# AlanaVLM: A Multimodal Embodied AI Foundation Model for Egocentric Video Understanding

arXiv: https://arxiv.org/abs/2406.13807 · HTML: https://mlsanity.com/paper/2406.13807/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 28 references that are in the map.
- First posted on arXiv 19 Jun 2024.

## Builds on (most cited first, 15 of 15)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding](https://mlsanity.com/paper/2308.09126/) (2023)
- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)
- [Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI](https://mlsanity.com/paper/2109.08238/) (2021)
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding](https://mlsanity.com/paper/2311.08046/) (2023)
- [MIMIC-IT: Multi-Modal In-Context Instruction Tuning](https://mlsanity.com/paper/2306.05425/) (2023)
- [Visually Grounded Reasoning across Languages and Cultures](https://mlsanity.com/paper/2109.13238/) (2021)
- [Lost in Space: Probing Fine-grained Spatial Understanding in Vision and Language Resamplers](https://mlsanity.com/paper/2404.13594/) (2024)
- [Multitask Multimodal Prompted Training for Interactive Embodied Task Completion](https://mlsanity.com/paper/2311.04067/) (2023)

## Built on by (most cited first, 23 of 23)

- [RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics](https://mlsanity.com/paper/2411.16537/) (2024)
- [VLM4D: Towards Spatiotemporal Awareness in Vision Language Models](https://mlsanity.com/paper/2508.02095/) (2025)
- [Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning](https://mlsanity.com/paper/2504.12680/) (2025)
- [UrbanVideo-Bench: Benchmarking Vision-Language Models on Embodied Intelligence with Video Data in Urban Spaces](https://mlsanity.com/paper/2503.06157/) (2025)
- [ECBench: Can Multi-modal Foundation Models Understand the Egocentric World? A Holistic Embodied Cognition Benchmark](https://mlsanity.com/paper/2501.05031/) (2025)
- [Large language models for artificial general intelligence (AGI): A survey of foundational principles and approaches](https://mlsanity.com/paper/2501.03151/) (2025)
- [Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input](https://mlsanity.com/paper/2504.08449/) (2025)
- [CLiViS: Unleashing Cognitive Map through Linguistic-Visual Synergy for Embodied Visual Reasoning](https://mlsanity.com/paper/2506.17629/) (2025)
- [EgoM2P: Egocentric Multimodal Multitask Pretraining](https://mlsanity.com/paper/2506.07886/) (2025)
- [VideoBrain: Learning Adaptive Frame Sampling for Long Video Understanding](https://mlsanity.com/paper/2602.04094/) (2026)
- [Towards Comprehensive Scene Understanding: Integrating First and Third-Person Views for LVLMs](https://mlsanity.com/paper/2505.21955/) (2025)
- [ANNEXE: Unified Analyzing, Answering, and Pixel Grounding for Egocentric Interaction](https://mlsanity.com/paper/2504.01472/) (2025)
- [Building Egocentric Procedural AI Assistant: Methods, Benchmarks, and Challenges](https://mlsanity.com/paper/2511.13261/) (2025)
- [EgoPrune: Efficient Token Pruning for Egomotion Video Reasoning in Embodied Agent](https://mlsanity.com/paper/2507.15428/) (2025)
- [ProbRes: Probabilistic Jump Diffusion for Open-World Egocentric Activity Recognition](https://mlsanity.com/paper/2504.03948/) (2025)
- [R4: Retrieval-Augmented Reasoning for Vision-Language Models in 4D Spatio-Temporal Space](https://mlsanity.com/paper/2512.15940/) (2025)
- [Bridging the Gap Between Multimodal Foundation Models and World Models](https://mlsanity.com/paper/2510.03727/) (2025)
- [EARL: Towards a Unified Analysis-Guided Reinforcement Learning Framework for Egocentric Interaction Reasoning and Pixel Grounding](https://mlsanity.com/paper/2605.14742/) (2026)
- [Efficient Spatial-Temporal Focal Adapter with SSM for Temporal Action Detection](https://mlsanity.com/paper/2604.09164/) (2026)
- [Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation](https://mlsanity.com/paper/2607.14497/) (2026)
- [Budget-Constrained Embodied Perception: Four Resource Walls and a Pre-Registered Evaluation of Access-Structured Perception on Open Models at less than 31B](https://mlsanity.com/paper/2608.22975/) (2026)
- [Informative Viewpoint Selection for Episodic-Memory Embodied Question Answering using Omnidirectional Images](https://mlsanity.com/paper/2609.33288/) (2026)
- [Mind the Temporal Gap: Evaluating Video Models for Temporal Understanding in Driving](https://mlsanity.com/paper/2610.12575/) (2026)

## Abstract (arXiv)

AI personal assistants deployed via robots or wearables require embodied understanding to collaborate with humans effectively. However, current Vision-Language Models (VLMs) primarily focus on third-person view videos, neglecting the richness of egocentric perceptual experience. To address this gap, we propose three key contributions. First, we introduce the Egocentric Video Understanding Dataset (EVUD) for training VLMs on video captioning and question answering tasks specific to egocentric videos. Second, we present AlanaVLM, a 7B parameter VLM trained using parameter-efficient methods on EVUD. Finally, we evaluate AlanaVLM's capabilities on OpenEQA, a challenging benchmark for embodied video question answering. Our model achieves state-of-the-art performance, outperforming open-source models including strong Socratic models using GPT-4 as a planner by 3.6%. Additionally, we outperform Claude 3 and Gemini Pro Vision 1.0 and showcase competitive results compared to Gemini Pro 1.5 and GPT-4V, even surpassing the latter in spatial reasoning. This research paves the way for building efficient VLMs that can be deployed in robots or wearables, leveraging embodied video understanding to collaborate seamlessly with humans in everyday tasks, contributing to the next generation of Embodied AI.