RoboScape
Search documents
锦秋被投企业Manifold AI流形空间完成超亿元天使+轮融资,国产世界模型让机器人大脑超进化|Jinqiu Spotlight
锦秋集· 2026-01-10 06:13
以下文章来源于Manifold AI流形空间 ,作者Manifold AI Manifold AI流形空间 . 基于自研的世界模型构建具有通用理解和交互能力的具身智能体。 「Jinqiu Spotlight」 追踪锦秋基金与被投企业的每一个光点与动态, 为创业者传递一线行业风向。 今天, Manifold AI(流形空间 )宣布 完成超亿元天使+轮 融资, 锦秋基金 持续加注。此前, 锦秋基金曾领投 Manifold AI 天使轮融资。 本轮投资由君联资本领投,梅花创投、华为哈勃跟投,老股东 英诺 基金 、 锦秋基金 、同创伟业 持续加注 。 Manifold AI(流形空间) 半年内累计 已获得数亿元融资 , 所募资金将用于 世界 模型 的迭代 和 具身大脑的 应用落地。 Manifold AI基于世界模型的深厚积累自研了 通用 空间 世界模型 WorldScape ,具备单图生成可交互空间的能力, 在生成质量、时空一致性、实时 性等方面全面对标国外的一线世界模型 如Google Genie3、 李飞飞 World Lab s RTFM等 。 图1:基于 WorldScape 单图生成 移动 交互 世界模型 ...
流形空间CEO武伟:当AI开始“理解世界”,世界模型崛起并重塑智能边界|「锦秋会」分享
锦秋集· 2025-11-05 14:01
Core Insights - The article discusses the evolution of AI towards "world models," which enable AI to simulate and understand the world rather than just generate content. This shift is seen as a critical leap towards "general intelligence" [4][5][9]. Group 1: Definition and Importance of World Models - World models are defined as generative models that can simulate all scenarios, allowing AI to predict and make better decisions through internal simulations rather than relying solely on experience-based learning [15][18]. - The need for world models arises from their ability to construct agent models for better decision-making and to serve as environment models for offline reinforcement learning, enhancing generalization capabilities [18][22]. Group 2: Development and Applications - The development of world models has been rapid, with significant advancements since the 2018 paper "World Models," leading to the emergence of structured models capable of video generation [24][52]. - Key applications of world models include their use in autonomous driving, robotics, and drone technology, where they provide a foundational layer for general intelligence [9][75]. Group 3: Technical Approaches - Various technical approaches to world models are discussed, including explicit physical modeling and the use of generative models that focus on creating environments for reinforcement learning [29][40]. - The article highlights the importance of data collection, representation learning, and architecture improvements to enhance the capabilities of world models [69][71]. Group 4: Future Directions - Future improvements in world models are expected to focus on richer multimodal data collection, stronger representation learning, and the ability to adapt to various tasks and environments [69][70][73]. - The company claims to be the only team globally to have developed a "universal world model" that can be applied across different domains, including ground and aerial intelligent agents [75][81].
清华最新RoboScape:基于物理信息的具身世界模型~
自动驾驶之心· 2025-07-03 06:34
编辑丨具身智能之心 本文只做学术分享,如有侵权,联系删文 >> 点击进入→ 具身智能之心 技术交流群 更多干货,欢迎加入国内首个具身智能全栈学习社区 : 具身智能之心知识星球 (戳我) , 这里包含所有你想要 的。 以下文章来源于具身智能之心 ,作者Yu Shang等 具身智能之心 . 与世界交互,更进一步 点击下方 卡片 ,关注" 具身智能 之心 "公众号 作者丨 Yu Shang等 研究背景与核心问题 在具身智能领域,世界模型作为强大的模拟器,能生成逼真的机器人视频并缓解数据稀缺问题,但现有模 型在物理感知上存在显著局限。尤其在涉及接触的机器人场景中,因缺乏对3D几何和运动动力学的建模能 力,生成的视频常出现不真实的物体变形或运动不连续等问题,这在布料等可变形物体的操作任务中尤为 突出。 根源在于现有模型过度依赖视觉令牌拟合,缺乏物理知识 awareness。此前整合物理知识的尝试分为三类: 物理先验正则化(局限于人类运动或刚体动力学等窄域)、基于物理模拟器的知识蒸馏(级联 pipeline 计 算复杂)、材料场建模(限于物体级建模,难用于场景级生成)。因此,如何在统一、高效的框架中整合 物理知识,成为亟 ...