张蒲石 Pushi Zhang

@article{yu2026walloss,
  title = {Wall-OSS-0.5 Technical Report},
  author = {Yu, Ryan and Zhang, Pushi and Liu, Starrick and Liu, Brae and Kang, Miracle and Li, Shalfun and Shi, Lights and Ma, Ellie and Yang, Ping and Pan, Chris and Chen, Jerry and Liu, Dongxiu and Sun, Rain and Guo, Miles and Zhang, Byron and Zhou, Hugo and Xu, Zach and Chen, Vincent and Huang, Harrison and Wang, James and Kuzi, Dance and Zhai, Andy and Su, Hang and Gan, Roy and Liang, Lucy and Wang, Hao and Wang, Qian},
  journal = {arXiv preprint arXiv:2605.30877},
  year = {2026},
}

@article{kang2026xtokenizer,
  title = {X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretraining},
  author = {Kang, Miracle and Shi, Lights and Liang, Lucy and Gan, Roy and Liu, Dongxiu and Zhang, Pushi and Chen, Sylas and Qin, Shawn and Zheng, Yinan and Zheng, Jinliang and Wang, Hao and Zhan, Xianyuan and Su, Hang},
  journal = {arXiv preprint arXiv:2606.14752},
  year = {2026},
}

@article{li2026wallwm,
  title = {WALL-WM: Carving World Action Modeling at the Event Joints},
  author = {Li, Shalfun and Yao, Victor and Yang, Charles and Qu, Truth and Cheng, Regis and Yu, Ryan and Lu, Howard and Von, Newton and Chen, Vincent and Tang, Yohann and Zhang, Maeve and Ma, Ellie and Li, Gody and Liu, Starrick and Yang, Sage and Shu, Lorien and Gao, J. W. and Chen, Ethan and Ye, Colin and Sun, Yu and Mon, Elise and Zhang, Pushi and Li, Neo and Li, Lily and Wang, James and Yang, Ping and Pan, Chris and Liang, Lucy and Su, Hang and Gan, Roy and Wang, Hao and Wang, Qian},
  journal = {arXiv preprint arXiv:2606.01955},
  year = {2026},
  note = {Early version at ECCV 2026 Workshop (STEAI), Oral}
}

@inproceedings{chen2026villax,
  title = {villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models},
  author = {Chen, Xiaoyu and Wei, Hangxing and Zhang, Pushi and Zhang, Chuheng and Wang, Kaixin and Guo, Yanjiang and Yang, Rushuai and Wang, Yucen and Xiao, Xinquan and Zhao, Li and Chen, Jianyu and Bian, Jiang},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
}

@inproceedings{zhang2025lam,
  title = {What Do Latent Action Models Actually Learn?},
  author = {Zhang, Chuheng and Pearce, Tim and Zhang, Pushi and Wang, Kaixin and Chen, Xiaoyu and Shen, Wei and Zhao, Li and Bian, Jiang},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  volume = {38},
  pages = {146676--146697},
  year = {2025},
}

@article{wan2025pignav,
  title = {PIG-Nav: Key Insights for Pretrained Image Goal Navigation Models},
  author = {Wan, Jiansong and Zhou, Chengming and Liu, Jinkua and Huang, Xiangge and Chen, Xiaoyu and Yi, Xiaohan and Yang, Qisen and Zhu, Baiting and Cai, Xin-Qiang and Liu, Lixing and Yang, Rushuai and Zhang, Chuheng and Abdelfattah, Sherif and Shin, Hayong and Zhang, Pushi and Zhao, Li and Bian, Jiang},
  journal = {arXiv preprint arXiv:2507.17220},
  year = {2025},
}

@article{chen2024igor,
  title = {IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI},
  author = {Chen, Xiaoyu and Guo, Junliang and He, Tianyu and Zhang, Chuheng and Zhang, Pushi and Yang, Derek Cathera and Zhao, Li and Bian, Jiang},
  journal = {arXiv preprint arXiv:2411.00785},
  year = {2024},
}