Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916066856271872 |
|---|---|
| author | Xing, Jiazheng Yuan, Hangjie Cai, Lingling Liu, Xinyu Wei, Yujie Du, Fei Ci, Hai Feng, Tao Tang, Jiasheng Chen, Weihua Wang, Fan Liu, Yong |
| author_facet | Xing, Jiazheng Yuan, Hangjie Cai, Lingling Liu, Xinyu Wei, Yujie Du, Fei Ci, Hai Feng, Tao Tang, Jiasheng Chen, Weihua Wang, Fan Liu, Yong |
| contents | Connector-based video unified models have demonstrated strong capability in instruction-grounded video synthesis, but integrating a large high-fidelity generator into the unified training loop is computationally prohibitive, limiting achievable visual quality. We therefore propose Lumos-Nexus, a training-efficient unified video generation framework that facilitates the development of strong reasoning-driven generation capabilities while significantly enhancing visual fidelity. Lumos-Nexus adopts a two-stage design: 1) During training, only a lightweight generator is aligned with the understanding block to learn to take in reasoning-driven semantic control. 2) During inference, we introduce Unified Progressive Frequency Bridging (UPFB) to progressively hand off generation to a high-capacity pretrained generator in the shared latent space, enabling coarse-to-fine refinement and producing high-fidelity videos without compromising reasoning quality. To fill the gap in reasoning-driven video generation benchmarks, we introduce VR-Bench, which assesses a model's capability to translate inferred intent into coherent and semantically aligned video content. Extensive experiments demonstrate that Lumos-Nexus achieves substantial gains in visual realism and temporal coherence on VBench, while exhibiting strong reasoning-based generative performance on VR-Bench. Code and models are available at https://jiazheng-xing.github.io/nexus-lumos-home/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_31603 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models Xing, Jiazheng Yuan, Hangjie Cai, Lingling Liu, Xinyu Wei, Yujie Du, Fei Ci, Hai Feng, Tao Tang, Jiasheng Chen, Weihua Wang, Fan Liu, Yong Computer Vision and Pattern Recognition Artificial Intelligence Connector-based video unified models have demonstrated strong capability in instruction-grounded video synthesis, but integrating a large high-fidelity generator into the unified training loop is computationally prohibitive, limiting achievable visual quality. We therefore propose Lumos-Nexus, a training-efficient unified video generation framework that facilitates the development of strong reasoning-driven generation capabilities while significantly enhancing visual fidelity. Lumos-Nexus adopts a two-stage design: 1) During training, only a lightweight generator is aligned with the understanding block to learn to take in reasoning-driven semantic control. 2) During inference, we introduce Unified Progressive Frequency Bridging (UPFB) to progressively hand off generation to a high-capacity pretrained generator in the shared latent space, enabling coarse-to-fine refinement and producing high-fidelity videos without compromising reasoning quality. To fill the gap in reasoning-driven video generation benchmarks, we introduce VR-Bench, which assesses a model's capability to translate inferred intent into coherent and semantically aligned video content. Extensive experiments demonstrate that Lumos-Nexus achieves substantial gains in visual realism and temporal coherence on VBench, while exhibiting strong reasoning-based generative performance on VR-Bench. Code and models are available at https://jiazheng-xing.github.io/nexus-lumos-home/. |
| title | Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2605.31603 |