Search papers, labs, and topics across Lattice.
Northeastern University Shenyang
2
0
5
HarmTrace reveals that fine-grained target identification can drastically improve harmful meme detection accuracy, closing a critical gap in multimodal AI understanding.
Achieving over 20% performance improvement in data-free knowledge distillation, UniDFKD eliminates reliance on architecture-specific priors, paving the way for more robust model training across diverse architectures.
