强化学习训练中混合rollout调度的新突破，跳出前缀局部性束缚，为分布式RL提速提供新思路。
arXiv:2608.11152v1 Announce Type: cross Abstract: Modern reinforcement learning (RL) post-training pipelines for large language models (LLMs) increasi…
应对突发推理负载，改进WAIT调度算法，提升LLM服务稳定性与吞吐量。
arXiv:2608.06135v1 Announce Type: new Abstract: Large Language Models (LLMs) such as ChatGPT and Claude are widely used for information retrieval and …
大模型推理的延迟"长尾"痛点有解了！本文提出GPU调度新方法UniBoost，通过感知输出长度分布，显著降低高响应百分位延迟。
Article URL: https://yl3469.github.io/uniboost-icml26/ Comments URL: https://news.ycombinator.com/item?id=48808378 Points: 2 # Comments: 0
护理出租车调度遇上整数规划与机器学习，专攻轮椅适配、时间窗等复杂约束的全局最优解
arXiv:2606.29725v1 Announce Type: new Abstract: In this paper, we formulate a new vehicle dispatch optimization problem, called Nursing Care Taxi Disp…
智能调度现场服务团队，优化路径安排，大幅减少驾驶时间，提升每日作业效率。
The hardest part of building a scheduling tool for field service teams isn't the calendar. It's the fact that the calendar is a lie. Here's what I mea…
ICML 2026 接收，提出动态滑动块调度策略，让扩散大语言模型生成效率更高。
arXiv:2602.05992v3 Announce Type: replace Abstract: Diffusion large language models (dLLMs) have emerged as a promising alternative for text generatio…
新型动态有向图约束数据调度方法，大幅提升LLM训练效率与收敛速度。
arXiv:2605.31164v1 Announce Type: cross Abstract: Training data plays a central role in large language models (LLMs) optimization, motivating extensiv…
破解飞机拆解调度难题，用运筹优化提升航空回收效率与可持续性。
arXiv:2605.23592v1 Announce Type: new Abstract: Dismantling aircrafts reaching their end of life is a complex endeavour that is necessary in terms of …
面向Superchip的LLM推理优化，提出SLO感知的旋转调度与内存管理方案，已被MLSys '26接收。
arXiv:2601.20309v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) serving faces a fundamental tension between stringent latency Ser…
面向LLM推理的SLO感知旋转调度与内存管理技术，已被MLSys 2026录用，值得关注。
Article URL: https://supercomputing-system-ai-lab.github.io/projects/superinfer/ Comments URL: https://news.ycombinator.com/item?id=48188146 Points: 3…
数据驱动方法解决化工流程需求响应调度中的终端约束难题，助力柔性操作与电网平衡。
arXiv:2605.14741v1 Announce Type: cross Abstract: Electrified chemical processes are incentivized by exposure to time-varying electricity markets to o…
提出流体引导的在线调度方法，在内存约束下优化LLM推理，显著降低延迟与运营成本
arXiv:2504.11320v3 Announce Type: replace-cross Abstract: Large language models now serve millions of users daily, with providers incurring costs exce…