Long-Context Attention Benchmark: From Kernel Efficiency to Distributed Context ParallelismApr 24, 2026·Tao Bu,Qiangang Wang,Bowen Zeng,Hanwen Sun,Yunpeng Huang,Chun CaoJingwei Xu· 0 min read Cite URLTypeConference paperPublicationThe Fourteenth International Conference on Learning RepresentationsLast updated on Apr 24, 2026AuthorsJingwei XuNanjing University School of Computer Science← DuPO: Enabling Reliable Self-Verification via Dual Preference Optimization Apr 24, 2026PixNerd: Pixel Neural Field Diffusion Apr 24, 2026 →
·
0 min read