Update README.md

README.md

@@ -15,14 +15,22 @@ For more details, please refer to the homepage:
 If this work has contributed to your research, welcome to cite it:
 
 ```
-@misc{zhao2025airscapeaerialgenerativeworld,
-      title={AirScape: An Aerial Generative World Model with Motion Controllability}, 
-      author={Baining Zhao and Rongze Tang and Mingyuan Jia and Ziyou Wang and Fanghang Man and Xin Zhang and Yu Shang and Weichen Zhang and Chen Gao and Wei Wu and Xin Wang and Xinlei Chen and Yong Li},
-      year={2025},
-      eprint={2507.08885},
-      archivePrefix={arXiv},
-      primaryClass={cs.RO},
-      url={https://arxiv.org/abs/2507.08885}, 
+@inproceedings{10.1145/3746027.3758180,
+author = {Zhao, Baining and Tang, Rongze and Jia, Mingyuan and Wang, Ziyou and Man, Fanhang and Zhang, Xin and Shang, Yu and Zhang, Weichen and Wu, Wei and Gao, Chen and Chen, Xinlei and Li, Yong},
+title = {AirScape: An Aerial Generative World Model with Motion Controllability},
+year = {2025},
+isbn = {9798400720352},
+publisher = {Association for Computing Machinery},
+address = {New York, NY, USA},
+url = {https://doi.org/10.1145/3746027.3758180},
+doi = {10.1145/3746027.3758180},
+abstract = {How to enable agents to predict the outcomes of their own motion intentions in three-dimensional space has been a fundamental problem in embodied intelligence. To explore general spatial imagination capability, we present AirScape, the first world model designed for six-degree-of-freedom aerial agents. AirScape predicts future observation sequences based on current visual inputs and motion intentions. Specifically, we construct a dataset for aerial world model training and testing, which consists of 11k video-intention pairs. This dataset includes first-person-view videos capturing diverse drone actions across a wide range of scenarios, with over 1,000 hours spent annotating the corresponding motion intentions. Then we develop a two-phase schedule to train a foundation model-initially devoid of embodied spatial knowledge-into a world model that is controllable by motion intentions and adheres to physical spatio-temporal constraints. Experimental results demonstrate that AirScape significantly outperforms existing foundation models in 3D spatial imagination capabilities, especially with over a 50\% improvement in metrics reflecting motion alignment. The project is available at: https://embodiedcity.github.io/AirScape/.},
+booktitle = {Proceedings of the 33rd ACM International Conference on Multimedia},
+pages = {12519–12528},
+numpages = {10},
+keywords = {aerial space, generative world model, motion controllability},
+location = {Dublin, Ireland},
+series = {MM '25}
 }
 ```
 ---