{"ID":2898002,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.04559","arxiv_id":"2507.04559","title":"MambaVideo for Discrete Video Tokenization with Channel-Split Quantization","abstract":"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.","short_abstract":"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 limit...","url_abs":"https://arxiv.org/abs/2507.04559","url_pdf":"https://arxiv.org/pdf/2507.04559v1","authors":"[\"Dawit Mureja Argaw\",\"Xian Liu\",\"Joon Son Chung\",\"Ming-Yu Liu\",\"Fitsum Reda\"]","published":"2025-07-06T22:23:27Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false}