Search papers, labs, and topics across Lattice.
3
0
7
FedLLMs, thought to be safer due to data localization, are shockingly vulnerable: a new attack achieves near 100% membership inference accuracy, even with differential privacy.
Tabular anomaly detection gets a serious upgrade: uLEAD-TabPFN leverages frozen PFNs to model complex feature dependencies, outperforming existing methods by a significant margin, especially in high-dimensional spaces.
Latent reasoning can beat explicit Chain-of-Thought – but only if you force it to learn causal dynamics via a visual world model, not just language.
