Found 3 document(s)
Page 1 of 1
-
Reinforcement learning with verifiable rewards (RLVR) enables large language models (LLMs) to continuously self-improve their reasoning capabilities. Compared to RLVR's scalar rewards, recent self-supervised on-policy di...
-
We consider decentralized stochastic nonconvex optimization over directed networks. Push--Pull provides an efficient decentralized optimization framework for such networks, but in the stochastic setting, gradient varianc...
-
Against the background of the media commercialization reform since the 1990s in China and drawing on the case of »X-Change« (2006-2019), Wei Dong investigates the affective meaning-making mechanism in the multimodal text...