Search papers, labs, and topics across Lattice.
Affiliation:, Affiliation:
2
0
1
Pretrained scientific foundation models can overcome massive chemical and instrumentation shifts entirely at test-time by using reference-guided retrieval to recalibrate latent predictions on the fly without query supervision.
Most single-cell perturbation models only appear accurate because they memorize generic background responses—their benchmark scores remain high even when gene labels are completely shuffled.