LongCat-Next: Lexicalizing Modalities as Discrete Tokens
The prevailing Next-Token Prediction (NTP) paradigm has driven the success of large language models through discrete autoregressive modeling. However, contemporary multimodal systems remain language-centric, often treating non-linguistic modalities as external attachments, leading to fragmented architectures and suboptimal integration. To transcend this limitation, we introduce Discrete Native Autoregressive (DiNA), a unified framework that represents multimodal information within a shared discrete space, enabling a consistent and principled autoregressive modeling across modalities. A key innovation is the Discrete Native Any-resolution Visual Transformer (dNaViT), which performs tokeniz...
| Authors | Meituan LongCat Team, Bin Xiao, Chao Wang et al. |
|---|---|
| Primary category | cs.CV |
| Published | 29 March 2026 |
| Last updated at source | 29 March 2026 |
Connected in the knowledge graph
- meituan-longcat/LongCat-NextModel · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.