2 papers
cs.LG2026
Decouple before Integration: Test-time Synthesis of SFT and RLVR Task Vectors
Chaohao Yuan, Chenghao Xiao, Yu Rong +2
SFT and RLVR represent two fundamental yet distinct paradigms for LLM post-training, each excelling in distinct dimensions. SFT expands knowledge breadth while RLVR enhances reason…
cs.CR2026
XekRung Technical Report
Jiutian Zeng, Junjie Li, Chengwei Dai +13
We present XekRung, a frontier large language model for cybersecurity, designed to provide comprehensive security capabilities. To achieve this, we develop diverse data synthesis p…