Program
Conference Schedule
All times are local to Ann Arbor (EDT). The program is subject to change.
Thursday, October 29, 2026
Coffee and Breakfast
Conference Welcome
Coffee Break
Public Infrastructure, Policy, and DX
A Global Comparison of Schemas, Transparency, and Interoperability in Public-Sector AI Registers and Inventories
Universal Internet Access at What Cost? Predicting Drivers of Funding Allocation under the Broadband Equity, Access, and Deployment (BEAD) Program
Toward Practical Venous Industry Digital Transformation: Lessons from a Long-term Deployment of City-scale Municipal Waste Sensing
Lunch
Power, Energy, and Grid-Integrated Computing
Interactive Power Flow in the Browser
From Barrier to Bridge: The Case for AI Data Center/Power Grid Co-Design
Synthesizing Voltage Ride-Through Controllers for Data Centers
Coffee Break
Comparing the Performance of Electric Vehicle Aggregation Models Under Driver Behavioral Uncertainty
Interpretability of Multi-Agent Reinforcement Learning Models in Power System Operations
Friday, October 30, 2026
Coffee and Breakfast
Conference Welcome
Coffee Break
Water and Community Utilities
Toward Agent-Native Water Systems: A Case Study of the Digital Transformation of a 2,300-square-kilometer Watershed, its Sensors, Dams, and the People Who Control Them
WaterAdmin: Orchestrating Community Water Distribution Optimization via AI Agents
Privacy-Preserving Leak Detection Across Water Utilities via Secure Multi-Party Statistics
Lunch
Scott James
Operational Intelligence, Edge, and Industrial Systems
Houston, We Have a Workload: Orchestrating Industrial Control over Satellite Computing Networks
Real-Time Indoor Localisation using Passively Captured Wi-Fi Probe Requests
ROOTS: A Community-Centered Reference Architecture for Continuous Operational Intelligence in Digital Transformation
Closing Remarks
Networking Session with Coffee & Snacks
Keynotes
Towards Precise, Autonomous, and Sustainable Agriculture
Jie Liu
Chair Professor, Harbin Institute of Technology
Abstract
Digital technologies, especially amplified by recent advances in the Internet of Things and artificial intelligence, are rapidly changing the landscape of agriculture. In this talk, we will discuss challenges of applying digital technologies in complex agriculture environments, especially on closing the loop. Then, discuss how intelligent sensing, agent-based decision making, and autonomous operations are becoming tangible with generalizable AI models and agents. We share experiences designing modern smart farms towards using less people, less resources, yet producing high yield at scale. We also lay out future challenges in both AI technologies and farming processes to accelerate future agriculture transformation.
Biography
Jie Liu is a Chair Professor at Harbin Institute of Technology (HIT), and the Dean of its Institute of Artificial Intelligence. He is also the Director of the National Key Laboratory of Smart Farm Technologies and Systems. Before joining HIT, he was a Partner Research Manager at Microsoft Research, Redmond. His research interests include Cyber-Physical Systems and Internet of Things, intelligent sensing and reasoning, and autonomous systems. He received IEEE TCCPS Distinguished Leadership Award, the Microsoft Gold Star Award, UC Berkeley Leon O. Chua Award, and 8 Best Paper Awards. He is an IEEE Fellow and ACM Distinguished Scientist.
Back to scheduleDigital Transformation for Manufacturing: From Data-Driven Insights to the Autonomous Plant
Pugal Janakiraman
Industry Principal – Manufacturing, Snowflake
Abstract
Manufacturers are racing to put AI agents to work. But one common belief, “deploy agents and your data will sort itself out,” keeps stalling pilots before they reach production. In this session, Pugal Janakiraman shows how leading automotive, heavy trucking and aerospace manufacturers are building the foundation that agentic AI needs.
The talk has three parts. It begins with the pillars of the agentic enterprise: governed data and context, AI model choice, connected applications and a single control plane for agents. It then explores what is possible across the product development process, from R&D and validation through manufacturing, supply chain and connected products. Finally, it goes onto the plant floor. There it tackles the realities of Industry 4.0: siloed IT and OT data, tags with no context, and tribal knowledge that leaves with retiring workers.
