Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.20742 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910003643809792 |
|---|---|
| author | Jin, Xin Liu, Jinming Wei, Yuntao Lin, Junyan Wang, Zhicheng Huang, Jianguo Yang, Xudong Liu, Yanxiao Zeng, Wenjun |
| author_facet | Jin, Xin Liu, Jinming Wei, Yuntao Lin, Junyan Wang, Zhicheng Huang, Jianguo Yang, Xudong Liu, Yanxiao Zeng, Wenjun |
| contents | "Compression Tells Intelligence", is supported by research in artificial intelligence, particularly concerning (multimodal) large language models (LLMs/MLLMs), where compression efficiency often correlates with improved model performance and capabilities. For compression, classical visual coding based on traditional information theory has developed over decades, achieving great success with numerous international industrial standards widely applied in multimedia (e.g., image/video) systems. Except that, the recent emergingvisual token technology of generative multi-modal large models also shares a similar fundamental objective like visual coding: maximizing semantic information fidelity during the representation learning while minimizing computational cost. Therefore, this paper provides a comprehensive overview of two dominant technique families first -- Visual Coding and Vision Token Technology -- then we further unify them from the aspect of optimization, discussing the essence of compression efficiency and model performance trade-off behind. Next, based on the proposed unified formulation bridging visual coding andvisual token technology, we synthesize bidirectional insights of themselves and forecast the next-gen visual codec and token techniques. Last but not least, we experimentally show a large potential of the task-oriented token developments in the more practical tasks like multimodal LLMs (MLLMs), AI-generated content (AIGC), and embodied AI, as well as shedding light on the future possibility of standardizing a general token technology like the traditional codecs (e.g., H.264/265) with high efficiency for a wide range of intelligent tasks in a unified and effective manner. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_20742 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Compression Tells Intelligence: Visual Coding, Visual Token Technology, and the Unification Jin, Xin Liu, Jinming Wei, Yuntao Lin, Junyan Wang, Zhicheng Huang, Jianguo Yang, Xudong Liu, Yanxiao Zeng, Wenjun Computer Vision and Pattern Recognition "Compression Tells Intelligence", is supported by research in artificial intelligence, particularly concerning (multimodal) large language models (LLMs/MLLMs), where compression efficiency often correlates with improved model performance and capabilities. For compression, classical visual coding based on traditional information theory has developed over decades, achieving great success with numerous international industrial standards widely applied in multimedia (e.g., image/video) systems. Except that, the recent emergingvisual token technology of generative multi-modal large models also shares a similar fundamental objective like visual coding: maximizing semantic information fidelity during the representation learning while minimizing computational cost. Therefore, this paper provides a comprehensive overview of two dominant technique families first -- Visual Coding and Vision Token Technology -- then we further unify them from the aspect of optimization, discussing the essence of compression efficiency and model performance trade-off behind. Next, based on the proposed unified formulation bridging visual coding andvisual token technology, we synthesize bidirectional insights of themselves and forecast the next-gen visual codec and token techniques. Last but not least, we experimentally show a large potential of the task-oriented token developments in the more practical tasks like multimodal LLMs (MLLMs), AI-generated content (AIGC), and embodied AI, as well as shedding light on the future possibility of standardizing a general token technology like the traditional codecs (e.g., H.264/265) with high efficiency for a wide range of intelligent tasks in a unified and effective manner. |
| title | Compression Tells Intelligence: Visual Coding, Visual Token Technology, and the Unification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.20742 |