Ang Li

Frozen medical AI models can now continuously learn and improve from real-world deployment experience without requiring weight updates or risking catastrophic forgetting.

Logistic regression GD with a large stepsize achieves polylogarithmic convergence to zero loss on linearly separable data, bypassing the sublinear rates of prior theory.

Unified prediction of future RGB, depth, normals, and segmentation from actions unlocks substantial gains in robot manipulation success.

Language components in VLA models are often redundant, allowing for significant performance gains by reducing their size without sacrificing control quality.