Exploring the Next Generation of Data
XD-MAP: Cross-Modal Domain Adaptation via Semantic Parametric Maps for Scalable Training Data Generation-
[pdf]
[bibtex]@InProceedings{Bieder_2026_CVPR, author = {Bieder, Frank and K\"onigshof, Hendrik and Hu, Haohao and Immel, Fabian and Shen, Yinzhe and Pauls, Jan-Hendrik and Stiller, Christoph}, title = {XD-MAP: Cross-Modal Domain Adaptation via Semantic Parametric Maps for Scalable Training Data Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3062-3071} }
Data Warmup: Complexity-Aware Curricula for Efficient Diffusion Training-
[pdf]
[arXiv]
[bibtex]@InProceedings{Lin_2026_CVPR, author = {Lin, Jinhong and Wang, Pan and Zhan, Zitong and Zhang, Lin and Morgado, Pedro}, title = {Data Warmup: Complexity-Aware Curricula for Efficient Diffusion Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3072-3081} }
Iterative Definition Refinement for Zero-Shot Classification via LLM-Based Semantic Prototype Optimization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Rehmat_2026_CVPR, author = {Rehmat, Naeem and Saeed, Muhammad Saad and Haq, Ijaz Ul and Malik, Khalid}, title = {Iterative Definition Refinement for Zero-Shot Classification via LLM-Based Semantic Prototype Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3082-3091} }
CADLoop: An Equivariant-Aware Skill-Grounded Loop for CAD Data Curation-
[pdf]
[bibtex]@InProceedings{Zhang_2026_CVPR, author = {Zhang, Haozhe and Chen, Miaomiao and Liu, Kaichen}, title = {CADLoop: An Equivariant-Aware Skill-Grounded Loop for CAD Data Curation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3092-3100} }

