Bridge V-2
Emerging4papers using it
2024first seen
'Bridge V2' is a benchmark dataset that contains time-synchronized multi-view videos used to evaluate the effectiveness of learning action-centric latent actions and their impact on vision-language-action model pretraining.
Papers using Bridge V-2 (4)
- MVP-LAM: Learning Action-Centric Latent Action via Cross-Viewpoint ReconstructionDRAW2ACT: Turning Depth-encoded Trajectories Into Robotic Demonstration VideosImage Generation As A Visual Planner For Robotic ManipulationEmma-X: An Embodied Multimodal Action Model with Grounded Chain of
Thought and Look-ahead Spatial Reasoning