paper7Updated Nov 21, 2026 · Português
← All papers

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models

Derek Ming Siang Tan, Shailesh Shailesh, Srikrishna Iyer, William Wei Jie Teo, Yunpeng Ju, Qiao Gu, Guillaume Sartoretti