Search papers, labs, and topics across Lattice.
2
0
4
6
Leveraging foundation models, LFM achieves superior performance in source-free universal domain adaptation, even in the presence of unknown classes.
Test-time training can finally scale for large reasoning models: TEMPO unlocks sustained performance gains by interleaving policy refinement with periodic critic recalibration, boosting accuracy by over 18% on challenging benchmarks.
