This work proposes PRISM, a new multi-reward RL framework built upon the idea of policy-space decomposition and composition, which alleviates the potential conflict during multi-reward policy optimization, while enabling controllability during inference by flexible policy composition.
Ruiming Liang, Yinjie Zhong, Yizhen Yuan et al.· 1 citation
DASH maps the gap between each local distillation signal and the sequence-level mean to an adaptive propagation gate and then uses these gates to control backward multi-step aggregation and improves over matched vanilla OPSD reruns on every benchmark at all three model scales.
Zhi-Yan Hou, Xinyu Tang, Hongyan An et al.· 1 citation
Anchored by this tri-axial framework, representative methods are systematically surveyed, the ongoing transition of continual learning is traced, and the key challenges, broader implications, and future directions arising from this paradigm shift are discussed.
Zhi-Yan Hou, Dan Zhang, Tao Feng et al.· 0 citations