AlanaVLM: A Multimodal Embodied AI Foundation Model for Egocentric Video Understanding
This work addresses the need for embodied AI in robots or wearables to collaborate with humans, representing an incremental advance by adapting existing VLM methods to egocentric data.
The paper tackles the problem of egocentric video understanding for AI personal assistants by introducing AlanaVLM, a 7B parameter vision-language model trained on a new dataset, which achieves state-of-the-art performance on the OpenEQA benchmark, outperforming open-source models by 3.6% and showing competitive results against models like GPT-4V.
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.