Search papers, labs, and topics across Lattice.
3
0
4
5
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.
Achieving state-of-the-art TSC performance without real data, TimEE redefines the potential of synthetic pre-training in classification tasks.
Existing tabular foundation models excel only on small IID datasets, leaving a significant gap in performance on more complex, real-world data challenges.
