Jaewoo Jung

Achieving state-of-the-art lensless image reconstruction, IFIN leverages a unique bidirectional coupling of forward and inverse processes to enhance data fidelity and adaptability.

Motion-aware correspondences can drastically enhance the geometric consistency of novel-view video generation, outperforming traditional methods.

GAM revolutionizes robot policy learning by seamlessly integrating 3D geometric reasoning, outperforming traditional models in accuracy and efficiency.

Forget training wheels: this training-free method leverages uncertainty to guide vision-language models to the right image regions, boosting performance on detail-oriented tasks.