Follow
SinkRouter: Sink-Aware Routing for Efficient Long-Context Decoding in Large Language and Multimodal Models https://arxiv.org/abs/2604.16883 #cs.LG #cs.AI
SinkRouter: Sink-Aware Routing for Efficient Long-Context Decoding in Large Language and Multimodal Models https://arxiv.org/abs/2604.16883 #cs.LG #cs.AI