TAVEN: Task-driven Adaptive Viewpoint Exploration for Training-Free 3D Spatial Reasoning and Understanding.

@inproceedings{jiang-2026-taven, author = {Shuyi Jiang and Zhihao Yuan and Na Zhao}, editor = {Stevan Rudinac and Zi Huang and Marcel Worring and Lucia Vadicamo and Xirong Li and Pascal Mettes and Lizi Liao}, title = {{TAVEN: Task-driven Adaptive Viewpoint Exploration for Training-Free 3D Spatial Reasoning and Understanding}}, booktitle = {{Proceedings of the 2026 International Conference on Multimedia Retrieval, ICMR 2026, Amsterdam, The Netherlands, June 16-19, 2026}}, pages = {911--920}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805622.3810869}, doi = {https://doi.org/10.1145/3805622.3810869} }