Tag
This paper introduces VideoRAE, a representation autoencoder that leverages frozen video foundation models to create compact, reconstruction-capable, and generation-friendly video latents. It achieves state-of-the-art results on UCF-101 with faster convergence than competing autoencoders.
LingBot-Video, a 30B parameter MoE-based video foundation model for embodied intelligence, has been released on Hugging Face with only 3B active parameters at inference, augmented with 70K hours of embodied data.