Search papers, labs, and topics across Lattice.
School of Artificial Intelligence, Laboratory for Novel Software Technology, Nanjing University National Key, Nanjing University
3
0
7
Later Transformer layers in tabular foundation models aren't always the smartest; revisiting earlier thoughts dramatically boosts performance.
Agents trained on static benchmarks falter dramatically in open-world settings, revealing a critical gap in their adaptability to real-world complexities.
An 8B parameter model, RideJudge, outperforms 32B baselines in ride-hailing dispute adjudication by aligning visual semantics with evidentiary protocols, achieving 88.41% accuracy.
