RynnEC: Bringing MLLMs into Embodied World
This work addresses the problem of fine-grained perception and interaction for embodied agents, offering a region-centric video paradigm to advance general-purpose cognitive cores, though it appears incremental as it builds upon existing vision-language models.
The authors tackled the challenge of enabling multimodal large language models (MLLMs) to interact with the physical world by introducing RynnEC, a video-based model for embodied cognition, which achieves state-of-the-art performance in object property understanding, segmentation, and spatial reasoning.
We introduce RynnEC, a video multimodal large language model designed for embodied cognition. Built upon a general-purpose vision-language foundation model, RynnEC incorporates a region encoder and a mask decoder, enabling flexible region-level video interaction. Despite its compact architecture, RynnEC achieves state-of-the-art performance in object property understanding, object segmentation, and spatial reasoning. Conceptually, it offers a region-centric video paradigm for the brain of embodied agents, providing fine-grained perception of the physical world and enabling more precise interactions. To mitigate the scarcity of annotated 3D datasets, we propose an egocentric video based pipeline for generating embodied cognition data. Furthermore, we introduce RynnEC-Bench, a region-centered benchmark for evaluating embodied cognitive capabilities. We anticipate that RynnEC will advance the development of general-purpose cognitive cores for embodied agents and facilitate generalization across diverse embodied tasks. The code, model checkpoints, and benchmark are available at: https://github.com/alibaba-damo-academy/RynnEC