Related papers: Platonic Representations for Poverty Mapping: Unif…

The fast development of location-based social networks (LBSNs) has led to significant changes in society, resulting in popular studies of using LBSN data for socioeconomic prediction, e.g., regional population and commercial activity…

Unified multimodal models provide a natural and promising architecture for understanding diverse and complex real-world knowledge while generating high-quality images. However, they still rely primarily on frozen parametric knowledge, which…

We introduce a multicrossmodal LLM-agent framework motivated by the growing volume and diversity of materials-science data ranging from high-resolution microscopy and dynamic simulation videos to tabular experiment logs and sprawling…

Large language models (LLMs) and vision-language models (VLMs) have demonstrated remarkable performance across a wide range of tasks and domains. Despite this promise, spatial understanding and reasoning -- a fundamental component of human…

This article explores the convergence of connectionist and symbolic artificial intelligence (AI), from historical debates to contemporary advancements. Traditionally considered distinct paradigms, connectionist AI focuses on neural…

Large language models (LLMs) can serve as the semantic-matching engine of a content-based publish/subscribe broker for agentic AI across the edge-cloud computing continuum, bridging the vocabulary and modality gaps that defeat keyword and…

Motivated by interpretability and reliability, we investigate whether large language models (LLMs) deploy universal geometric structures to encode discrete, graph-structured knowledge. To this end, we present two complementary experimental…

We investigate, at the fundamental level, the questions of `why', `when' and `how' one could or should reach out to poor and vulnerable people to support them in the absence of governmental institutions. We provide a simple and new approach…

There is growing evidence that independently trained AI systems come to represent the world in the same way. In other words, independently trained embeddings from text, vision, audio, and neural signals share an underlying geometry. We call…

Future sixth-generation (6G) mobile networks are envisioned to be equipped with a diverse set of powerful, yet highly specialized, optimization experts. Such a promising vision is concurrently expected to give rise to the need for scalable…

We present \textbf{DeepInflation}, an AI agent designed for research and model discovery in inflationary cosmology. Built upon a multi-agent architecture, \textbf{DeepInflation} integrates Large Language Models (LLMs) with a symbolic…

The rapid emergence of Large Language Models (LLMs) has catalyzed Agentic artificial intelligence (AI), autonomous systems integrating perception, reasoning, and action into closed-loop pipelines for continuous adaptation. While unlocking…

Existing change detection methods often lack the versatility to handle diverse real-world queries and the intelligence for comprehensive analysis. This paper presents a general agent framework, integrating Large Language Models (LLM) with…

Visual Language Models (VLMs) have increasingly become the main paradigm for understanding indoor scenes, but they still struggle with metric and spatial reasoning. Current approaches rely on end-to-end video understanding or large-scale…

Background: The House-Tree-Person (HTP) drawing test, introduced by John Buck in 1948, remains a widely used projective technique in clinical psychology. However, it has long faced challenges such as heterogeneous scoring standards,…

Despite substantial progress of large language models (LLMs) for automatic poetry generation, the generated poetry lacks diversity while the training process differs greatly from human learning. Under the rationale that the learning process…

Vision-Language Models (VLMs) often yield inconsistent descriptions of the same object across viewpoints, hindering the ability of embodied agents to construct consistent semantic representations over time. Previous methods resolved…

Combining satellite imagery with machine learning (SIML) has the potential to address global challenges by remotely estimating socioeconomic and environmental conditions in data-poor regions, yet the resource requirements of SIML limit its…

This paper shows how a multimodal large language model (MLLM) can expand urban measurement capacity and support tracking of place-based policy interventions. Using a structured, reason-then-estimate pipeline on street-view imagery, GPT-4o…

Agentic retrieval-augmented reasoning pipelines are increasingly used to structure how large language models (LLMs) incorporate external evidence in clinical decision support. These systems iteratively retrieve curated domain knowledge and…