与「KAN」相关的搜索结果

The future of the game is shaped long before the spotlight in Kansas City. Episode 3 of Air Time: Road to Peach Jam is now live on Nike and NBA YouTube accounts. Watch Here:

Imagine driving a single route that takes you along China's entire land border and coastline. That is exactly what a massive new 27,000-kilometer loop will make possible. According to the Ministry of Transport, China plans to build this super-highway during the 15th Five-Year Plan period (2026–2030) by linking three major routes—the G219, G331, and G228—end to end. Tracing the country's borders and coastline, the journey will stretch more than half the length of the Earth's equator. Far more than a transportation corridor, the route weaves together hundreds of scenic areas and historic cities, offering a journey across some of China's most diverse landscapes. G219 runs about 10,000 km from the Kanas Scenic Area in northwest China’s Xinjiang to Dongxing in south China's Guangxi, crossing deserts, the Qinghai-Xizang Plateau, the Himalayas, and other spectacular terrain. G331 stretches about 9,200 km along China's northern border, taking travelers through the vast grasslands of Inner Mongolia, the fertile plains of northeast China, and iconic destinations including Fuyuan, Mohe, Changbai Mountain, and the Greater and Lesser Khingan Mountains. G228 extends about 7,400 km from Dongxing in Guangxi to Dandong in Liaoning Province, linking China's coastal provinces and dozens of seaside cities. Running across major rivers including the Pearl, Yangtze, Yellow, and Yalu, it offers sweeping views of the country's coastline. If you could explore one part of this epic loop, where would you start?

Andrew Kang explains why Robotics remained overlooked until now. “Even though to us, it seemed like robotics and physical AI were going to become a multi decade trillion-dollar industry, I don’t think it was obvious to most.”

开源项目 LoopX：超长程 Agent 自主运行 200+ hours，状态不漂移。 我的技术主张是：LLM 上下文有限，长程 Agent 需要外置状态，通过完备的状态管理、监督和规划，让 Agent 无人干预时跑得稳、持续有产出；有人干预时跑得更好，能吸收反馈继续演进。 两条真实 trajectory 分别跨越 220.7 / 272.9 小时，跨多轮执行、等待、人工决策、writeback 与 resume 后，整个 loop 仍能找回目标、证据和下一步。 目前 LoopX 已有 3 个 showcase：auto PR issue fix、AutoML experiment 和 auto coredump fix。 以 OpenViking 开源仓库的 PR issue fix 为例，Agent 不只是循环写代码。它需要持续理解 issue 的不同状态，判断何时开发、何时等待、何时请求 review，处理 CI、冲突和上游变化，并连续交付多个 PR。 这对应 LoopX 的 domain state 管理：领域系统决定真实状态，LoopX 负责把状态投影成下一步可执行的工作。 与此同时，Agent 还可以在干活过程中实现能力自进化。当它发现现有系统缺少某项能力时，可以提出 feature、完成开发与验证、发布新的离线或在线版本，再使用新能力继续原来的任务。 长程 Agent 天然适合自进化，“完成工作”和“升级完成工作的系统”可以在同一条长程轨迹中发生。 LoopX 把这些信息外置成结构化控制面： • Goal / Vision：目标是什么，什么不能被局部优化牺牲 • Todo / Gate：当前执行的 frontier，以及必须留给人的关键判断 • Identity / Authority：谁能 claim、writeback、approve • Evidence / Receipt：每次推进留下什么可回读证据 • Quota / Scheduler：何时继续执行，何时安静等待 • Handoff / Recovery：换模型、换会话、换 host 后如何恢复 你也可以把它理解为一块专门给 Agent 设计的可执行 Kanban。 普通看板只展示“谁在做什么”；LoopX 的状态会直接约束和驱动下一次 bounded turn，让看板本身成为执行系统的一部分。 这套系统最强的地方是通用性。它不只可以修 PR，还可以做 auto research、长期实验、自媒体运营、复杂 feature 开发和办公任务。 Agent 不再只是一次性的回答机器，而可以围绕一个人的 vision，长期工作、等待、吸收反馈、积累证据并持续演进。 LoopX 从一开始 build in public：状态协议、CLI、控制面实现和真实运行轨迹都进入了开源仓库；它也已经和 OpenViking、NoKV 等 agent infra 项目形成了开源合作伙伴关系。 我希望 LoopX 最终能放大每个人的 vision 和想象力。只要你有自己的目标、想法或技术主张，就能拥有一个全天候继续工作和探索的 Agent 系统，帮助你把愿景一点点变成现实。 欢迎试用、提 issue、贡献代码，或者用一个真实的 multi-day task 跑 LoopX。

Very excited to share that I'll be joining UIUC ECE and CS (affiliate) as an Assistant Professor @UofIllinois I'm recruiting PhD students, interns, and postdocs to build trustworthy AI agents and robots that reason, learn, and grow alongside humans. If you're interested in joining my lab at UIUC, reach out at yaqixie.ai@gmail.com Many thanks to my advisors and collaborators for all their help and support! @haroldsoh @ Katia_Sycara @RamananDeva @ Alexander_Gray @ David_Hsu @ksmeel @ Mohan_Kankanhalli @joecampb @SimonStepputtis @ Woojun_Kim @yswhynot