Sung-eui Yoon

Generative MARL teachers fail by interpolating coordination modes; a novel optimal transport approach forces them to commit to distinct strategies, boosting student performance.

APT achieves a remarkable 0.92 IoU in tamper localization, outperforming existing methods that collapse to random performance in real-world scenarios.

RoME achieves superior robustness against multiple adversarial threats by intelligently routing them through specialized expert pathways, outperforming existing methods in both accuracy and resilience.

Implicit coordination in decentralized multi-agent systems can be achieved without direct communication, leading to a 38% success rate in complex manipulation tasks.

Quadruped robots can now nimbly navigate complex 3D terrain using only onboard depth images, thanks to a hierarchical policy that learns strategic navigation and posture adaptation.