Reinforcement learning with verifiable rewards (RLVR) produces rich training experience, yet outcome rewards reduce each attempt to a single number and leave most of this information unused. Training-time scaffolds, such as strategies or hints added to the prompt during training, offer a natural way to turn this inform...
Zijian Zhang, Rizhen Hu, Jiangweizhi Peng et al.· 0 citations
This work implements PagePilot, a reuse-aware page offloading framework for heterogeneous swap systems that improves application throughput and reduces page-fault handling latency under memory pressure, while substantially increasing the fraction of refaults served by fast backends.
Xing-Ze Liu, Jiayan Dong, Xin-Yue Liu et al.· ACM Transactions on Architec...· 0 citations
This work presents SparseDitto, an LLM-based system that constructs a GPU kernel for each matrix, operator, and target GPU, and supports SpMV, SpMM, and SpGEMM within a unified design framework.