rl2-vla-qam-droid

Model Card for RL2-VLA QAM - DROID

For more information on usage, please refer to the RL2-VLA Github repository here.

<img src="rl2_main_teaser.png" width="100%"/>

Citation

@article{tan2026rl2,
  title   = {RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models},
  author  = {Derek Ming Siang Tan and Shailesh Shailesh and Srikrishna Iyer and William Wei Jie Teo and Yuanliang Ju and Qiao Gu and Guillaume Sartoretti},
  year    = {2026},
  journal = {arXiv preprint arXiv:2607.26991}
}