{"slug":"sota-f4dd7961","url":"https://silinex.xyz/wire/sota-f4dd7961","json_url":"https://silinex.xyz/wire/sota-f4dd7961.json","md_url":"https://silinex.xyz/wire/sota-f4dd7961.md","headline":"Ascend computing power has trained an embodied world model that achieves SOTA on two leaderboards, and Huawei Cloud now wants to open up the entire foundation stack.","headline_zh":"昇腾算力训出了双榜SOTA的具身世界模型，华为云这次想把整套底座开放出来","title":"Ascend computing power has trained an embodied world model that achieves SOTA on two leaderboards, and Huawei Cloud now wants to open up the entire foundation stack.","summary":"Compiled from public reports including Quantum位: Huawei Cloud is about to open-source its embodied world model—and it's launching straight to first place on two leaderboards!","summary_zh":"综合 量子位 等公开报道整理：华为云要开源具身世界模型了，一开就是双榜第一！","date_published":"2026-11-20T08:04:58.000+00:00","date_modified":"2026-11-20T10:20:29.436+00:00","author":{"type":"Organization","name":"量子位","url":"https://www.qbitai.com/2026/11/511610.html"},"publisher":{"name":"Silicon Nexus","url":"https://silinex.xyz/"},"category":"robotics","language":"zh","source_url":"https://www.qbitai.com/2026/11/511610.html","source_name":"量子位","source_tier":"L3","corroborating_sources":[],"key_facts":["Compiled from public reports including QuantumBit: Huawei Cloud is open-sourcing its embodied world model—and it debuts at the top of two leaderboards at once!","On the timeline: on November 16, Huawei Cloud released the Ascend-native embodied world model CloudRobo-WM1.2.","In two embodied intelligence benchmarks, RoboTwin 2.0 and LIBERO-Pro 2.0, it ranks first in average success rate on both."],"key_facts_zh":["综合 量子位 等公开报道整理：华为云要开源具身世界模型了，一开就是双榜第一！","事件脉络方面，11月16日，华为云发布了 昇腾原生具身世界模型CloudRobo-WM1.2 。","在RoboTwin 2.0和LIBERO-Pro 2.0两项具身智能评测中，它的平均成功率都排第一。"],"tldr":["Compiled from public reports including QuantumBit: Huawei Cloud is open-sourcing its embodied world model—and it debuts at the top of two leaderboards at once!","On the timeline: on November 16, Huawei Cloud released the Ascend-native embodied world model CloudRobo-WM1.2.","In two embodied intelligence benchmarks, RoboTwin 2.0 and LIBERO-Pro 2.0, it ranks first in average success rate on both."],"tldr_zh":["综合 量子位 等公开报道整理：华为云要开源具身世界模型了，一开就是双榜第一！","事件脉络方面，11月16日，华为云发布了 昇腾原生具身世界模型CloudRobo-WM1.2 。","在RoboTwin 2.0和LIBERO-Pro 2.0两项具身智能评测中，它的平均成功率都排第一。"],"brief_body":"Compiled from public reports including Quantum位: Huawei Cloud is about to open-source its embodied world model—and it's launching straight to first place on two leaderboards!\n\nTimeline: On November 16, Huawei Cloud released the Ascend-native embodied world model CloudRobo-WM1.2. It ranked first in average success rate on two embodied intelligence benchmarks, RoboTwin 2.0 and LIBERO-Pro 2.0. Huawei Cloud plans to open the model weights, inference code, and post-training code on the same day.\n\nPublic information also notes: Well, open-sourcing even the post-training code outright—Huawei's move is indeed aggressive. Other robotics teams that want to teach this model a new task no longer need to build a training pipeline from scratch; with the ready-made code, they can plug in their own data and start debugging and validating right away! And this time, Huawei Cloud did not stop at \"getting the model to run on Ascend chips.