Reka发布RIDM模型从视频提取低级动作
Reka开源了RIDM模型,能从游戏视频学习并应用到现实世界,无需复杂标注。
Reka实验室发布了逆向动力学模型RIDM,可直接从原始视频中提取低级相机/电机命令。该模型完全基于视频游戏训练,能泛化到真实世界视频。RIDM解决了传统模拟环境缺乏真实物理和噪声的问题,无需标注低级动作标签。
Standard simulated environments lack real-world physics and noise. Interactive World Models get closer, but training them needs video labelled with low-level actions, and real footage rarely has those labels.
Today, we’re releasing the Reka Inverse Dynamics Model (RIDM), a compact model that extracts low-level camera/motor commands directly from raw video. 🕹️Trained entirely on video games 🌐Generalizes to real-world footage 🔐 Weights open-sourced under Apache 2.0
Read the research note and grab the weights on 🤗Hugging Face: https://t.co/T4bvGkkoEm
#MachineLearning #Robotics #WorldModels #AIResearch #OpenSource
本条情报归属 AITOP「模型」核心栏目,重点聚焦北美前沿实验室与硅谷科技巨头。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」「中美大模型技术代差与商业化对照」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:RIDM、Reka、逆向动力学模型、视频生成,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明:本文原始线索采编自「Reka」(@RekaAILabs),经 AITOP 多维评分管线结构化提炼。