Xin Gao

We propose GOOD, a training-free framework that leverages off-the-shelf classifiers to guide diffusion models for generating diverse, informative OOD samples—improving outlier exposure without requiring external datasets or embedding alignment.

OrderMind is a spatial-aware framework for manipulation ordering in cluttered environments. It learns object manipulation orderings by encoding spatial relationships. It outperforms existing methods in both simulated and real-world tasks.