提出基于MLIR的大语言模型编译新方法，有望显著提升模型推理效率与硬件适配能力。
arXiv:2607.15865v1 Announce Type: new Abstract: Large Language Models (LLMs) have become the dominant workload on modern AI accelerators, yet deployin…
开源论文提出用中间形式规范训练代码大模型，显著提升复杂推理能力。
arXiv:2607.04232v1 Announce Type: cross Abstract: Unlike natural-language specifications, executable formal specifications provide machine-checkable c…
针对深度研究代理面临的信息不确定与中间表示污染问题，提出可演化的心智模型显式调控方法。
arXiv:2605.26081v1 Announce Type: new Abstract: Deep research agents face vast, interdependent, and pervasively uncertain information. Existing system…