Xiaopeng Hong

KBK achieves a 2.7% accuracy boost over previous methods in multi-label class-incremental learning, all without using replay buffers.

By decoupling detection from explanation, PATE-Forensics achieves unprecedented accuracy in deepfake forensics, setting a new benchmark for explainability in AI.

Decision-level fusion outperforms traditional feature-level methods in detecting audio-visual forgeries, revealing a critical flaw in existing assumptions about modality correspondence.

OKR achieves a remarkable +6.5% mAP improvement over existing methods by preventing knowledge interference in domain-incremental object detection.