VideoMAP: Toward Scalable Mamba-based Video Autoregressive Pretraining
Published in arXiv preprint arXiv:2503.12332, 2025
Recommended citation: Liu, Y., Wu, P., Liang, C., Shen, J., Wang, L. & Yi, L. (2025). VideoMAP: Toward Scalable Mamba-based Video Autoregressive Pretraining. arXiv:2503.12332. https://arxiv.org/abs/2503.12332
Yunze Liu, Peiran Wu, Cheng Liang, Junxiao Shen, Limin Wang, Li Yi
Scalable Mamba-based autoregressive pretraining recipe for long-form video understanding.