OpenVLA-OFT
Emerging4papers using it
2025first seen
OpenVLA-OFT is a benchmark dataset used to evaluate Vision-Language-Action models in the context of embodied robotic manipulation, focusing on their ability to integrate visual inputs and natural language instructions while adhering to physical principles.
Papers using OpenVLA-OFT (4)
- SimpleVLA-RL: Scaling VLA Training via Reinforcement LearningPhysVLA: Towards Physically-Grounded VLA for Embodied Robotic ManipulationSTRONG-VLA: Decoupled Robustness Learning for Vision-Language-Action Models under Multimodal PerturbationsVISTA: Enhancing Visual Conditioning via Track-Following Preference Optimization in Vision-Language-Action Models