Gordon Guocheng Qian

Adversarial distillation achieves state-of-the-art few-step visual generation by learning log-density ratios directly via classification, eliminating the need for auxiliary score fitting.

Severe oversaturation and artifacts in few-step video distillation stem directly from compounding critic errors, which can be neutralized via a single-line geometric projection without discarding the true generative signal.

EgoPlay achieves a remarkable 17.7% improvement in editing quality over the previous state-of-the-art, redefining the capabilities of egocentric video editing.