MAGE: Multimodal Alignment and Generation Enhancement via Bridging Visual and Semantic Spaces

E et al. "MAGE: Multimodal Alignment and Generation Enhancement via Bridging Visual and Semantic Spaces." International Joint Conference on Artificial Intelligence, 2025. doi:10.24963/IJCAI.2025/107

[E et al. "MAGE: Multimodal Alignment and Generation Enhancement via Bridging Visual and Semantic Spaces." International Joint Conference on Artificial Intelligence, 2025.](https://mlanthology.org/ijcai/2025/e2025ijcai-mage/) doi:10.24963/IJCAI.2025/107

@inproceedings{e2025ijcai-mage,
  title     = {{MAGE: Multimodal Alignment and Generation Enhancement via Bridging Visual and Semantic Spaces}},
  author    = {E, Shaojun and Yang, Yuchen and Wu, Jiaheng and Zhang, Yan and Zhao, Tiejun and Chen, Ziyan},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {954-962},
  doi       = {10.24963/IJCAI.2025/107},
  url       = {https://mlanthology.org/ijcai/2025/e2025ijcai-mage/}
}