RL^2-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models
Paper • 2607.26991 • Published • 4
Derek Tan Ming Siang
derektan95
·
AI & ML interests
None yet
Recent Activity
submitted a paper about 13 hours ago
RL^2-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models upvoted a paper about 21 hours ago
RL^2-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models authored a paper about 23 hours ago
RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action ModelsOrganizations
