1
积累宝贵经验，神舟二十三号舷窗空间碎片防护已进行适应性改进
神舟二十三号舷窗防护已做适应性改进，20天应急发射验证滚动备份策略有效性
IT之家 5 月 23 日消息，2026 年 5 月 23 日上午 9 时，神舟二十三号载人飞行任务新闻发布会在酒泉卫星发射中心召开，中国载人航天工程新闻发言人、工程办公室综合计划局局长张静波介绍了本次任务的相关情况。 去年底，中国载人航天工程实施了首次应急发射任务，备受国内外关注。对于经历了这次实…
2
微软 35 年老将优素福 · 迈赫迪宣布离职，最后一年将协助 Windows 适应 Agent 时代
微软35年资深高管宣布离职，最后一年专注推动Windows接入Agent时代，AI战略转型信号明确。
IT之家 5 月 22 日消息，据《商业内幕》今日报道，在微软工作 35 年的资深高管优素福 · 迈赫迪将在下一财年结束后离开公司。2023 年至今，迈赫迪担任微软商业业务首席营销官。 迈赫迪在备忘录中写道：“在微软度过 35 段非凡岁月后，我认为现在是开始规划下一段人生旅程的时候了。在这 35 年…
3
Learning to Configure Agentic AI Systems
提出学习式配置方法，替代手动调优，提升LLM智能体系统的自适应能力
arXiv:2602.11574v3 Announce Type: replace Abstract: Configuring LLM-based agent systems involves choosing workflows, tools, token budgets, and prompts…
4
微软 XBOX 上线自适应摇杆帽结构，新增球门柱造型
IT之家 5 月 22 日消息，在全球无障碍宣传日（每年 5 月的第三个星期四，2026 年为 5 月 21 日），微软 XBOX 面向玩家，发布多项无障碍更新，聚焦硬件适配、信息获取与游戏体验 3 个层面。 本次更新最值得关注的项目，是自适应摇杆帽计划，微软已在 XBOX Design Lab 上…
5
STAR: Semantic-Tuned and Tail-Adaptive Retriever for Graph-Augmented Generation
图增强生成新方案：语义调优与尾部自适应检索，提升复杂查询效果。
arXiv:2605.18765v1 Announce Type: cross Abstract: To augment Large Language Models (LLMs) for multi-hop question answering, a mainstream solution with…
6
Adaptive Probe-based Steering for Robust LLM Jailbreaking
针对LLM越狱新方法，采用自适应探针引导，克服了传统对比引导的偏差和手动调参局限，提升鲁棒性与有效性。
arXiv:2605.20286v1 Announce Type: cross Abstract: Recent work has demonstrated the potential of contrastive steering for jailbreaking Large Language M…
7
From SGD to Muon: Adaptive Optimization via Schatten-p Norms
深入解读从SGD到Muon的优化器演进，以Schatten-p范数统一矩阵几何约束，为AI研究者提供理论新视角
arXiv:2605.19781v1 Announce Type: new Abstract: Modern optimizers, like Muon, impose matrix-wise geometry constraints on their updates. These matrix-w…
8
Sequential Consensus for Multi-Agent LLM Debates: A Wald-SPRT compute governor with calibration-based failure detection
用Wald的序贯概率比检验动态调控LLM辩论轮数，显著提升推理效率与资源利用率
arXiv:2605.19193v1 Announce Type: new Abstract: Multi-agent LLM debate improves factuality and reasoning, but most recipes pick a fixed round count, o…
9
Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents
LLM智能体测试时动态合成技能，无需预训练即可灵活适应新任务
arXiv:2605.16986v1 Announce Type: new Abstract: LLM agents benefit from reusable skills, yet test-time tasks often require guidance more specific than…
10
DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention
提出可微分自适应稀疏层次注意力机制，显著提升长序列建模效率与计算可扩展性
arXiv:2605.18753v1 Announce Type: cross Abstract: Current hierarchical attention methods, such as NSA and InfLLMv2, select the top-k relevant key-valu…
11
LEAP: Learnable End-to-End Adaptive Pruning of Large Language Models
提出LEAP可学习端到端自适应剪枝方法，在保持大语言模型性能的同时实现高效压缩
arXiv:2605.17289v1 Announce Type: new Abstract: Unstructured sparsity is now natively accelerated by recent GPU kernels and dataflow hardware, shiftin…
12
HPC-LLM: Practical Domain Adaptation and Retrieval-Augmented Generation for HPC Support
如何让大模型理解高性能计算？这篇论文用领域自适应和RAG打造HPC专属LLM，实用又前沿。
arXiv:2605.16347v1 Announce Type: new Abstract: Modern scientific research increasingly depends on High-Performance Computing (HPC) infrastructures, y…
13
Dual-Dimensional Consistency: Balancing Budget and Quality in Adaptive Inference-Time Scaling
LLM推理时缩放的新方法：双维度一致性，有效平衡采样预算与推理质量，提升效率。
arXiv:2605.15100v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable abilities in reasoning. However, maximizing …
14
Hybrid-LoRA: Bridging Full Fine-Tuning and Low-Rank Adaptation for Post-Training
混合全微调与低秩适应的新方法，专为后训练场景优化，效率与性能兼得
arXiv:2605.18822v1 Announce Type: new Abstract: Post-training has become essential for adapting large language models (LLMs) to complex downstream beh…
15
Stage-adaptive Token Selection for Efficient Omni-modal LLMs
阶段自适应token选择策略，显著提升全模态大语言模型推理效率，突破多任务性能瓶颈。
arXiv:2605.20035v1 Announce Type: new Abstract: Omni-modal large language models (om-LLMs) achieve unified audio-visual understanding by encoding vide…
16
Aperion Shield: local guardrail that blocks destructive AI coding agent ops
开源本地安全护栏，阻挡AI编码代理的破坏性操作，v0.7新增45+自适应规则与更多测试用例。
Article URL: https://github.com/AperionAI/shield Comments URL: https://news.ycombinator.com/item?id=48207471 Points: 2 # Comments: 0
17
CoLLM: Continuous Adaptation for SLO-Aware LLM Serving on Shared GPU Clusters
面向共享GPU集群，提出连续自适应方法优化大模型服务SLO，降低延迟与成本
arXiv:2604.16400v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) are increasingly adopted in edge intelligence to power domai…
18
RAP: Runtime Adaptive Pruning for LLM Inference
提出运行时自适应剪枝方法，让LLM推理内存动态调整，效率大增
arXiv:2505.17138v5 Announce Type: replace Abstract: Large language models (LLMs) excel at language understanding and generation, but their enormous co…
19
ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning
提出ANNEAL框架，用符号补丁学习让LLM智能体高效自适应新环境，无需微调大模型。
arXiv:2605.16309v1 Announce Type: cross Abstract: LLM-based agents can recover from individual execution errors, yet they repeatedly fail on the same …
20
AMO: Adaptive Muon Orthogonalization
提出自适应Muon正交化方法，有望优化深度学习训练过程。
arXiv:2605.17806v1 Announce Type: new Abstract: Muon has recently emerged as a competitive alternative to AdamW for large-scale pre-training, with ort…