution

Speaker: Ting Yao (Co-Founder & CTO, HiDream.ai, China)

Abstract: In the wave of Artificial Intelligence, along with the proliferation of mobile devices, digital content has been generated and published in an explosive way. Digital content is inherent multimodal: text, image, audio, video, etc. How to effectively and efficiently automate the entire multimodal content lifecycle from idea, to creation and distribution is therefore of great importance. In this talk, we will first delve into the core technological breakthroughs in multimodal content generation, particularly the latest advancements in image and video generation tasks. Then, we will present an agent-based solution from HiDream.ai to interpret user intention and manage content creation—from ideation to final distribution—using three core, interconnected agents. In between, the Content Creation Agent takes a simple user prompt, instantly comprehends the creator’s intention, and accurately sources relevant assets from content platform to create multimodal content. Such way frees creators to focus on the story, not the software. The Self-evolving Platform Agent translates global trends and user preferences into strategic directives, guiding models to autonomously generate high-impact content and continuously enriching the platform’s ecosystem. The Distribution Agent adapts multimodal content for various social media platforms and analyzes its performance after publishing. Together, these intelligent agents create a seamless ecosystem to connect creators, content and consumers.

Bio: Dr. Ting Yao is currently the Co-Founder and CTO of HiDream.ai, a high-tech startup company working on generative intelligence in China. Previously, he was a Principal Researcher with JD.com and a Researcher with Microsoft Research Asia. Dr. Yao has co-authored more than 100 peer-reviewed papers in top-notch conferences/journals, with 20,000+ citations. In particular, his Pseudo-3D Residual Net has become one standard 3D CNN for video understanding. His video-to-text dataset (MSR-VTT) has built the foundation for video generation and has been used by 500+ institutions worldwide. He is the architect of HiDream-I1 image generative model, which tops the authoritative Artificial Analysis Image Arena leaderboard within 24 hours of its open-source release and has surpassed 1 million downloads in Hugging Face. His research has also led to several ground-breaking products in Microsoft, JD.com and HiDream.ai with millions of daily active users. Dr. Yao is an active member of the editorial boards of the IEEE Transactions on Pattern Analysis and Machine Intelligence (2025-present), IEEE Transactions on Image Processing (2024-present), IEEE Transactions on Multimedia (2019-2023), ACM Transactions on Multimedia Computing, Communications, and Applications (2024-present), and Pattern Recognition Letters (2022-present), and frequently serves as an area chair and keynote/tutorial speaker in numerous conferences. He has organized 10+ high-quality workshops/challenges with the flagship conferences. His works have led to many awards, including 2015 ACM SIGMM Outstanding Ph.D. Thesis Award, 2019 ACM SIGMM Rising Star Award, 2019 IEEE Computer Society TCMC Rising Star Award, 2022 IEEE ICME Multimedia Star Innovator Award, and the winning of 10+ championships in international competitions.