MeshKV, a KV cache fabric that moves blocks as packetized flows over a lightweight NoC, co-designs TaKV affine striping to spread homes and cut hotspot load and co-designs Mare multicast with verified duplicate suppression, and Pad, which converts bisection back-pressure into useful KV transfer.
KVLearn, a learning-based retention framework that makes keep/evict decisions as first-class cost-optimization choices in disaggregated LLM serving is presented and evaluated on both text and multimodal workloads.
Dong Liu, Yan-Xuan Yu, E. Jiang et al.· Proceedings of the 19th ACM...· 0 citations
Topology-guided safeguards for LLM-based multi-agent systems (MAS) train a GNN over the inter-agent communication graph to localize risky agents and intervene on the topology---but they assume one operator can pool all labeled traces. Across organizations that assumption breaks: episodes contain private prompts, tool o...
Jin-Xi Yu, Eric Jiang, Levina Li et al.· 0 citations
This work introduces RUBRIC, a generator-agnostic filtering framework that formulates synthetic sample selection as a quality-over-quantity optimization problem and shows that RUBRIC improves F1-macro and recall while maintaining comparable ROC-AUC across several generators.
Yan-Xuan Yu, Dong Liu, Shu Wang et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.