用验证引导的稀疏注意力加速长上下文LLM推理，自推测解码摆脱KV缓存瓶颈。
arXiv:2602.07223v2 Announce Type: replace Abstract: Long-context large language model (LLM) inference has become the norm for today's AI applications.…
ICML'26 论文强调开放型 AI 部署前必须优先保障安全，为行业敲响警钟。
arXiv:2502.04512v4 Announce Type: replace Abstract: AI advancements have been significantly driven by a combination of foundation models and curiosity…
ICML'26接收，新方法通过协变量转移建模高效估计随机实验纵向治疗效果。
arXiv:2605.31443v1 Announce Type: cross Abstract: We present a regression-adjustment framework designed for the estimation of longitudinal treatment e…
ICML'26收录，首个工业级优化建模基准，为大规模整数与非线性规划研究提供标准化测试平台。
arXiv:2602.10450v2 Announce Type: replace-cross Abstract: Optimization modeling underpins decision-making in logistics, manufacturing, energy, and fin…