Related papers: City Editing: Hierarchical Agentic Execution for D…
World models have emerged as a powerful paradigm for building interactive simulation environments, with recent video-based approaches demonstrating impressive progress in generating visually plausible dynamics. However, because these models…
Mobile GUI agents powered by large foundation models enable autonomous task execution, but frequent updates altering UI appearance and reorganizing workflows cause agents trained on historical data to fail. Despite surface changes,…
With the acceleration of urbanization, traffic forecasting has become an essential role in smart city construction. In the context of spatio-temporal prediction, the key lies in how to model the dependencies of sensors. However, existing…
Tool invocation is a core capability of agentic systems, yet failures often arise not from individual tool calls but from how multiple tools are organized and executed together. Existing approaches tightly couple tool execution with…
Generative Adversarial Networks (GANs) with style-based generators (e.g. StyleGAN) successfully enable semantic control over image synthesis, and recent studies have also revealed that interpretable image translations could be obtained by…
Mapping road networks today is labor-intensive. As a result, road maps have poor coverage outside urban centers in many countries. Systems to automatically infer road network graphs from aerial imagery and GPS trajectories have been…
We describe a hybrid agent-based model and simulation of urban morphogenesis. It consists of a cellular automata grid coupled to a dynamic network topology. The inherently heterogeneous properties of urban structure and function are taken…
Intelligent agents working in real-world environments must be able to learn about the environment and its capabilities which enable them to take actions to change to the state of the world to complete a complex multi-step task in a…
Image-goal navigation steers an agent to a target location specified by an image in unseen environments. Existing methods primarily handle this task by learning an end-to-end navigation policy, which compares the similarities of target and…
As the underground infrastructure systems of cities age, maintenance and repair become an increasing concern. Cities face difficulties in planning maintenance, predicting and responding to infrastructure related issues, and in realizing…
Existing methods for self-supervised representation learning of geospatial regions and map entities rely extensively on the design of pretext tasks, often involving augmentations or heuristic sampling of positive and negative pairs based on…
Solving multiagent problems can be an uphill task due to uncertainty in the environment, partial observability, and scalability of the problem at hand. Especially in an urban setting, there are more challenges since we also need to maintain…
Streets are large, diverse, and used for several (and possibly conflicting) transport modalities as well as social and cultural activities. Proper planning is essential and requires data. Manually fabricating data that represent streets…
We attempt to take a comprehensive look at the challenges of representing the spatio-temporal structures and dynamic processes defining a city's overall characteristics. For the task of urban planning and urban operation, we take the stance…
Automatic parameter tuning methods for planning algorithms, which integrate pipeline approaches with learning-based techniques, are regarded as promising due to their stability and capability to handle highly constrained environments. While…
Instruction-based image editing (IIE) aims to modify images according to textual instructions while preserving irrelevant content. Despite recent advances in diffusion transformers, existing methods often suffer from over-editing,…
Towards intelligent image editing, object removal should eliminate both the target object and its causal visual artifacts, such as shadows and reflections. However, existing image appearance-based methods either follow strictly mask-aligned…
Humans seamlessly fuse anticipatory planning with immediate feedback to perform successive mobile manipulation tasks without stopping, achieving both high efficiency and reliability. Replicating this fluid and reliable behavior in robots…
Recent advances in Multimodal Large Language Models (MLLMs) have enabled the development of mobile agents that can understand visual inputs and follow user instructions, unlocking new possibilities for automating complex tasks on mobile…
Reconstructing real-world objects from multi-view images is essential for applications in 3D editing, AR/VR, and digital content creation. Existing methods typically prioritize either geometric accuracy (Multi-View Stereo) or photorealistic…