Search papers, labs, and topics across Lattice.
2
0
4
3
TabPFN-Rel not only tops the leaderboard on RelArena-$\alpha$ but also challenges the notion that specialized architectures are always superior to flattened relational databases.
PFNs, despite their strong empirical performance in causal inference, can suffer from prior-induced confounding bias, but a simple one-step posterior correction can restore frequentist consistency.
