Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909005245317120 |
|---|---|
| author | Wu, Keming Yang, Zuhao Zhang, Kaichen Wang, Shizun Zhu, Haowei Leng, Sicong Yang, Zhongyu Wang, Qijie Wang, Sudong Wang, Ziting Wang, Zili Zhang, Hui Wang, Haonan Zhou, Hang Pu, Yifan Li, Xingxuan Zhan, Fangneng Li, Bo Bing, Lidong Song, Yuxin Liu, Ziwei Chen, Wenhu Wang, Jingdong Wang, Xinchao Qi, Xiaojuan Lu, Shijian Wang, Bin |
| author_facet | Wu, Keming Yang, Zuhao Zhang, Kaichen Wang, Shizun Zhu, Haowei Leng, Sicong Yang, Zhongyu Wang, Qijie Wang, Sudong Wang, Ziting Wang, Zili Zhang, Hui Wang, Haonan Zhou, Hang Pu, Yifan Li, Xingxuan Zhan, Fangneng Li, Bo Bing, Lidong Song, Yuxin Liu, Ziwei Chen, Wenhu Wang, Jingdong Wang, Xinchao Qi, Xiaojuan Lu, Shijian Wang, Bin |
| contents | Recent visual generation models have made major progress in photorealism, typography, instruction following, and interactive editing, yet they still struggle with spatial reasoning, persistent state, long-horizon consistency, and causal understanding. We argue that the field should move beyond appearance synthesis toward intelligent visual generation: plausible visuals grounded in structure, dynamics, domain knowledge, and causal relations. To frame this shift, we introduce a five-level taxonomy: Atomic Generation, Conditional Generation, In-Context Generation, Agentic Generation, and World-Modeling Generation, progressing from passive renderers to interactive, agentic, world-aware generators. We analyze key technical drivers, including flow matching, unified understanding-and-generation models, improved visual representations, post-training, reward modeling, data curation, synthetic data distillation, and sampling acceleration. We further show that current evaluations often overestimate progress by emphasizing perceptual quality while missing structural, temporal, and causal failures. By combining benchmark review, in-the-wild stress tests, and expert-constrained case studies, this roadmap offers a capability-centered lens for understanding, evaluating, and advancing the next generation of intelligent visual generation systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_28185 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling Wu, Keming Yang, Zuhao Zhang, Kaichen Wang, Shizun Zhu, Haowei Leng, Sicong Yang, Zhongyu Wang, Qijie Wang, Sudong Wang, Ziting Wang, Zili Zhang, Hui Wang, Haonan Zhou, Hang Pu, Yifan Li, Xingxuan Zhan, Fangneng Li, Bo Bing, Lidong Song, Yuxin Liu, Ziwei Chen, Wenhu Wang, Jingdong Wang, Xinchao Qi, Xiaojuan Lu, Shijian Wang, Bin Computer Vision and Pattern Recognition Recent visual generation models have made major progress in photorealism, typography, instruction following, and interactive editing, yet they still struggle with spatial reasoning, persistent state, long-horizon consistency, and causal understanding. We argue that the field should move beyond appearance synthesis toward intelligent visual generation: plausible visuals grounded in structure, dynamics, domain knowledge, and causal relations. To frame this shift, we introduce a five-level taxonomy: Atomic Generation, Conditional Generation, In-Context Generation, Agentic Generation, and World-Modeling Generation, progressing from passive renderers to interactive, agentic, world-aware generators. We analyze key technical drivers, including flow matching, unified understanding-and-generation models, improved visual representations, post-training, reward modeling, data curation, synthetic data distillation, and sampling acceleration. We further show that current evaluations often overestimate progress by emphasizing perceptual quality while missing structural, temporal, and causal failures. By combining benchmark review, in-the-wild stress tests, and expert-constrained case studies, this roadmap offers a capability-centered lens for understanding, evaluating, and advancing the next generation of intelligent visual generation systems. |
| title | Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.28185 |