Peng Lu

Achieve state-of-the-art arbitrary-scale super-resolution with a single model by reframing extreme upscaling as a series of distribution-aligned, self-similarity-aware transitions.

Achieve state-of-the-art surgical attention tracking with a new method that leverages temporal coherence and a large-scale benchmark dataset, enabling more robust and interpretable FoV guidance.

A new unified LVLM, OmniCT, bridges the gap between slice-level detail and volumetric understanding in CT scans, outperforming existing methods by a significant margin.