Search papers, labs, and topics across Lattice.
Xiamen University
2
0
4
8
PAMT reveals that aligning translation processes with rewards can significantly enhance multi-domain machine translation performance, especially in complex scenarios.
Ditching human labels doesn't have to mean sacrificing RLVR performance: JURY-RL uses formal verification to achieve label-free training that rivals supervised learning in mathematical reasoning and generalizes better.