\" Instead, from model architecture and training framework to core operators and inference deployment, it optimized software-hardware co-design around the characteristics of embodied models. From world model pre-training and reinforcement learning to robots getting hands-on with tasks, Huawei Cloud has connected the entire pipeline.","brief_body_zh":"综合 量子位 等公开报道整理：华为云要开源具身世界模型了，一开就是双榜第一！\n\n事件脉络方面，11月16日，华为云发布了 昇腾原生具身世界模型CloudRobo-WM1.2 。在RoboTwin 2.0和LIBERO-Pro 2.0两项具身智能评测中，它的平均成功率都排第一。华为云计划在同日，开放该模型权重、推理代码和后训练代码。\n\n公开信息还提到：好么，连后训练代码都直接开源放出，华为这一步确实够猛。别家机器人团队想教这个模型干个新活儿，不用从零搭训练链路，拿到现成代码，接上自家数据就能直接上手调试验证！而且这次，华为云没有停留在「把模型迁移到昇腾芯片上跑通」这一步，而是 从模型架构、训练框架到核心算子、推理部署，围绕具身模型的特点做软硬件协同优化。从世界模型预训练、强化学习，到机器人上手干活，华为云把这整条链路接了起来。","entities":[],"signal_type":"research","impact_score":5,"key_metrics":[],"body_md":"## Wire brief\n\nCompiled from public reports including Quantum位: Huawei Cloud is about to open-source its embodied world model—and it's launching straight to first place on two leaderboards!\n\nTimeline: On November 16, Huawei Cloud released the Ascend-native embodied world model CloudRobo-WM1.2. It ranked first in average success rate on two embodied intelligence benchmarks, RoboTwin 2.0 and LIBERO-Pro 2.0. Huawei Cloud plans to open the model weights, inference code, and post-training code on the same day.\n\nPublic information also notes: Well, open-sourcing even the post-training code outright—Huawei's move is indeed aggressive. Other robotics teams that want to teach this model a new task no longer need to build a training pipeline from scratch; with the ready-made code, they can plug in their own data and start debugging and validating right away! And this time, Huawei Cloud did not stop at \"getting the model to run on Ascend chips.\" Instead, from model architecture and training framework to core operators and inference deployment, it optimized software-hardware co-design around the characteristics of embodied models. From world model pre-training and reinforcement learning to robots getting hands-on with tasks, Huawei Cloud has connected the entire pipeline.\n\n---\n\nSource desk: **量子位** · [origin link](https://www.qbitai.com/2026/11/511610.html)\n","body_md_zh":"## 电讯正文\n\n综合 量子位 等公开报道整理：华为云要开源具身世界模型了，一开就是双榜第一！\n\n事件脉络方面，11月16日，华为云发布了 昇腾原生具身世界模型CloudRobo-WM1.2 。在RoboTwin 2.0和LIBERO-Pro 2.0两项具身智能评测中，它的平均成功率都排第一。华为云计划在同日，开放该模型权重、推理代码和后训练代码。\n\n公开信息还提到：好么，连后训练代码都直接开源放出，华为这一步确实够猛。别家机器人团队想教这个模型干个新活儿，不用从零搭训练链路，拿到现成代码，接上自家数据就能直接上手调试验证！而且这次，华为云没有停留在「把模型迁移到昇腾芯片上跑通」这一步，而是 从模型架构、训练框架到核心算子、推理部署，围绕具身模型的特点做软硬件协同优化。从世界模型预训练、强化学习，到机器人上手干活，华为云把这整条链路接了起来。\n\n---\n\n来源台：**量子位** · [原文链接](https://www.qbitai.com/2026/11/511610.html)\n","observations":{"human":1,"bot":2,"crawlers":[{"crawlerId":"ClaudeBot","hits":2,"lastSeenAt":"2026-11-20T10:57:38.796Z"}],"last_seen_at":"2026-11-20T10:57:38.796Z","note":"Counts are request logs classified by User-Agent. User-Agents can be spoofed. This is not proof of search-engine or LLM inclusion."}}