Yi-Xuan Jia

This work investigates an alternative representation in which each joint trajectory is expressed as a command-conditioned Fourier series and modified online using feedback from the robot state, showing periodic structure without an explicit Fourier generator.

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.