Related papers: How Many Visual Levers Drive Urban Perception? Int…
Perception research is increasingly modelled using streetscapes, yet many approaches still rely on pixel features or object co-occurrence statistics, overlooking the explicit relations that shape human perception. This study proposes a…
Large language models (LLMs) are increasingly used as reasoning engines in autonomous driving, yet their decision-making remains opaque. We propose to study their decision process through counterfactual explanations, which identify the…
While objective street metrics derived from imagery or GIS have become standard in urban analytics, they remain insufficient to capture subjective perceptions essential to inclusive urban design. This study introduces a novel Multimodal…
Knowledge editing, which aims to update the knowledge encoded in language models, can be deceptive. Despite the fact that many existing knowledge editing algorithms achieve near-perfect performance on conventional metrics, the models edited…
Humans perform visual perception at multiple levels, including low-level object recognition and high-level semantic interpretation such as behavior understanding. Subtle differences in low-level details can lead to substantial changes in…
Large multimodal models exhibit remarkable intelligence, yet their embodied cognitive abilities during motion in open-ended urban 3D space remain to be explored. We introduce a benchmark to evaluate whether video-large language models…
LLM-based social simulations can generate believable community interactions, enabling ``policy wind tunnels'' where governance interventions are tested before deployment. But believability is not causality. Claims like ``intervention $A$…
Stereotypical bias encoded in language models (LMs) poses a threat to safe language technology, yet our understanding of how bias manifests in the parameters of LMs remains incomplete. We introduce local contrastive editing that enables the…
Recent advances in causal interpretability have extended from language models to vision-language models (VLMs), seeking to reveal their internal mechanisms through input interventions. While textual interventions often target semantics,…
Analyzing street-view imagery with computer vision models for rapid, hyperlocal damage assessment is becoming popular and valuable in emergency response and recovery, but traditional models often act like black boxes, lacking…
A basic aspiration for interpretability research in large language models is to "localize" semantically meaningful behaviors to particular components within the LLM. There are various heuristics for finding candidate locations within the…
Large language models (LLMs) are increasingly used to describe, evaluate and interpret places, yet it remains unclear whether they do so from a culturally neutral standpoint. Here we test urban perception in frontier LLMs using a balanced…
Counterfactual explanations are increasingly proposed as interpretable mechanisms to achieve algorithmic recourse. However, current counterfactual techniques for time series classification are predominantly designed with static data…
Editable high-fidelity 4D scenes are crucial for autonomous driving, as they can be applied to end-to-end training and closed-loop simulation. However, existing reconstruction methods are primarily limited to replicating observed scenes and…
Multimodal counterfactual reasoning is a vital yet challenging ability for AI systems. It involves predicting the outcomes of hypothetical circumstances based on vision and language inputs, which enables AI models to learn from failures and…
Next-venue recommender systems are increasingly embedded in location-based services, shaping individual mobility decisions in urban environments. While their predictive accuracy has been extensively studied, less attention has been paid to…
Buildings shape how people feel, yet the mechanisms through which specific facade properties drive affective states remain empirically underspecified. Here we introduce the Cambridge Facade Affect Dataset (CFAD), 86 orthogonally rectified…
In this paper, we aim to explain the decisions of neural networks by utilizing multimodal information. That is counter-intuitive attributes and counter visual examples which appear when perturbed samples are introduced. Different from…
Street-view imagery (SVI) is widely used to quantify key indicators of urban environment, such as green- ery, sky, or road view indices. However, existing studies largely focus on measuring current streetscapes and rarely support the…
Counterfactual image editing is an important task in generative AI, which asks how an image would look if certain features were different. The current literature on the topic focuses primarily on changing individual features while remaining…