Averaging and temporally interpolating text latents in VLAs enables 83% success on novel task combinations in the libero-ood benchmark where SOTA models achieve under 15%.
Libero: Benchmarking knowledge transfer for lifelong robot learning.Advances in Neural Information Processing Systems, 36, 2024
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
A discrete diffusion model tokenizes multimodal robotic data and uses a progress token to predict future states and task completion for scalable policy evaluation.
Pose-VLA uses a decoupled two-stage pre-training with discrete pose tokens to extract universal 3D spatial priors from 3D datasets and robotic trajectories, achieving 79.5% success on RoboTwin 2.0 and 96.0% on LIBERO.
citing papers explorer
-
VLAs are Confined yet Capable of Generalizing to Novel Instructions
Averaging and temporally interpolating text latents in VLAs enables 83% success on novel task combinations in the libero-ood benchmark where SOTA models achieve under 15%.
-
dWorldEval: Scalable Robotic Policy Evaluation via Discrete Diffusion World Model
A discrete diffusion model tokenizes multimodal robotic data and uses a progress token to predict future states and task completion for scalable policy evaluation.
-
Universal Pose Pretraining for Generalizable Vision-Language-Action Policies
Pose-VLA uses a decoupled two-stage pre-training with discrete pose tokens to extract universal 3D spatial priors from 3D datasets and robotic trajectories, achieving 79.5% success on RoboTwin 2.0 and 96.0% on LIBERO.