Osoro, Ogutu B., Jingjing Li, Ming Tang, Xi Chen, Kelly Merrill, Lauren Forbes, Briana L. Simms, Paris Wheeler, Clementine Adeyemi, and Diego F. Cuadros. “Family Specific Spatial Borrowing in Multimodal Urban Reconstruction: A Leave-One-Neighborhood-Out Study of Cincinnati.” Computers, Environment and Urban Systems 132 (2027): 102541.https://doi.org/10.1016/j.compenvurbsys.2026.102541.
Family Specific Spatial Borrowing in Multimodal Urban Reconstruction: A Leave-One-Neighborhood-Out Study of Cincinnati.
Urban spatial models often assume that nearby borrowing improves prediction across target variables, but this assumption is rarely tested across distinct urban feature families within a city. We evaluate this question on a citywide hexagonal grid of Cincinnati, Ohio (2016 cells, 60 features in 14 feature families) using multimodal masked reconstruction. We compare four models spanning linear, local nonlinear, shared-gate graph, and selective-gate graph architectures under full leave-one-neighborhood-out evaluation across 50 neighborhoods, with primary summaries for the 36 neighborhoods having at least 20 cells. Median held-out-neighborhood R2 is the primary comparison metric. Cross-neighborhood transfer is family-specific, and no single borrowing strategy dominates. Ridge performs best for street structure, indicating that some spatially regular families are best reconstructed from local linear combinations. The local nonlinear masked autoencoder (MLP-MAE) holds the highest median for most families with positive transfer, though these differences are not statistically distinguishable from the graph models, indicating that local nonlinear multimodal fusion is often sufficient. Graph-based models help most clearly for topography, while the selective-gate graph model wins many individual neighborhood comparisons for several families despite lower medians, reflecting different error profiles. Graph models also produce more neighborhood-structured representations: contextual embeddings from the selective multimodal spatial autoencoder (SMSA) recover neighborhood structure better than raw principal components or local-only embeddings. Learned gates are stable across folds and provide interpretable diagnostics of context reliance, but not a universal ranking of borrowing regimes. These results show that the appropriate spatial borrowing strategy is target-specific rather than universal. For neighborhood-scale interpolation, imputation, and urban monitoring, one spatial modeling recipe can systematically misrepresent some feature families even within the same city.
https://i1.wp.com/ming3d.com/new/wp-content/uploads/2026/10/CEAUS.jpg?fit=247%2C192192247Ming Tanghttp://ming3d.com/new/wp-content/uploads/2022/01/TY_logo-300x300-new.pngMing Tang2026-10-23 03:23:232026-10-23 03:43:37paper in Computers, Environment and Urban Systems
Metaverse of Simpson’s Victory City Reconstruct & Reimaging of Orville Simpson’s Vision of Urban Futures using AI
Ming Tang. $4500. Supported by SAID Simpson Urban Futures Grant Program. UC. 8. 2026-8. 2027
This project works on the AI-creation of an online Metaverse by reconstructing and reimaging Orville Simpson’s visionary “Victory City.” Using archival materials from the Simpson Collection—including drawings, paintings, and manuscripts—the project will generate digital interpretations of Simpson’s future city through AI-assisted visualization and 3D modeling. The platform will allow users to explore a multiplayer virtual city accessible through web browsers, mobile devices, and VR headsets. In addition to a virtual reconstruction of Victory City, the project will include a digital gallery presenting Simpson’s archival works and a digital installation at the Simpson Center, reintroducing Simpson’s ideas as a contemporary dialogue on sustainable urban futures.
The goal of this project is to translate Simpson’s visionary urban concepts into an interactive 3D digital environment that allows the public to experience and interpret his ideas spatially. Although Simpson’s online archive contains extensive drawings and models, these materials remain largely static. This project transforms them into an immersive platform where users can explore the spatial logic of Victory City. The project emphasis:
AI-assisted visualization: generative AI tools will be used to produce architectural imagery, animations, and 3D models inspired by Simpson’s designs.
Construction of a Metaverse environment: a browser-based immersive environment will be developed to represent major elements of Victory City, including the central 102-story tower and the larger metropolitan system described in Simpson’s writings.
By Stephen Luo + AI. Victory City VIZ.
https://i1.wp.com/ming3d.com/new/wp-content/uploads/2026/08/victorycity.jpg?fit=841%2C539539841Ming Tanghttp://ming3d.com/new/wp-content/uploads/2022/01/TY_logo-300x300-new.pngMing Tang2026-08-19 18:21:482026-10-17 19:55:02Victory City
AI research agents increasingly support ideation, literature search, coding, experimental execution, analysis, and manuscript drafting across the scientific workflow. This progress advances automated discovery, but workflow automation is not scientific cognition. Scientific reasoning is cumulative and path-dependent: it depends on what a researcher has written, read, learned from critique, absorbed through experience, and used as habitual standards for judging novelty, rigor, feasibility, and significance. We propose Mnemo as a framework for modeling scientific cognition in AI research agents. First, scientific cognition may require differentiated memory, organized into distinct spaces for authored work, external reference, critique, experience, and judgment. Second, provenance should be treated not as passive metadata but as memory routing, because source origin helps determine cognitive function in reasoning. Third, new ideas may be better modeled as controlled collisions across memory spaces, filtered by judgment, rejection, and epistemic calibration, than as generic recombination from model priors. Mnemo motivates a research agenda for AI in science centered on routing fidelity, critique use, judgment alignment, rejection quality, and epistemic calibration.
https://i0.wp.com/ming3d.com/new/wp-content/uploads/2026/08/frontiers.jpg?fit=332%2C307307332Ming Tanghttp://ming3d.com/new/wp-content/uploads/2022/01/TY_logo-300x300-new.pngMing Tang2026-08-06 13:59:092026-09-09 01:26:21paper in Frontiers
SENSE–AI: Developing Spatial Experiences through Narrative, Senses, and Emotions with AI
ARCH 4001 studio. SAID, DAAP, UC.
