1
Orchestrating AI Code Review at scale
Cloudflare分享大规模部署AI代码审查的实践经验，从瓶颈到解决方案，技术细节与工程思考兼具。
Learn about how we built a CI-native AI code reviewer using OpenCode that helps our engineers ship better, safer code.
2
Notes on blogging
一篇关于写博客的深情自白，带你回到那个充满热忱和真诚的个人网络时代。
The ever-so-great-and-interesting Katherine answered some questions about blogging and tagged me to do the same. Why did you start blogging in the fir…
3
Container Queries and Typography
回顾CSS发展历程，Container Queries如何解决组件级响应式排版的痛点。
Back in 2013 when I started my career there were a few big problems with CSS: We had to rely on Sass to get variables which made everything a lot more…
4
Agile as Trauma
敏捷开发本质是抵抗糟糕管理的免疫反应？本文犀利批判盲目协作，并引用Brooks观点反思过度合作并非总是好事。
Dorian Taylor has written an outstanding piece about making software and project management . He rushes out of the gate with the following sentence: T…
5
GraphBit: A Graph-based Agentic Framework for Non-Linear Agent Orchestration
GraphBit用有向无环图取代大模型自编排，彻底根治幻觉路由与无限循环，AI工作流走向确定性执行。
arXiv:2605.13848v1 Announce Type: new Abstract: Agentic LLM frameworks that rely on prompted orchestration, where the model itself determines workflow…
6
SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration
提出Flow-Driven递归技能进化框架，解决智能体编排中策略崩溃与信用分配难题，为LLM智能体自动化复杂任务提供新思路。
arXiv:2605.14089v1 Announce Type: new Abstract: In recent years, a variety of powerful LLM-based agentic systems have been applied to automate complex…
7
Agentic AI Ecosystems in Higher Education: A Perspective on AI Agents to Emerging Inclusive, Agentic Multi-Agent AI Framework for Learning, Teaching and Institutional Intelligence
探讨AI Agent构建包容性多智能体框架，重塑高等教育学习、教学与机构智能。
arXiv:2605.14266v1 Announce Type: new Abstract: Integration of artificial intelligent (AI) agents in higher education is transforming teaching, learni…
8
TeachAnything: A Multimodal Crowdsourcing Platform for Training Embodied AI Agents in Symmetrical Reality
对称现实下众包多模态示范让普通人也能训练具身AI，革新人类-智能体协同。
arXiv:2605.14556v1 Announce Type: new Abstract: Symmetrical Reality (SR) is emerging as a future trend for human-agent coexistence, placing higher dem…
9
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 …
10
Dywave: Event-Aligned Dynamic Tokenization for Heterogeneous IoT Sensing Signal
新方法实现IoT异构传感信号的事件对齐动态分词，提升非平稳多尺度信号处理效率。
arXiv:2605.14014v1 Announce Type: cross Abstract: Internet of Things (IoT) systems continuously collect heterogeneous sensing signals from ubiquitous …
11
ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition
提出ICED方法，通过可解释概念分解实现视觉语言模型中的概念级遗忘，精准移除目标知识而不影响无关语义。
arXiv:2605.14309v1 Announce Type: cross Abstract: Machine unlearning in Vision-Language Models (VLMs) is typically performed at the image or instance …
12
NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfaces
首个系统评估基础模型在临床EEG和脑机接口任务中的泛化能力，为领域提供标准化基准
arXiv:2605.14698v1 Announce Type: cross Abstract: Foundation models (FMs) promise to extract unified representations that generalize across downstream…
13
Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining
从视频中自动合成海量GUI交互轨迹，破解GUI Agent预训练数据稀缺难题，让智能体更好理解真实应用。
arXiv:2605.14747v1 Announce Type: cross Abstract: Recent advances in multimodal large language models have driven growing interest in graphical user i…
14
ML-Embed: Inclusive and Efficient Embeddings for a Multilingual World
多语言文本嵌入新方案ML-Embed，突破成本、语种和透明壁垒，迈向包容高效未来。
arXiv:2605.15081v1 Announce Type: cross Abstract: The development of high-quality text embeddings is increasingly drifting toward an exclusionary futu…
15
CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG
提出CuSearch课程采样法，通过搜索深度优化Agentic RAG的强化学习训练，提升效率
arXiv:2605.11611v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for trai…
16
LangPrecip: Language-Aware Multimodal Precipitation Nowcasting
用语言感知提升降水短临预报精度，结合多模态信息解决运动不明确难题
arXiv:2512.22317v3 Announce Type: replace-cross Abstract: Short-term precipitation nowcasting is an inherently uncertain and under-constrained spatiot…
17
Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training
提出稀疏到稠密奖励原则，四阶段后训练流程更高效利用稀缺标注数据，为LLM推理优化提供新范式。
arXiv:2605.12483v2 Announce Type: replace-cross Abstract: When labeled verifiable training data is scarce, each checked example should be used where i…
18
A Woman Was in the US Legally. She Was Deported Anyway
合法DACA持有者申请绿卡反被驱逐，揭露特朗普政府移民执法的严酷现实
María de Jesús Estrada Juárez was applying for her green card and thought she was doing everything right. Instead, she was arrested and deported to Me…
19
Copy.Fail Linux Vulnerability
Linux内核惊现"copy.fail"本地提权漏洞，无需竞态条件即可跨发行版利用，严重性数年未见。
This is the worst Linux vulnerability in years. TL;DR copy.fail is a Linux kernel local privilege escalation, not a browser or clipboard attack. Discl…
20
深度分析Sorry勒索软件的加密实现与行为特征
深度解析Sorry勒索软件的RSA+RSA+AES-GCM分层加密机制与完整攻击链，安全团队防“假期攻击”必读