Hi, I'm Shujie Zhang

Publications

• 
  VLMs are Native Action Models: Unleashing the Manipulation Capabilities of VLMs with Explicit Action-Space Grounding

  Jingkun Yi*, Shujie Zhang*, Zirui Zhou, Haoxiao Wang, Haiyang Sun, ..., Jiangning Zhang^† (under review)

  arXiv | Code | Page | Video

• 
  RoboSnap: One-Shot Real-to-Sim Scene Generation for Generalizable Robot Learning and Evaluation

  Shujie Zhang*, Jingkun Yi*, Weipeng Zhong, Zirui Zhou, Yangkun Zhu, Hanqing Wang, Xudong Xu, Weinan Zhang, Chunhua Shen

  Conference on Robot Learning (CoRL 2026)

  arXiv | Code | Pdf | Page | Video

• 
  RoboVIP: Multi-View Video Generation with Visual Identity Prompting Augments Robot Manipulation

  B. Wang*, H. Zhang*, Shujie Zhang*, et al.

  arXiv | Code | Page

• 
  All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent

  Yandan Yang*, Baoxiong Jia*, Shujie Zhang, Siyuan Huang

  NeurIPS 2025 & IROS 2025 Workshop Best Paper

  arXiv | Code | Pdf | Page

• 
  Pair2Scene: Learning Local Object Relations for Procedural Scene Generation

  X. Ran, Shujie Zhang, W. Zhong, L. Luo, B. Dai

  International Conference on Machine Learning (ICML 2026)

  arXiv | Page

• 
  3D Scene Change Modeling With Consistent Multi-View Aggregation

  Zirui Zhou, J. Ni, Shujie Zhang, Y. Chen, Siyuan Huang

  International Conference on 3D Vision (3DV 2026)

  arXiv | Code | Page