# MM-Ego: Towards Building Egocentric Multimodal LLMs for Video QA

arXiv: https://arxiv.org/abs/2410.07177 · HTML: https://mlsanity.com/paper/2410.07177/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 47 of its 59 references that are in the map.
- First posted on arXiv 9 Oct 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 30 of 47)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [Pointer Networks](https://mlsanity.com/paper/1506.03134/) (2015)
- [Scaling Egocentric Vision: The EPIC-KITCHENS Dataset](https://mlsanity.com/paper/1804.02748/) (2018)
- [A Tutorial on Bayesian Optimization](https://mlsanity.com/paper/1807.02811/) (2018)
- [NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions](https://mlsanity.com/paper/2105.08276/) (2021)
- [VILA: On Pre-training for Visual Language Models](https://mlsanity.com/paper/2312.07533/) (2023)
- [EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding](https://mlsanity.com/paper/2308.09126/) (2023)
- [LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding](https://mlsanity.com/paper/2407.15754/) (2024)
- [ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering](https://mlsanity.com/paper/1906.02467/) (2019)
- [LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models](https://mlsanity.com/paper/2311.17043/) (2023)
- [MovieChat: From Dense Token to Sparse Memory for Long Video Understanding](https://mlsanity.com/paper/2307.16449/) (2023)
- [Long Context Transfer from Language to Vision](https://mlsanity.com/paper/2406.16852/) (2024)
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [TVQA: Localized, Compositional Video Question Answering](https://mlsanity.com/paper/1809.01696/) (2018)

## Built on by (most cited first, 24 of 24)

- [Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces](https://mlsanity.com/paper/2412.14171/) (2024)
- [HD-EPIC: A Highly-Detailed Egocentric Video Dataset](https://mlsanity.com/paper/2502.04144/) (2025)
- [EgoLife: Towards Egocentric Life Assistant](https://mlsanity.com/paper/2503.03803/) (2025)
- [MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs](https://mlsanity.com/paper/2503.13111/) (2025)
- [EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering](https://mlsanity.com/paper/2502.07411/) (2025)
- [Eyes Wide Open: Ego Proactive Video-LLM for Streaming Video](https://mlsanity.com/paper/2510.14560/) (2025)
- [In the Eye of MLLM: Benchmarking Egocentric Video Intent Understanding with Gaze-Guided Prompting](https://mlsanity.com/paper/2509.07447/) (2025)
- [EgoBlind: Towards Egocentric Visual Assistance for the Blind](https://mlsanity.com/paper/2503.08221/) (2025)
- [EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT](https://mlsanity.com/paper/2510.23569/) (2025)
- [LongViTU: Instruction Tuning for Long-Form Video Understanding](https://mlsanity.com/paper/2501.05037/) (2025)
- [EgoVLM: Policy Optimization for Egocentric Video Understanding](https://mlsanity.com/paper/2506.03097/) (2025)
- [Fine-grained Spatiotemporal Grounding on Egocentric Videos](https://mlsanity.com/paper/2508.00518/) (2025)
- [EgoM2P: Egocentric Multimodal Multitask Pretraining](https://mlsanity.com/paper/2506.07886/) (2025)
- [Advancing Egocentric Video Question Answering with Multimodal Large Language Models](https://mlsanity.com/paper/2504.04550/) (2025)
- [Benchmarking Egocentric Multimodal Goal Inference for Assistive Wearable Agents](https://mlsanity.com/paper/2510.22443/) (2025)
- [Ego-EXTRA: video-language Egocentric Dataset for EXpert-TRAinee assistance](https://mlsanity.com/paper/2512.13238/) (2025)
- [Seeing Together: Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language Models](https://mlsanity.com/paper/2605.18431/) (2026)
- [LLaVAction: evaluating and training multi-modal large language models for action understanding](https://mlsanity.com/paper/2503.18712/) (2025)
- [ProbRes: Probabilistic Jump Diffusion for Open-World Egocentric Activity Recognition](https://mlsanity.com/paper/2504.03948/) (2025)
- [EgoAVU: Egocentric Audio-Visual Understanding](https://mlsanity.com/paper/2602.06139/) (2026)
- [WeaveTime: Stream from Earlier Frames into Emergent Memory in VideoLLMs](https://mlsanity.com/paper/2602.22142/) (2026)
- [Benchmarking Egocentric Clinical Intent Understanding Capability for Medical Multimodal Large Language Models](https://mlsanity.com/paper/2601.06750/) (2026)
- [EgoIntrospect: An Egocentric Dataset and Benchmark for User-Centric Internal State Reasoning](https://mlsanity.com/paper/2605.17262/) (2026)
- [Incentivizing Temporal-Awareness in Egocentric Video Understanding Models](https://mlsanity.com/paper/2603.27184/) (2026)

## Abstract (arXiv)

This research aims to comprehensively explore building a multimodal foundation model for egocentric video understanding. To achieve this goal, we work on three fronts. First, as there is a lack of QA data for egocentric video understanding, we automatically generate 7M high-quality QA samples for egocentric videos ranging from 30 seconds to one hour long in Ego4D based on human-annotated data. This is one of the largest egocentric QA datasets. Second, we contribute a challenging egocentric QA benchmark with 629 videos and 7,026 questions to evaluate the models' ability in recognizing and memorizing visual details across videos of varying lengths. We introduce a new de-biasing evaluation method to help mitigate the unavoidable language bias present in the models being evaluated. Third, we propose a specialized multimodal architecture featuring a novel "Memory Pointer Prompting" mechanism. This design includes a textitglobal glimpse step to gain an overarching understanding of the entire video and identify key visual information, followed by a fallback step that utilizes the key visual information to generate responses. This enables the model to more effectively comprehend extended video content. With the data, benchmark, and model, we build MM-Ego, an egocentric multimodal LLM that shows powerful performance on egocentric video understanding.