furonghuang-lab/Mementos

Official Dataset for [Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences](https://arxiv.org/abs/2401.10529). All data is downloaded from the original google drive [link](https://drive.google.com/drive/folders/1CKBWtHKzJgkGJb3Qdl2e_HHhc0fThW61?usp=sharing).

搜集汇总

背景与挑战

背景概述

Mementos是一个用于多模态大语言模型在图像序列推理任务上的综合基准测试数据集。它提供了官方数据，旨在评估模型对连续图像的理解和推理能力。所有数据可通过Google Drive获取。