Related papers: GraphGeo: Multi-Agent Debate Framework for Visual …

The coordination of autonomous agents in dynamic environments is hampered by the semantic gap between high-level mission objectives and low-level planner inputs. To address this, we introduce a framework centered on a Knowledge Graph (KG)…

We study a symmetric collaborative dialogue setting in which two agents, each with private knowledge, must strategically communicate to achieve a common goal. The open-ended dialogue state in this setting poses new challenges for existing…

Combining multiple knowledge graphs (KGs) across linguistic boundaries is a persistent challenge due to semantic heterogeneity and the complexity of graph environments. We propose a framework for cross-lingual graph fusion, leveraging the…

This paper presents a framework for jointly grounding objects that follow certain semantic relationship constraints given in a scene graph. A typical natural scene contains several objects, often exhibiting visual relationships of varied…

Generative answer engines expose content through selective citation rather than ranked retrieval, fundamentally altering how visibility is determined. This shift calls for new optimization methods beyond traditional search engine…

This paper addresses the challenge of decentralized task allocation within heterogeneous multi-agent systems operating under communication constraints. We introduce a novel framework that integrates graph neural networks (GNNs) with a…

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…

Large Language Models (LLMs) offer significant promise for intelligent traffic management; however, current chain-based systems like TrafficGPT are hindered by sequential task execution, high token usage, and poor scalability, making them…

An effective way to obtain different perspectives on any given topic is by conducting a debate, where participants argue for and against the topic. Here, we propose a novel debate framework for understanding and explaining a continuous…

Recently, to comprehensively improve Vision Language Models (VLMs) for Visual Question Answering (VQA), several methods have been proposed to further reinforce the inference capabilities of VLMs to independently tackle VQA tasks rather than…

Document structure analysis, such as zone segmentation and table recognition, is a complex problem in document processing and is an active area of research. The recent success of deep learning in solving various computer vision and machine…

Graph Retrieval-Augmented Generation (GraphRAG) has emerged as a promising paradigm that organizes external knowledge into structured graphs of entities and relations, enabling large language models (LLMs) to perform complex reasoning…

Text-to-image generation has advanced rapidly, but existing models still struggle with faithfully composing multiple objects and preserving their attributes in complex scenes. We propose coDrawAgents, an interactive multi-agent dialogue…

Navigating heterogeneous traffic environments with diverse driving styles poses a significant challenge for autonomous vehicles (AVs) due to their inherent complexity and dynamic interactions. This paper addresses this challenge by…

As Large Language Models (LLMs) transition from static tools to autonomous agents, traditional evaluation benchmarks that measure performance on downstream tasks are becoming insufficient. These methods fail to capture the emergent social…

Image geolocalization has traditionally been addressed through retrieval-based place recognition or geometry-based visual localization pipelines. Recent advances in Vision-Language Models (VLMs) have demonstrated strong zero-shot reasoning…

Multi-view learning has progressed rapidly in recent years. Although many previous studies assume that each instance appears in all views, it is common in real-world applications for instances to be missing from some views, resulting in…

This paper introduces a decentralized multi-agent reinforcement learning framework enabling structurally heterogeneous teams of agents to jointly discover and acquire randomly located targets in environments characterized by partial…

Accurate and robust trajectory prediction of neighboring agents is critical for autonomous vehicles traversing in complex scenes. Most methods proposed in recent years are deep learning-based due to their strength in encoding complex…

Visual grounding (VG) aims to establish fine-grained alignment between vision and language. Ideally, it can be a testbed for vision-and-language models to evaluate their understanding of the images and texts and their reasoning abilities…