Attendees will see how a Unified Namespace organizes plant data by meaning. They will also see how an ontology layered on top turns that data into a knowledge graph that agents can reason over. A live example follows a single pump fault from alert through root cause to autonomous action, closing in seconds a loop that once took a team hours. The session ends with a practical crawl-walk-run path to the autonomous plant.
Biography
Pugal Janakiraman is Industry Principal – Manufacturing at Snowflake. He launched Snowflake’s Manufacturing Cloud and drives the solution vision for manufacturing by mapping Snowflake technology components to build higher-order solutions within the manufacturing domain. He also drives partner strategy for manufacturing and works with strategic C-level audiences at manufacturing customers as a sponsor for key digital transformation initiatives.
For the last three decades, he has worked with the world’s top auto, trucking, heavy machinery, and aerospace OEMs, healthcare, and oil & natural gas companies, including companies in mainland China. Before Snowflake, he led worldwide business development around industrial IoT at Amazon Web Services and led the PLM, BOM, Digital Twin, and Real Time Operational Intelligence practice areas at Siemens.
Back to scheduleScaling Intelligence in the Real World
Theo Papadopoulos
Head of Siemens Industrial Metaverse Lab
Abstract
Industrial AI is moving from isolated demonstrations into the engineering and operating workflows of the physical world. The strategic challenge is no longer simply to deploy more powerful models, but to connect intelligence with industrial context, computing infrastructure and accountable execution.
This keynote explores how digital twins, simulation, industrial copilots, automation and the device-to-cloud computing continuum can work together to improve industrial decisions. The discussion also considers the convergence of simulation, high-performance computing and AI, and the physical power infrastructure needed to scale computing.
The keynote concludes with a practical agenda for leaders and researchers: anchor applications in measurable outcomes, preserve engineering context, make deployment and lifecycle ownership explicit, and evaluate what can be reused across sites and domains. Its central argument is that the next phase of digital transformation will be defined not by the volume of AI deployed, but by the ability to turn intelligence into repeatable improvements in the real world.
Biography
Theo Papadopoulos studied Mechanical Engineering at the National Technical University of Athens and completed an MBA in Innovation & Business Creation at the Technical University of Munich. He is a strategic technology and innovation leader at Siemens with 15+ years of experience across R&D, business development, technology strategy and digital transformation at Siemens. He is the Founder and Head of the Siemens Industrial Metaverse Lab, leading co-creation, rapid prototyping and executive engagement across AI, digital twins, smart glasses and XR technologies. He combines hands-on technology understanding with business impact, ecosystem leadership and the ability to translate emerging capabilities into practical opportunities, strategic roadmaps and executive decision support.
Back to scheduleScott James
Talk title, abstract, and biography to be announced.
Back to scheduleAccepted Papers
-
A Global Comparison of Schemas, Transparency, and Interoperability in Public-Sector AI Registers and Inventories
-
Comparing the Performance of Electric Vehicle Aggregation Models Under Driver Behavioral Uncertainty
-
From Barrier to Bridge: The Case for AI Data Center/Power Grid Co-Design
-
Houston, We Have a Workload: Orchestrating Industrial Control over Satellite Computing Networks
-
Interactive Power Flow in the Browser
-
Interpretability of Multi-Agent Reinforcement Learning Models in Power System Operations
-
Privacy-Preserving Leak Detection Across Water Utilities via Secure Multi-Party Statistics
-
ROOTS: A Community-Centered Reference Architecture for Continuous Operational Intelligence in Digital Transformation
-
Real-Time Indoor Localisation using Passively Captured Wi-Fi Probe Requests
-
Synthesizing Voltage Ride-Through Controllers for Data Centers
-
Toward Agent-Native Water Systems: A Case Study of the Digital Transformation of a 2,300-square-kilometer Watershed, its Sensors, Dams, and the People Who Control Them
-
Toward Practical Venous Industry Digital Transformation: Lessons from a Long-term Deployment of City-scale Municipal Waste Sensing
-
Universal Internet Access at What Cost? Predicting Drivers of Funding Allocation under the Broadband Equity, Access, and Deployment (BEAD) Program
-
WaterAdmin: Orchestrating Community Water Distribution Optimization via AI Agents