Ciro Beneduce

Filippo Ziliotto, Ciro Beneduce, Bruno Lepri et al.

In the animal kingdom, mirror self-recognition is a canonical probe of higher-order cognition, emerging only in some species. We ask whether an analogous functional capability emerges in embodied vision-language model (VLM) agents: can they recognize themselves in a mirror? We introduce a controlled 3D benchmark where a first-person VLM agent must infer a hidden body attribute from its reflection and select the matching target, while avoiding self-other misattribution. To separate mirror-grounded self-identification from shortcuts, we test mirror removal, misleading cues, and occluded reflections. We also evaluate the decision process through mirror seeking, temporal ordering, self-attribution, and reasoning-action consistency. Our experiments show that mirror-based self-identification emerges mainly in stronger VLMs. These models can use reflected evidence for action, whereas weaker models often inspect the mirror but fail to extract self-relevant information or misattribute their reflection. Language-vision conflict further shows that self-referential language alone is not evidence of grounded self-identification. Overall, mirror-based evaluation provides a diagnostic for whether embodied self-grounding is causally rooted in perception and action rather than priors, prompt compliance, or confabulation.

Ciro Beneduce, Bruno Lepri, Massimiliano Luca

Understanding how urban environments are perceived in terms of safety is crucial for urban planning and policymaking. Traditional methods like surveys are limited by high cost, required time, and scalability issues. To overcome these challenges, this study introduces Large Multimodal Models (LMMs), specifically Llava 1.6 7B, as a novel approach to assess safety perceptions of urban spaces using street-view images. In addition, the research investigated how this task is affected by different socio-demographic perspectives, simulated by the model through Persona-based prompts. Without additional fine-tuning, the model achieved an average F1-score of 59.21% in classifying urban scenarios as safe or unsafe, identifying three key drivers of perceived unsafety: isolation, physical decay, and urban infrastructural challenges. Moreover, incorporating Persona-based prompts revealed significant variations in safety perceptions across the socio-demographic groups of age, gender, and nationality. Elder and female Personas consistently perceive higher levels of unsafety than younger or male Personas. Similarly, nationality-specific differences were evident in the proportion of unsafe classifications ranging from 19.71% in Singapore to 40.15% in Botswana. Notably, the model's default configuration aligned most closely with a middle-aged, male Persona. These findings highlight the potential of LMMs as a scalable and cost-effective alternative to traditional methods for urban safety perceptions. While the sensitivity of these models to socio-demographic factors underscores the need for thoughtful deployment, their ability to provide nuanced perspectives makes them a promising tool for AI-driven urban planning.

Ciro Beneduce, Massimiliano Luca, Bruno Lepri

Image generation models are revolutionizing many domains, and urban analysis and design is no exception. While such models are widely adopted, there is a limited literature exploring their geographic knowledge, along with the biases they embed. In this work, we generated 150 synthetic images for each state in the USA and related capitals using FLUX 1 and Stable Diffusion 3.5, two state-of-the-art models for image generation. We embed each image using DINO-v2 ViT-S/14 and the Fréchet Inception Distances to measure the similarity between the generated images. We found that while these models have implicitly learned aspects of USA geography, if we prompt the models to generate an image for "United States" instead of specific cities or states, the models exhibit a strong representative bias toward metropolis-like areas, excluding rural states and smaller cities. {\color{black} In addition, we found that models systematically exhibit some entity-disambiguation issues with European-sounding names like Frankfort or Devon.

Massimiliano Luca, Ciro Beneduce, Bruno Lepri et al.

With the wide and cross-domain adoption of Large Language Models, it becomes crucial to assess to which extent the statistical correlations in training data, which underlie their impressive performance, hide subtle and potentially troubling biases. Gender bias in LLMs has been widely investigated from the perspectives of works, hobbies, and emotions typically associated with a specific gender. In this study, we introduce a novel perspective. We investigate whether LLMs can predict an individual's gender based solely on online shopping histories and whether these predictions are influenced by gender biases and stereotypes. Using a dataset of historical online purchases from users in the United States, we evaluate the ability of six LLMs to classify gender and we then analyze their reasoning and products-gender co-occurrences. Results indicate that while models can infer gender with moderate accuracy, their decisions are often rooted in stereotypical associations between product categories and gender. Furthermore, explicit instructions to avoid bias reduce the certainty of model predictions, but do not eliminate stereotypical patterns. Our findings highlight the persistent nature of gender biases in LLMs and emphasize the need for robust bias-mitigation strategies.

Massimiliano Luca, Ciro Beneduce, Bruno Lepri

We investigate the effectiveness of time series foundation models (TSFMs) for crowd flow prediction, focusing on Moirai and TimesFM. Evaluated on three real-world mobility datasets-Bike NYC, Taxi Beijing, and Spanish national OD flows-these models are deployed in a strict zero-shot setting, using only the temporal evolution of each OD flow and no explicit spatial information. Moirai and TimesFM outperform both statistical and deep learning baselines, achieving up to 33% lower RMSE, 39% lower MAE and up to 49% higher CPC compared to state-of-the-art competitors. Our results highlight the practical value of TSFMs for accurate, scalable flow prediction, even in scenarios with limited annotated data or missing spatial context.