The Chinese Communist Party (CCP) views artificial intelligence (AI) as central to strategic competition with the United States and is pursuing every means to strengthen its AI ecosystem. China’s base ...
SDPG is the main contribution. It extends GRPO with an exact per-token forward KL between the actor (without privileged context) and itself conditioned on privileged context c: ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results