works on
latent compositional steering 1offline reinforcement learning 1out-of-domain generalization 1test-time adaptation 1vision-language-action 1

From the 1 of 1 linked paper with an AI index.

collaborators
Showing cs.ROShow all

1 paper · 1 filter

cs.RO2026

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

Derek Ming Siang Tan, Shailesh Shailesh, Srikrishna Iyer +4

The paper presents RL², an adaptive test‑time steering framework that uses offline reinforcement learning on latent features from a frozen Vision‑Language‑Action model to compose a…