# Exploring Multimodal LMMs for Online Episodic Memory Question Answering on the Edge

arXiv: https://arxiv.org/abs/2602.22455 · HTML: https://mlsanity.com/paper/2602.22455/

## 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 14 of its 18 references that are in the map.
- First posted on arXiv 25 Feb 2026.

## Placed in

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

## Builds on (most cited first, 14 of 14)

- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [InternVideo2: Scaling Foundation Models for Multimodal Video Understanding](https://mlsanity.com/paper/2403.15377/) (2024)
- [VideoLLM-online: Online Video Large Language Model for Streaming Video](https://mlsanity.com/paper/2406.11816/) (2024)
- [Streaming Video Question-Answering with In-context Video KV-Cache Retrieval](https://mlsanity.com/paper/2503.00540/) (2025)
- [TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos](https://mlsanity.com/paper/2504.17343/) (2025)
- [StreamingVLM: Real-Time Understanding for Infinite Video Streams](https://mlsanity.com/paper/2510.09608/) (2025)
- [EgoLife: Towards Egocentric Life Assistant](https://mlsanity.com/paper/2503.03803/) (2025)
- [Grounded Question-Answering in Long Egocentric Videos](https://mlsanity.com/paper/2312.06505/) (2023)
- [LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos](https://mlsanity.com/paper/2312.05269/) (2023)
- [InfiniPot: Infinite Context Processing on Memory-Constrained LLMs](https://mlsanity.com/paper/2410.01518/) (2024)
- [Encode-Store-Retrieve: Augmenting Human Memory through Language-Encoded Egocentric Perception](https://mlsanity.com/paper/2308.05822/) (2023)
- [How Far Can Off-the-Shelf Multimodal Large Language Models Go in Online Episodic Memory Question Answering?](https://mlsanity.com/paper/2506.16450/) (2025)

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

- [From Seeing to Acting: Smart Glasses as First-Person Intelligence Platforms](https://mlsanity.com/paper/2608.24877/) (2026)

## Abstract (arXiv)

We investigate the feasibility of using Multimodal Large Language Models (MLLMs) for real-time online episodic memory question answering. While cloud offloading is common, it raises privacy and latency concerns for wearable assistants, hence we investigate implementation on the edge. We integrated streaming constraints into our question answering pipeline, which is structured into two asynchronous threads: a Descriptor Thread that continuously converts video into a lightweight textual memory, and a Question Answering (QA) Thread that reasons over the textual memory to answer queries. Experiments on the QAEgo4D-Closed benchmark analyze the performance of Multimodal Large Language Models (MLLMs) within strict resource boundaries, showing promising results also when compared to clound-based solutions. Specifically, an end-to-end configuration running on a consumer-grade 8GB GPU achieves 51.76% accuracy with a Time-To-First-Token (TTFT) of 0.41s. Scaling to a local enterprise-grade server yields 54.40% accuracy with a TTFT of 0.88s. In comparison, a cloud-based solution obtains an accuracy of 56.00%. These competitive results highlight the potential of edge-based solutions for privacy-preserving episodic memory retrieval.