Search papers, labs, and topics across Lattice.
Affiliation:
2
0
4
Traditional causal inference requires hand-crafted pipelines and bespoke estimator training for every dataset, but causal foundation models can now infer treatment effects entirely zero-shot via in-context learning.
Brittle, hand-crafted prompts are no longer necessary for distribution-free NLP: ensembling diverse in-context demonstrations provably minimizes prediction set size while maintaining strict coverage guarantees.
