UP Lab

Recent publications

1. ICML

   From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation

   Yajie Li, Bozhou Zhang, Chun Gu, Zipei Ma, Jiahui Zhang, Jiankang Deng,  Xiatian Zhu, and Li Zhang

   In Forty-third International Conference on Machine Learning 2026

   Bib PDF

   @inproceedings{li2026imaginedfutures,
     title = {From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation},
     author = {Li, Yajie and Zhang, Bozhou and Gu, Chun and Ma, Zipei and Zhang, Jiahui and Deng, Jiankang and Zhu, Xiatian and Zhang, Li},
     booktitle = {Forty-third International Conference on Machine Learning},
     year = {2026},
   }

2. CVPR

   RAID: Retrieval-Augmented Anomaly Detection

   Mingxiu Cai, Zhe Zhang, Gaochang Wu, Tianyou Chai, and Xiatian Zhu

   In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2026

   Bib PDF Code

   @inproceedings{cai2026raidretrievalaugmentedanomalydetection,
     title = {RAID: Retrieval-Augmented Anomaly Detection},
     author = {Cai, Mingxiu and Zhang, Zhe and Wu, Gaochang and Chai, Tianyou and Zhu, Xiatian},
     year = {2026},
     booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
   }

3. CVPR (Highlight)

   EthoCLIP: Ontology-Enhanced Video-Language Pretraining for Animal Behavior Understanding

   Yinuo Jing, Jinyan Wu, Zixi Yang, Kongming Liang,  Xiatian Zhu, and Zhanyu Ma

   In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2026

   Bib PDF Code

   @inproceedings{jing2026ethoclip,
     title = {EthoCLIP: Ontology-Enhanced Video-Language Pretraining for Animal Behavior Understanding},
     author = {Jing, Yinuo and Wu, Jinyan and Yang, Zixi and Liang, Kongming and Zhu, Xiatian and Ma, Zhanyu},
     year = {2026},
     booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
   }

4. CVPR

   SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Driving

   Jingyu Li, Junjie Wu, Dongnan Hu, Xiangkai Huang, Bin Sun, Zhihui Hao, Xianpeng Lang,  Xiatian Zhu, and Li Zhang

   In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2026

   Bib PDF Code

   @inproceedings{li2026sgdrive,
     title = {SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Driving},
     author = {Li, Jingyu and Wu, Junjie and Hu, Dongnan and Huang, Xiangkai and Sun, Bin and Hao, Zhihui and Lang, Xianpeng and Zhu, Xiatian and Zhang, Li},
     booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
     year = {2026},
   }

5. CVPR-F

   SCOPE: Scene-Contextualized Incremental Few-Shot 3D Segmentation

   Vishal Thengane, Zhaochong An, Tianjin Huang, Son Lam Phung, Abdesselam Bouzerdoum, Lu Yin, Na Zhao, and Xiatian Zhu

   In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (Findings Track) 2026

   Bib PDF Code

   @inproceedings{thengane2026scopescenecontextualizedincrementalfewshot,
     title = {SCOPE: Scene-Contextualized Incremental Few-Shot 3D Segmentation},
     author = {Thengane, Vishal and An, Zhaochong and Huang, Tianjin and Phung, Son Lam and Bouzerdoum, Abdesselam and Yin, Lu and Zhao, Na and Zhu, Xiatian},
     year = {2026},
     booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (Findings Track)},
   }

6. CVPR-F

   See Tomorrow, Act Today: Foresight-Driven Autonomous Driving

   Bozhou Zhang, Nan Song, Yuang Wang, Jiankang Deng,  Xiatian Zhu, and Li Zhang

   In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (Findings Track) 2026

   Bib PDF Code

   @inproceedings{zhang2026tomorrowacttodayforesightdriven,
     title = {See Tomorrow, Act Today: Foresight-Driven Autonomous Driving},
     author = {Zhang, Bozhou and Song, Nan and Wang, Yuang and Deng, Jiankang and Zhu, Xiatian and Zhang, Li},
     year = {2026},
     booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (Findings Track)},
   }

7. ICLR

   MergeTune: Continued fine-tuning of vision-language models

   Wenqing Wang, Da Li,  Xiatian Zhu, and Josef Kittler

   In Proceedings of International Conference on Learning Representations 2026

   Bib PDF

   @inproceedings{wang2026mergetune,
     title = {MergeTune: Continued fine-tuning of vision-language models},
     author = {Wang, Wenqing and Li, Da and Zhu, Xiatian and Kittler, Josef},
     year = {2026},
     booktitle = {Proceedings of International Conference on Learning Representations},
   }

8. ICLR

   Consistent text-to-image generation via scene de-contextualization

   Song Tang, Peihao Gong, Kunyu Li, Kai Guo, Boyu Wang, Mao Ye, Jianwei Zhang, and Xiatian Zhu

   In Proceedings of International Conference on Learning Representations 2026

   Bib PDF

   @inproceedings{tang2025consistenttexttoimagegenerationscene,
     title = {Consistent text-to-image generation via scene de-contextualization},
     author = {Tang, Song and Gong, Peihao and Li, Kunyu and Guo, Kai and Wang, Boyu and Ye, Mao and Zhang, Jianwei and Zhu, Xiatian},
     year = {2026},
     booktitle = {Proceedings of International Conference on Learning Representations},
   }

9. ICLR

   Dynamic Novel View Synthesis in High Dynamic Range

   Kaixuan Zhang, Zhipeng Xiong, Minxian Li, Mingwu Ren, Jiankang Deng, and Xiatian Zhu

   In Proceedings of International Conference on Learning Representations 2026

   Bib PDF Code

   @inproceedings{zhang2025dynamicnovelviewsynthesis,
     title = {Dynamic Novel View Synthesis in High Dynamic Range},
     author = {Zhang, Kaixuan and Xiong, Zhipeng and Li, Minxian and Ren, Mingwu and Deng, Jiankang and Zhu, Xiatian},
     year = {2026},
     booktitle = {Proceedings of International Conference on Learning Representations},
   }