Qi Zhang

A single GPU-optimized factor graph fuses LiDAR, IMU, and GNSS to achieve unprecedented real-time global localization accuracy, outperforming baselines that diverge on challenging datasets.

The Morin transition in hematite is driven by a rapid decrease in uniaxial anisotropy, not the Dzyaloshinskii-Moriya field, as revealed by precise magnon velocity measurements.

External agent scaffolding can be discarded after training by distilling evolved decision-making procedures directly into a model's native reasoning traces.

A generalized Medical Imaging Disentanglement Learning framework that outperforms state-of-the-art supervised and self-supervised classification methods in accuracy across all datasets and successfully isolates target-specific latent representations.

Beyond instance-level understanding, few methods have explored fine-grained classification for urban buildings, and thus this work puts forward a fine-grained classification model for urban buildings with a spatially-supervised contrastive loss.