Search papers, labs, and topics across Lattice.
3
0
5
6
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.
LLMs trained on a synthetic corpus can outperform native data benchmarks while using significantly fewer tokens, challenging the assumption that more data always leads to better performance.
LLM-derived rankings can now achieve near-human accuracy with a fraction of the cost, thanks to a new method that quantifies and calibrates uncertainty in evaluations.
