Cross-model KV cache sharing reduces prefill computation by allowing a receiver model to reuse prefix KV states generated by a related sender model. Existing methods optimize such reuse for latency and generation quality, but its safety implications remain unclear. In this work, we systematically evaluate this issue ac...
Zhi-Wei Lin, Jia-Hao Liu, Yan Liu et al.· 1 citation
DatalogBench is presented, a benchmark of 136 text-to-Datalog synthesis tasks curated from existing Datalog-based artifacts that identifies recursive reasoning and decomposition as open challenges for current LLMs and agents, and offers a reliable, execution-grounded measure of both.
RepoFuse, a dual-context framework deployed at Ant Group serving 10,000+ developers across 50+ million lines of code, is presented, demonstrating that principled context categorization enables practical repository-level completion at industrial scale.
Ming Liang, Xiaoheng Xie, Gehao Zhang et al.· SIGSOFT FSE Companion· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.