Jian Guan

Native computer use can be achieved at scale, enabling agents to outperform leading systems while significantly enhancing security against adversarial attacks.

CoCaRS achieves superior knowledge transfer in heterogeneous model distillation by balancing redundancy suppression with structural integrity, outperforming traditional methods.

SynCLIP resolves synonym-induced grounding inconsistencies, achieving unprecedented robustness in open-vocabulary dense perception tasks.