polar-bridge-vla

PoLAR Bridge VLA

BridgeData V2 latent VLA checkpoint for PoLAR, as presented in the paper PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning.

• Project Page: https://joon-stack.github.io/PoLAR
• GitHub Repository: https://github.com/joon-stack/PoLAR

Model Details

• model family: hyperbolic_factorized_radprog
• latent action token length: 5
• codebook size: 32
• predicted action horizon: 10

This repository keeps the Hugging Face model snapshot filenames intact so it can be loaded by the PoLAR evaluation code.

Citation

@misc{jeong2026polar,
  title = {PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning},
  author = {Jeong, Youngjoon and Yu, Jihwan and Jo, Minsoo and Chun, Junha and Kim, Taesup},
  year = {2026},
  eprint = {2606.21139},
  archivePrefix = {arXiv}
}