Related papers: GeoBrowse: A Geolocation Benchmark for Agentic Too…
IP geolocation aims at locating the geographical position of Internet devices, which plays an essential role in many Internet applications. In this field, a long-standing challenge is how to find a large number of highly-reliable landmarks,…
Recent advancements in image generation models have enabled the prediction of future Graphical User Interface (GUI) states based on user instructions. However, existing benchmarks primarily focus on general domain visual fidelity, leaving…
Geometric Problem Solving (GPS) remains at the heart of enhancing mathematical reasoning in large language models because it requires the combination of diagrammatic understanding, symbolic manipulation and logical inference. In existing…
Leveraging multimodal large language models (MLLMs) to develop embodied agents offers significant promise for addressing complex real-world tasks. However, current evaluation benchmarks remain predominantly language-centric or heavily…
Data-driven scientific discovery requires the iterative integration of scientific domain knowledge, statistical expertise, and an understanding of data semantics to make nuanced analytical decisions, e.g., about which variables,…
Frontier multimodal large language models (MLLMs) have been reported to achieve over 90% accuracy on fine-grained perception benchmarks. However, such scores do not necessarily imply faithful use of visual evidence. Prior studies have…
In this paper, we propose to go beyond the well-established approach to vision-based localization that relies on visual descriptor matching between a query image and a 3D point cloud. While matching keypoints via visual descriptors makes…
Language-goal aerial navigation requires UAVs to localize targets in the complex outdoors, such as urban blocks based on textual instructions. The indoor methods are often hard to scale to urban scenes due to ambiguous objects, limited…
Our method for multi-lingual geoparsing uses monolingual tools and resources along with machine translation and alignment to return location words in many languages. Not only does our method save the time and cost of developing geoparsers…
Traditional Visual Grounding (VG) predominantly relies on textual descriptions to localize objects, a paradigm that inherently struggles with linguistic ambiguity and often ignores non-verbal deictic cues prevalent in real-world…
Vision Language Models (VLMs) are good at recognizing the global location of a photograph -- their geolocation prediction accuracy rivals the best human experts. But many VLMs are startlingly bad at \textit{explaining} which image evidence…
Empirical methods in geoparsing have thus far lacked a standard evaluation framework describing the task, metrics and data used to compare state-of-the-art systems. Evaluation is further made inconsistent, even unrepresentative of…
Knowledge graphs provide structured and reliable information for many real-world applications, motivating increasing interest in combining large language models (LLMs) with graph-based retrieval to improve factual grounding. Recent…
Recent multimodal LLMs have shown promise in chart-based visual question answering, but their performance declines sharply on unannotated charts-those requiring precise visual interpretation rather than relying on textual shortcuts. To…
Multimodal creative assistants decompose user goals and route tasks to subagents for layout, styling, retrieval, and generation. Retrieval quality is pivotal, yet failures can arise at several stages: understanding user intent, choosing…
Understanding how humans cooperatively utilize semantic knowledge to explore unfamiliar environments and decide on navigation directions is critical for house service multi-robot systems. Previous methods primarily focused on single-robot…
Recent advances in deep-research systems have demonstrated the potential for AI agents to autonomously discover and synthesize knowledge from external sources. In this paper, we introduce WebResearcher, a novel framework for building such…
Global geolocation, which seeks to predict the geographical location of images captured anywhere in the world, is one of the most challenging tasks in the field of computer vision. In this paper, we introduce an innovative interactive…
Recent advances in multimodal large language models (MLLMs) have accelerated progress in domain-oriented AI, yet their development in geoscience and remote sensing (RS) remains constrained by distinctive challenges: wide-ranging…
Geospatial reasoning is essential for real-world applications such as urban analytics, transportation planning, and disaster response. However, existing LLM-based agents often fail at genuine geospatial computation, relying instead on web…