Discrete video tokenization is essential for efficient autoregressive generative modeling due to the high dimensionality of video data. This work introduces a state-of-the-art discrete video tokenizer with two key contributions. First, we propose a novel Mamba-based encoder-decoder architecture that overcomes the limitations of previous sequencebased tokenizers. Second, we introduce a new quantization scheme, channel-split quantization, which significantly enhances the representational power of quantized latents while preserving the token count. Our model sets a new state-of-the-art, outperforming both causal 3D convolutionbased and Transformer-based approaches across multiple datasets. Experimental results further demonstrate its robustness as a tokenizer for autoregressive video generation.
@article{arxiv.2507.04559,
title = {MambaVideo for Discrete Video Tokenization with Channel-Split Quantization},
author = {Dawit Mureja Argaw and Xian Liu and Joon Son Chung and Ming-Yu Liu and Fitsum Reda},
journal= {arXiv preprint arXiv:2507.04559},
year = {2025}
}