Multi-Agent Embodied Intelligent Systems Meet Agentic-AI era: Opportunities, Challenges and Futures
Bridging the Pretrain-to-Real Gap: Alignment Challenges in Deploying Generalist VLA Models for Additive Manufacturing-
[pdf]
[bibtex]@InProceedings{Liu_2026_CVPR, author = {Liu, Zhugang and Zhang, Kaichuang and Lu, Qi and Saenz, Efren and Asare, Martha and Ermolinsky, Maxim and Hernandez, Jose and Yang, Jinghao}, title = {Bridging the Pretrain-to-Real Gap: Alignment Challenges in Deploying Generalist VLA Models for Additive Manufacturing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {1048-1056} }
Mitigating Multi-Module Errors for Reliable Navigation in Dynamic Environments via Online Trajectory Refinement-
[pdf]
[bibtex]@InProceedings{Yin_2026_CVPR, author = {Yin, Qi and Shi, Yangming}, title = {Mitigating Multi-Module Errors for Reliable Navigation in Dynamic Environments via Online Trajectory Refinement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {1077-1086} }
HeckNav: Interpretable Heuristic Knowledge Navigation via Bayesian Probabilistic Inference-
[pdf]
[bibtex]@InProceedings{Jiang_2026_CVPR, author = {Jiang, Xianshun and Xiong, Yao and Gao, Xiangbo and Huang, Yanjia and Tu, Zhengzhong}, title = {HeckNav: Interpretable Heuristic Knowledge Navigation via Bayesian Probabilistic Inference}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {1040-1047} }
Multi-Agent Video Prediction: Self-Correcting Conditional Frames for Dynamic Scene Forecasting-
[pdf]
[bibtex]@InProceedings{Zhang_2026_CVPR, author = {Zhang, Qixin and Gurumadaiah, Ajay Kumar and Zhang, Zhi-Li}, title = {Multi-Agent Video Prediction: Self-Correcting Conditional Frames for Dynamic Scene Forecasting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {1087-1096} }
Fine-Tuning Large Language Models for Cooperative Tactical Deconfliction of Small Unmanned Aerial Systems-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Sharifi_2026_CVPR, author = {Sharifi, Iman and Zongo, Alex and Wei, Peng}, title = {Fine-Tuning Large Language Models for Cooperative Tactical Deconfliction of Small Unmanned Aerial Systems}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {1067-1076} }
Diverse Yet Consistent: Context-Guided Diffusion with Energy-Based Joint Refinement for Multi-Agent Motion Prediction-
[pdf]
[arXiv]
[bibtex]@InProceedings{Chu_2026_CVPR, author = {Chu, Lei and zhao, Yuhuan}, title = {Diverse Yet Consistent: Context-Guided Diffusion with Energy-Based Joint Refinement for Multi-Agent Motion Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {1029-1039} }
CoSA-3D: Vision-Only Automatic 3D Annotation for Cooperative Perception-
[pdf]
[bibtex]@InProceedings{Lu_2026_CVPR, author = {Lu, Chenyang and Wang, Jiahao and Yu, Mingda and Lei, Dianqiao and Xu, Shaobing and Wang, Jianqiang}, title = {CoSA-3D: Vision-Only Automatic 3D Annotation for Cooperative Perception}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {1057-1066} }