Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes

Project page | Paper | Video

Jing Tan, Zhaoyang Zhang, Yantao Shen, Jiarui Cai, Shuo Yang, Jiajun Wu, Wei Xia, Zhuowen Tu, Stefano Soatto

✨ Updates

[2026-01-06] Paper release.

[2026-03-16] Code released at https://github.com/amazon-science/talk2move.

📆 Todo

• Release Paper
• Release Inference Code and Weights
• Release Train Code

📧 Contact Us

Jing Tan: tj023@ie.cuhk.edu.hk

✒️ Citation

If you find our work helpful for your research, please consider giving a star ⭐ and citation 📝

@misc{tan2026talk2movereinforcementlearningtextinstructed,
      title={Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes}, 
      author={Jing Tan and Zhaoyang Zhang and Yantao Shen and Jiarui Cai and Shuo Yang and Jiajun Wu and Wei Xia and Zhuowen Tu and Stefano Soatto},
      year={2026},
      eprint={2601.02356},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2601.02356}, 
}