This SENSE-AI design studio invites students to explore the complex relationship between architecture, human emotion, cultural heritage, and experiential design through the conceptualization and design of a new museum at Fort Ancient, part of the UNESCO-listed Hopewell Ceremonial Earthworks. Using an AI-assisted design approach, students will explore how generative AI, computational analysis, digital heritage, and immersive technologies can support research, site interpretation, design ideation, visualization, and evaluation throughout the architectural design process. Students will investigate how spatial design can evoke, mediate, and communicate the histories, stories, and cultural significance of Fort Ancient—moving beyond functionality to create environments that resonate on psychological, sensory, and emotional levels. By integrating AI-assisted design with architecture, landscape, Indigenous cultural narratives, storytelling, and digital heritage, students will develop proposals for a museum that serves not only as a cultural and educational institution, but also as a place of reflection, empathy, discovery, and connection to the earthworks and surrounding landscape.
The studio examines how space can evoke memory, shape emotion, and deepen our understanding of history and culture. Students use AI-assisted design, Extended Reality (XR), and immersive visualization as design tools to explore ideas, test spatial experiences, and communicate narratives. Through digital modeling, virtual reality, and interactive media, they develop and evaluate architectural experiences that engage visitors on sensory, emotional, and cultural levels.
Working closely with the Fort Ancient team, students create museum proposals that tell the stories of Native American communities through research, design exploration, immersive prototyping, and narrative development. Building on the parallel research project Re-Story Fort Ancientand the 2025 SENSE studio, the 2026 studio emphasizes thoughtful design, interdisciplinary collaboration, and emerging technologies as means of creating meaningful places that connect people with history, culture, and one another.
This studio is supported by the Gensler Award. Gensler is a global architecture, design, and planning firm. Founded in 1965, Gensler has built a team of 6,000 professionals who partner with clients in over 100 countries each year on projects that act as catalysts for growth. We are deeply grateful for Gensler’s support.
Site: Fort Ancient Earthworks, Hopewell UNESCO World Heritage Site, Ohio
Program: Museum.
Before Meaning: Encountering Fort Ancient
Ming Tang, with the assistance of GPT
I enter Fort Ancient from the north as a storm is gathering.
The sky has darkened. Wind moves through the trees, lifting thousands of early autumn leaves into the air. They cross the road in waves, rise, scatter, disappear, and return. From inside the moving car, the wind seems almost to take shape—invisible curves made visible by leaves, chasing the vehicle as we follow the narrow road south.
For a moment, it feels as if the landscape is whispering.
I do not know what it is saying.
There is urgency in the approaching storm, but also an unexpected calm. The forest encloses the road. Beyond it, partially hidden by trees and hills, the ancient earthworks stretch across the plateau above the Little Miami River. Their scale is difficult to understand from any single position. They appear, disappear, and reappear as we move. What seems at first to be natural terrain gradually reveals itself as something shaped by human hands nearly two thousand years ago.
I know very little about what those hands intended.
And yet I feel something.
This contradiction stays with me.
It reminds me of standing before the Great Wall of China. We can study their geometry, construction, and history, but knowledge is not necessarily what creates our first response. Before explanation, there is size, scale, distance, and the relationship between a small human body and something much larger than itself.
Perhaps this is where what we feel comes before what we understand.
We ask questions about meaning. What is this place? Who built it? What did it mean?
But our physical experience asks something different.
How does the ground rise beneath my feet? How far can I see? What disappears behind the trees? What does the wind sound like? What happens when the sky becomes dark?
We experience a place through our bodies before our minds begin to explain it.
Fort Ancient makes this relationship particularly powerful. The earthworks carry histories, knowledge, and cultural meanings that extend far beyond what we can see today. Archaeological research helps us understand their construction and significance, while Indigenous oral traditions and the knowledge of descendant Tribal communities offer important connections to the people who shaped this landscape.
Yet as a visitor, I recognize how much I still do not understand.
The earth remains.
The embankments remain. The openings remain. The geometry remains. The little Miami river flows below the cliffs. Seasons return, storms arrive, leaves fall, and people continue to move through the landscape.
This raises a question for architecture.
How do we design a museum that respects the history of Fort Ancient while allowing visitors to experience the place for themselves?
There is a danger in telling a story too confidently.
Digital techologies give us powerful tools to represent the past. We can reconstruct buildings that no longer exist, generate imagined scenes, and surround visitors with convincing stories.
But powerful technology does not mean we fully understand the past. These tools should support historical research and Indigenous knowledge, rather than replace them with our own assumptions.
Perhaps the purpose of technology should not be to remove every uncertainty.
Perhaps architecture should not speak louder.
Perhaps it should help us listen.
A museum at Fort Ancient might begin not with information, but with experience: walking between earthworks, watching the horizon change, hearing wind move through trees, moving from darkness into light, and feeling the passage of time.
Then come the stories, histories, and different ways of understanding the place.
Experience before explanation. Feeling before understanding.
This idea also connects to our relationship with AI. Large language models can connect words, histories, images, and ideas at an extraordinary scale. Yet human beings experience the world through something more: gravity, temperature, balance, fear, touch, movement, and breath.
We understand through language.
But we also understand through experience, even before we find the words.
Driving through Fort Ancient beneath the approaching storm, I cannot say what the people who shaped this landscape two thousand years ago intended. Their histories deserve careful study, respect, and the voices of the communities connected to them.
The leaves continue to move across the road. The earth rises quietly beside me. The forest opens and closes.
