Yixuan Jia

Compromised agents can reconstruct sensitive imagery from public broadcasts, but CILC secures loop closure detection without revealing global descriptors.

A single-line code change can restore diversity and fidelity in video generation models, outperforming even the original teacher models.

Invariance in diffusion models peaks at intermediate noise levels, revealing a critical link between representation quality and classification performance.

Meridian achieves accurate global localization in unstructured environments without the need for area-specific training, outperforming traditional methods.

LiDAR-only dynamic object detection gets a major boost in cluttered environments by fusing temporal occupancy grids with a learned BEV dynamic prior, significantly reducing false negatives.