LongCat-Next: Lexicalizing Modalities as Discrete Tokens

• URL: http://arxiv.org/abs/2603.27538v1
• Date: Sun, 29 Mar 2026 06:35:03 GMT
• Title: LongCat-Next: Lexicalizing Modalities as Discrete Tokens
• Abstract summary: LongCat-Next is a native multimodal model that processes text, vision, and audio under a single autoregressive objective.<n>In particular, LongCat-Next addresses the long-standing performance ceiling of discrete vision modeling on understanding tasks.<n>As an attempt toward native multimodality, we open-source the LongCat-Next and its tokenizers, hoping to foster further research and development in the community.
• Score: 111.50794040093656
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 tokenization and de-tokenization at arbitrary resolutions, transforming continuous visual signals into hierarchical discrete tokens. Building on this foundation, we develop LongCat-Next, a native multimodal model that processes text, vision, and audio under a single autoregressive objective with minimal modality-specific design. As an industrial-strength foundation model, it excels at seeing, painting, and talking within a single framework, achieving strong performance across a wide range of multimodal benchmarks. In particular, LongCat-Next addresses the long-standing performance ceiling of discrete vision modeling on understanding tasks and provides a unified approach to effectively reconcile the conflict between understanding and generation. As an attempt toward native multimodality, we open-source the LongCat-Next and its tokenizers, hoping to foster further research and development in the community. GitHub: https://github.com/meituan-longcat/LongCat-Next

Related papers

• Toward Native Multimodal Modeling: A Roadmap [73.2994129763275]
  Multimodal modeling represents a vital step from modality-agnostic reasoning toward world modeling.<n>Recent efforts have shifted the paradigm toward native multimodal modeling.<n>Despite its potential, the design space of native architectures remains insufficiently defined.
  arXiv  Detail & Related papers  (2026-05-25T01:57:43Z)
• Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion [66.78268790956493]
  We introduce Omni-Diffusion, the first any-to-any multimodal language model built entirely on mask-based discrete diffusion models.<n>Our method outperforms or performs on par with existing multimodal systems that process two or more modalities.
  arXiv  Detail & Related papers  (2026-03-06T18:59:57Z)
• Kelix Technical Report [86.64551727600104]
  We present Kelix, a fully discrete autoregressive unified model that closes the understanding gap between discrete and continuous visual representations.<n>Recent work has explored discrete visual tokenization to enable fully autoregressive multimodal modeling.
  arXiv  Detail & Related papers  (2026-02-10T14:48:26Z)
• NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching [64.10695425442164]
  We introduce NExT-OMNI, an open-source omnimodal foundation model that achieves unified modeling through discrete flow paradigms.<n>Trained on large-scale interleaved text, image, video, and audio data, NExT-OMNI delivers competitive performance on multimodal generation and understanding benchmarks.<n>To advance further research, we release training details, data protocols, and open-source both the code and model checkpoints.
  arXiv  Detail & Related papers  (2025-10-15T16:25:18Z)
• OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generation [91.45421429922506]
  OneCAT is a unified multimodal model that seamlessly integrates understanding, generation, and editing.<n>Our framework eliminates the need for external components such as Vision Transformers (ViT) or vision tokenizer during inference.
  arXiv  Detail & Related papers  (2025-09-03T17:29:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.