Search papers, labs, and topics across Lattice.
AI Innovation Institute, Stony Brook University
3
0
5
A unified P膩ninian framework could revolutionize NLP for over a billion speakers by merging disparate language resources into a single, high-performance system.
You can now audit R茅nyi differential privacy with near-optimal sample complexity, thanks to a new framework that directly estimates R茅nyi divergence using Donsker-Varadhan estimators.
LLM hallucinations aren't random errors, but predictable consequences of overlapping "hallucination basins" in the model's latent space, offering a new path to control them.