Yidan Zhang

GeoSearcher transforms the challenging task of remote sensing visual grounding into a more manageable anchor-guided reasoning process, achieving superior localization accuracy.

Training generative inverse renderers on AAA game footage closes the realism gap, enabling superior generalization and controllable generation compared to models trained on existing synthetic datasets.

By decoupling patch details from semantics, Cheers achieves state-of-the-art multimodal performance at 20% of the training cost of comparable models.