paper-with-me

Papers

Multi-Agent VQA: Exploring Multi-Agent Foundation Models in Zero-Shot Visual Question Answering

2024-03-21 · Bowen Jiang, Zhijun Zhuang, Shreyas S. Shivakumar, Dan Roth, Camillo J. Taylor

This work explores the zero-shot capabilities of foundation models in Visual Question Answering (VQA) tasks. We propose an adaptive multi-agent system, named Multi-Agent VQA, to overcome the limitations of foundation models in object detection and counting by using specialized agents as tools. Unlike existing approaches, our study focuses on the system's performance without fine-tuning it on specific VQA datasets, making it more practical and robust in the open world. We present preliminary experimental results under zero-shot scenarios and highlight some failure cases, offering new directions for future research.

📄 PDF Abstract BibTeX arXiv:2403.14783

Code (1)

bowen-upenn/Multi-Agent-VQA 공식 구현 pytorch

Tasks

object-detectionObject DetectionQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Similar Papers 제목 키워드 기반

Multi-Agent Causal Discovery Using Large Language Models

2024-07-21 · Hao Duong Le, Xin Xia, Zhang Chen

Large Language Models (LLMs) have demonstrated significant potential in causal discovery tasks by utilizing their vast expert knowledge from extensive text corpora. However, the multi-agent capabilities of LLMs in causal…

Causal Discovery

Sheaf-Theoretic Planning: A Categorical Foundation for Resilient Multi-Agent Autonomous Systems

2026-05-03 · Manuel Hernández, Eduardo Sánchez-Soto arxiv

The challenge of engineering autonomous agents capable of navigating the stochastic and adversarial nature of the physical world has historically resided at the intersection of symbolic logic and control theory. Traditio…

Swiss Cheese Model for AI Safety: A Taxonomy and Reference Architecture for Multi-Layered Guardrails of Foundation Model Based Agents

2024-08-05 · Md Shamsujjoha, Qinghua Lu, Dehai Zhao, Liming Zhu

Foundation Model (FM)-based agents are revolutionizing application development across various domains. However, their rapidly growing capabilities and autonomy have raised significant concerns about AI safety. Researcher…

modelSystematic Literature Review

A Semi-Decentralized Approach to Multiagent Control

2026-03-12 · Mahdi Al-Husseini, Mykel J. Kochenderfer, Kyle H. Wray arxiv

We introduce an expressive framework and algorithms for the semi-decentralized control of cooperative agents in environments with communication uncertainty. Whereas semi-Markov control admits a distribution over time for…

Exploring Multi-Modal Data with Tool-Augmented LLM Agents for Precise Causal Discovery

2024-12-18 · ChengAo Shen, Zhengzhang Chen, Dongsheng Luo, Dongkuan Xu 외

Causal discovery is an imperative foundation for decision-making across domains, such as smart health, AI for drug discovery and AIOps. Traditional statistical causal discovery methods, while well-established, predominan…

Causal DiscoveryCausal Inference