Search papers, labs, and topics across Lattice.
Cold Spring Harbor Laboratory
3
0
6
Sparse autoencoders' failure to generalize compositionally isn't due to amortized inference, but because they learn lousy dictionaries in the first place.
Forget relying on pretrained models or complex aggregation schemes: FederatedFactory achieves near-centralized performance in federated learning with extreme data heterogeneity by simply swapping generative priors.
Interpretability studies on LLMs often overreach, but causal inference offers a framework to ensure claims about model behavior are actually valid and generalizable.
