arXiv subjects

Guangyuan Weng

Publications and source records attributed to Guangyuan Weng.

5 recordsLinked to original sources

arXiv2026

Large language models create an uneven informational layer over cities

Large language models (LLMs) are emerging as a new informational layer over cities, shaping which places people discover, consider, and ultimately visit. Yet little is known about which places they surface, which they ignore, and whether these patterns vary across communities and users and translate into real-world economic consequences. Here, we audit restaurant recommendations from three major LLMs across 304 neighborhoods in five U.S. cities using 320 synthetic user profiles spanning income, age, sex, and residential status. We find that LLMs both fabricate venues and systematically overlook real ones. Fabrication is concentrated in neighborhoods with weaker digital and physical footprints and disappears when models are provided with verified venue lists. In contrast, invisibility persists: even when choosing from a fixed set of real venues, 47.5% of establishments are never recommended, and 31.9% of these blind spots are shared across all three model families, indicating that uneven visibility reflects not only missing knowledge but also stable patterns of selective attention rooted in shared patterns of visibility rather than model-specific errors. The same selectivity extends to users. Within identical venue pools, higher-income users receive more expensive and less popular venues, while tourists are directed toward costlier but more socially diverse establishments than local residents. Simulating the resulting shifts in consumer demand suggests that widespread reliance on LLM recommendations would redirect visits and revenue away from chain and quick-service restaurants toward independent and full-service dining. Together, our findings show that LLMs act as a selective layer of urban information that unevenly distributes visibility across places and people, with potential consequences for local economies and urban inequality.

cs.CY↗

arXiv2025

Beyond Distance: Mobility Neural Embeddings Reveal Visible and Invisible Barriers in Urban Space

Human mobility in cities is shaped not only by visible structures such as highways, rivers, and parks but also by invisible barriers rooted in socioeconomic segregation, uneven access to amenities, and administrative divisions. Yet identifying and quantifying these barriers at scale and their relative importance on people's movements remains a major challenge. Neural embedding models, originally developed for language, offer a powerful way to capture the complexity of human mobility from large-scale data. Here, we apply this approach to 25.4 million observed trajectories across 11 major U.S. cities, learning mobility embeddings that reveal how people move through urban space. These mobility embeddings define a functional distance between places, one that reflects behavioral rather than physical proximity, and allow us to detect barriers between neighborhoods that are geographically close but behaviorally disconnected. We find that the strongest predictors of these barriers are differences in access to amenities, administrative borders, and residential segregation by income and race. These invisible borders are concentrated in urban cores and persist across cities, spatial scales, and time periods. Physical infrastructure, such as highways and parks, plays a secondary but still significant role, especially at short distances. We also find that individuals who cross barriers tend to do so outside of traditional commuting hours and are more likely to live in areas with greater racial diversity, and higher transit use or income. Together, these findings reveal how spatial, social, and behavioral forces structure urban accessibility and provide a scalable framework to detect and monitor barriers in cities, with applications in planning, policy evaluation, and equity analysis.

cs.CY↗

arXiv2022

Action Recognition based on Cross-Situational Action-object Statistics

Machine learning models of visual action recognition are typically trained and tested on data from specific situations where actions are associated with certain objects. It is an open question how action-object associations in the training set influence a model's ability to generalize beyond trained situations. We set out to identify properties of training data that lead to action recognition models with greater generalization ability. To do this, we take inspiration from a cognitive mechanism called cross-situational learning, which states that human learners extract the meaning of concepts by observing instances of the same concept across different situations. We perform controlled experiments with various types of action-object associations, and identify key properties of action-object co-occurrence in training data that lead to better classifiers. Given that these properties are missing in the datasets that are typically used to train action classifiers in the computer vision literature, our work provides useful insights on how we should best construct datasets for efficiently training for better generalization.

cs.CV↗

arXiv2020

Advanced Mapping Robot and High-Resolution Dataset

This paper presents a fully hardware synchronized mapping robot with support for a hardware synchronized external tracking system, for super-precise timing and localization. Nine high-resolution cameras and two 32-beam 3D Lidars were used along with a professional, static 3D scanner for ground truth map collection. With all the sensors calibrated on the mapping robot, three datasets are collected to evaluate the performance of mapping algorithms within a room and between rooms. Based on these datasets we generate maps and trajectory data, which is then fed into evaluation algorithms. We provide the datasets for download and the mapping and evaluation procedures are made in a very easily reproducible manner for maximum comparability. We have also conducted a survey on available robotics-related datasets and compiled a big table with those datasets and a number of properties of them.

cs.RO↗

arXiv2019

Towards Generation and Evaluation of Comprehensive Mapping Robot Datasets

This paper presents a fully hardware synchronized mapping robot with support for a hardware synchronized external tracking system, for super-precise timing and localization. We also employ a professional, static 3D scanner for ground truth map collection. Three datasets are generated to evaluate the performance of mapping algorithms within a room and between rooms. Based on these datasets we generate maps and trajectory data, which is then fed into evaluation algorithms. The mapping and evaluation procedures are made in a very easily reproducible manner for maximum comparability. In the end we can draw a couple of conclusions about the tested SLAM algorithms.

cs.RO↗