2 papers
cs.CL2026
GRPO Beyond English: A Large-Scale Study of GRPO in Non-English and Multilingual Settings
Konstantin Dobler, Federico Scozzafava, Jonathan Janke +2
Reinforcement Learning with Verifiable Rewards (RLVR), often optimized with Group Relative Policy Optimization (GRPO), has become a central recipe for improving the reasoning capab…
cond-mat.other2026
Antisymmetric spontaneous resistivity anisotropy due to hard-axis collapse in polycrystalline Co thin films
Y. Fernandes, J. Geshev, A. M. H. de Andrade +1
We investigate magnetoresistance phenomena associated with the magnetization hard-axis collapse in polycrystalline Co thin films. Transport measurements reveal that, for specific o…