1st Workshop on Video World Models: Interaction, Memory, and Efficiency
CoDA: Cosmos-driven DCT-Adaptive Sparse Attention for Efficient Robotic Trajectory Generation-
[pdf]
[bibtex]@InProceedings{Cheon_2026_CVPR, author = {Cheon, Yuseong and Kim, Sungho}, title = {CoDA: Cosmos-driven DCT-Adaptive Sparse Attention for Efficient Robotic Trajectory Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5897-5906} }
Causal Physics Steering in Video World Models via Concept Activation Vectors-
[pdf]
[bibtex]@InProceedings{Alam_2026_CVPR, author = {Alam, Nahid}, title = {Causal Physics Steering in Video World Models via Concept Activation Vectors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5890-5896} }