Yi Xiao

Triangular consistency can universally enhance optical flow learning, yielding consistent performance gains across diverse training settings without additional annotations.

RealityBridge closes the Sim-to-Real gap in 3D driving simulations, achieving superior visual fidelity and temporal stability that existing methods fail to deliver.

Achieve the accuracy of complex 4D data assimilation with the speed of end-to-end inference by operating in a learned latent space.