DuPO: Enabling Reliable Self-Verification via Dual Preference OptimizationApr 24, 2026·Shuaijie She,Yu Bao,Yu Lu,Lu Xu,Tao Li,Wenhao Zhu,Jianbing ZhangShujian Huang,Shanbo Cheng,Lu Lu,Yuxuan Wang· 0 min read Cite URLTypeConference paperPublicationThe Fourteenth International Conference on Learning RepresentationsLast updated on Apr 24, 2026← CaReBench: A Fine-grained Benchmark for Video Captioning and Retrieval Apr 24, 2026Long-Context Attention Benchmark: From Kernel Efficiency to Distributed Context Parallelism Apr 24, 2026 →