# How Far Can Off-the-Shelf Multimodal Large Language Models Go in Online Episodic Memory Question Answering?

arXiv: https://arxiv.org/abs/2506.16450 · HTML: https://mlsanity.com/paper/2506.16450/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Video understanding with MLLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 8 of its 14 references that are in the map.
- First posted on arXiv 19 Jun 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/)

## Builds on (most cited first, 8 of 8)

- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [InternVideo2: Scaling Foundation Models for Multimodal Video Understanding](https://mlsanity.com/paper/2403.15377/) (2024)
- [How Language Model Hallucinations Can Snowball](https://mlsanity.com/paper/2305.13534/) (2023)
- [Streaming Video Question-Answering with In-context Video KV-Cache Retrieval](https://mlsanity.com/paper/2503.00540/) (2025)
- [Grounded Question-Answering in Long Egocentric Videos](https://mlsanity.com/paper/2312.06505/) (2023)
- [Advancing Egocentric Video Question Answering with Multimodal Large Language Models](https://mlsanity.com/paper/2504.04550/) (2025)

## Built on by (most cited first, 1 of 1)

- [Exploring Multimodal LMMs for Online Episodic Memory Question Answering on the Edge](https://mlsanity.com/paper/2602.22455/) (2026)

## Abstract (arXiv)

We investigate whether off-the-shelf Multimodal Large Language Models (MLLMs) can tackle Online Episodic-Memory Video Question Answering (OEM-VQA) without additional training. Our pipeline converts a streaming egocentric video into a lightweight textual memory, only a few kilobytes per minute, via an MLLM descriptor module, and answers multiple-choice questions by querying this memory with an LLM reasoner module. On the QAEgo4D-Closed benchmark, our best configuration attains 56.0% accuracy with 3.6 kB per minute storage, matching the performance of dedicated state-of-the-art systems while being 10**4/10**5 times more memory-efficient. Extensive ablations provides insights into the role of each component and design choice, and highlight directions of improvement for future research.