pith. sign in

arxiv: 2507.04559 · v1 · pith:4LAOCZZ7new · submitted 2025-07-06 · 💻 cs.CV

MambaVideo for Discrete Video Tokenization with Channel-Split Quantization

classification 💻 cs.CV
keywords videodiscretequantizationautoregressivechannel-splitstate-of-the-arttokenizationtokenizer
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.