Related papers: Recognition through Reasoning: Reinforcing Image G…
CAPTCHA, originally designed to distinguish humans from robots, has evolved into a real-world benchmark for assessing the spatial reasoning capabilities of vision-language models. In this work, we first show that step-by-step reasoning is…
As textual reasoning with large language models (LLMs) has advanced significantly, there has been growing interest in enhancing the multimodal reasoning capabilities of large vision-language models (LVLMs). However, existing methods…
Planet-scale photo geolocalization is the complex task of estimating the location depicted in an image solely based on its visual content. Due to the success of convolutional neural networks (CNNs), current approaches achieve super-human…
Language-guided grasping has emerged as a promising paradigm for enabling robots to identify and manipulate target objects through natural language instructions, yet it remains highly challenging in cluttered or occluded scenes. Existing…
Recent breakthroughs in reasoning models have markedly advanced the reasoning capabilities of large language models, particularly via training on tasks with verifiable rewards. Yet, a significant gap persists in their adaptation to real…
Geospatial Location Embedding (GLE) helps a Large Language Model (LLM) assimilate and analyze spatial data. GLE emergence in Geospatial Artificial Intelligence (GeoAI) is precipitated by the need for deeper geospatial awareness in our…
Multimodal Large Language Models (MLLMs) have become a powerful tool for integrating visual and textual information. Despite their exceptional performance on visual understanding benchmarks, measuring their ability to reason abstractly…
Multimodal Large Language Models (MLLMs) are increasingly applied in real-world scenarios where user-provided images are often imperfect, requiring active image manipulations such as cropping, editing, or enhancement to uncover salient…
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…
Cross-view geo-localisation identifies coarse geographical position of an automated vehicle by matching a ground-level image to a geo-tagged satellite image from a database. Despite the advancements in Cross-view geo-localisation,…
Accurate visual re-localization is very critical to many artificial intelligence applications, such as augmented reality, virtual reality, robotics and autonomous driving. To accomplish this task, we propose an integrated visual…
This paper proposes ReaGeo, an end-to-end geocoding framework based on large language models, designed to overcome the limitations of traditional multi-stage approaches that rely on text or vector similarity retrieval over geographic…
Object-aware reasoning in vision-language tasks poses significant challenges for current models, particularly in handling unseen objects, reducing hallucinations, and capturing fine-grained relationships in complex visual scenes. To address…
Vision-Language Foundation Models (VLFMs) have made remarkable progress on various multimodal tasks, such as image captioning, image-text retrieval, visual question answering, and visual grounding. However, most methods rely on training…
Recent advancements in dialogue systems have highlighted the significance of integrating multimodal responses, which enable conveying ideas through diverse modalities rather than solely relying on text-based interactions. This enrichment…
Spatial reasoning is a core aspect of human intelligence that allows perception, inference and planning in 3D environments. However, current vision-language models (VLMs) struggle to maintain geometric coherence and cross-view consistency…
Worldwide image geolocalization aims to predict precise GPS coordinates for images captured anywhere on Earth, which is challenging due to the large visual and geographic diversity. Recent methods mainly follow two paradigms:…
Vision language models (VLMs) are expected to perform effective multimodal reasoning and make logically coherent decisions, which is critical to tasks such as diagram understanding and spatial problem solving. However, current VLM reasoning…
Automated perception of urban roadside infrastructure is crucial for smart city management, yet general-purpose models often struggle to capture the necessary fine-grained attributes and domain rules. While Large Vision Language Models…
Large language models (LLMs) exhibit a variety of promising capabilities in robotics, including long-horizon planning and commonsense reasoning. However, their performance in place recognition is still underexplored. In this work, we…