Learning Physics from Pretrained Video Models: A Multimodal Continuous and Sequential World Interaction Models for Robotic Manipulation.

@inproceedings{song-2026-learning, author = {Zijian Song and Qichang Li and Sihan Qin and Yuhao Chen and Tianshui Chen and Liang Lin and Guangrun Wang}, editor = {Stevan Rudinac and Zi Huang and Marcel Worring and Lucia Vadicamo and Xirong Li and Pascal Mettes and Lizi Liao}, title = {{Learning Physics from Pretrained Video Models: A Multimodal Continuous and Sequential World Interaction Models for Robotic Manipulation}}, booktitle = {{Proceedings of the 2026 International Conference on Multimedia Retrieval, ICMR 2026, Amsterdam, The Netherlands, June 16-19, 2026}}, pages = {758--767}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805622.3810752}, doi = {https://doi.org/10.1145/3805622.3810752} }