Search papers, labs, and topics across Lattice.
2
0
4
0
Escaping the curse of noisy data in semi-supervised learning: S$^2$MAM adaptively selects features and tunes similarity metrics, leading to more robust and interpretable models.
Even with only 0.3% data poisoning, BadCLIP++ achieves near-perfect attack success rates on multimodal models and maintains effectiveness against a wide range of defenses, highlighting a significant vulnerability.
