Learning to Remember:Exploring Multimodal Memory Mechanisms in Long Video Understanding | Reading Group

Learning to Remember: Exploring Multimodal Memory Mechanisms in Long Video Understanding

keywords: Memory, Long Video Understanding, VLA

论文分享主题是就是长视频理解领域的记忆模块应用，也是与我目前研究的方向比较契合

完整PPT如下：

参考文献：

1.[CVPR 2024]《MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding》
https://arxiv.org/pdf/2404.05726

2.[NeurIPS 2025]《VideoLucy: Deep Memory Backtracking for Long Video Understanding》
https://arxiv.org/abs/2510.12422

3.[arXiv 2025]《MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation》
https://arxiv.org/abs/2508.19236