Related papers: Spatial Language Representation with Multi-Level G…
3D visual grounding aims to localize the unique target described by natural languages in 3D scenes. The significant gap between 3D and language modalities makes it a notable challenge to distinguish multiple similar objects through the…
Accurately reconstructing road surfaces is pivotal for various applications especially in autonomous driving. This paper introduces a position encoding Multi-Layer Perceptrons (MLPs) framework to reconstruct road surfaces, with input as…
Hierarchical multi-label classification (HMLC) is essential for modeling structured label dependencies in remote sensing. Yet existing approaches struggle in multi-path settings, where images may activate multiple taxonomic branches,…
Understanding the latent space geometry of large language models (LLMs) is key to interpreting their behavior and improving alignment. Yet it remains unclear to what extent LLMs linearly organize representations related to semantic…
Large Language Models (LLM) have emerged as a tool for robots to generate task plans using common sense reasoning. For the LLM to generate actionable plans, scene context must be provided, often through a map. Recent works have shifted from…
Agricultural landscape segmentation in the Global South is challenging as it is characterized by fragmented plots, high intra-class variance, and a scarcity of labeled training data. Recent advances in segmentation have been made by…
LLMs are increasingly used to support qualitative research, yet existing systems produce outputs that vary widely--from trace-faithful summaries to theory-mediated explanations and system models. To make these differences explicit, we…
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…
We present Multi-Scale Manifold Alignment(MSMA), an information-geometric framework that decomposes LLM representations into local, intermediate, and global manifolds and learns cross-scale mappings that preserve geometry and information.…
Multi-modal large language models (MLLMs) have rapidly advanced in visual tasks, yet their spatial understanding remains limited to single images, leaving them ill-suited for physical-world applications that require multi-frame reasoning.…
Natural-language Guided Cross-view Geo-localization (NGCG) aims to retrieve geo-tagged satellite imagery using textual descriptions of ground scenes. While recent NGCG methods commonly rely on CLIP-style dual-encoder architectures, they…
Large Language Models (LLMs) have demonstrated unprecedented capabilities across various natural language processing tasks. Their ability to process and generate viable text and code has made them ubiquitous in many fields, while their…
Variation in spatial categorization across languages is often studied by eliciting human labels for the relations depicted in a set of scenes known as the Topological Relations Picture Series (TRPS). We demonstrate that labels generated by…
Multimodal Large Language Models (MLLMs) have achieved remarkable progress but continue to struggle with geometric reasoning, primarily due to the perception bottleneck regarding fine-grained visual elements. While formal languages have…
Heterogeneous graph neural networks (HGNNs) excel at capturing structural and semantic information in heterogeneous graphs (HGs), while struggling to generalize across domains and tasks. With the rapid advancement of large language models…
Recent advances in cellular research demonstrate that scRNA-seq characterizes cellular heterogeneity, while spatial transcriptomics reveals the spatial distribution of gene expression. Cell representation is the fundamental issue in the two…
Systems which incrementally create 3D semantic maps from image sequences must store and update representations of both geometry and semantic entities. However, while there has been much work on the correct formulation for geometrical…
The Multi-Modal Large Language Model (MLLM) refers to an extension of the Large Language Model (LLM) equipped with the capability to receive and infer multi-modal data. Spatial awareness stands as one of the crucial abilities of MLLM,…
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…
Multilingual language models (LMs) organize representations for typologically and orthographically diverse languages into a shared parameter space, yet the nature of this internal organization remains elusive. In this work, we investigate…