v1v2 (latest)

MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks

8 June 2025

Papers citing "MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks"

2 / 2 papers shown

Title
CFVBench: A Comprehensive Video Benchmark for Fine-grained Multimodal Retrieval-Augmented Generation Kaiwen Wei Xiao-Yang Liu Jie Zhang Zijian Wang Ruida Liu ... C. Pan Y. Zhang Jiang Zhong Peijin Wang Yingchao Feng VGen VLM 96 0 0 10 Oct 2025
AURA: A Fine-Grained Benchmark and Decomposed Metric for Audio-Visual Reasoning Siminfar Samakoush Galougah Rishie Raj Sanjoy Chowdhury Sayan Nag Ramani Duraiswami 169 2 0 10 Aug 2025