Reka AI 发布 190 亿参数全能模型 Rho-1，单模型处理文本图像视频与机器人控制
Reka AI's omni-model Rho-1 handles text, images, video, and robot control in a single model
评分 58
导读
Reka AI 的 Rho-1 是一个 190 亿参数的全能模型，可在同一个神经网络中处理和生成文本、图像、视频以及机器人控制动作，训练使用 320 块 H100 GPU、耗时约三个月，算力消耗只是当前顶尖模型的一小部分。它不把任务分发给专用系统，而是把全部模态作为 token 放进同一个共享上下文窗口。
推荐理由
190 亿参数单模型统一处理文本图像视频与机器人动作，可对照它与专用系统分路方案的路线差异。
主体与标签
Reka AI#模型发布#多模态#具身智能#端侧#部署/工程
正文
Reka AI has released a research preview of Rho-1. The 19-billion-parameter omni-model processes and generates text, images, video, and robot control actions in a single neural network. Unlike most AI systems that route tasks to specialized models, Rho-1 runs all modalities as tokens in one shared context window with no tool calls or external models. The model generates continuous video in real time and responds to new instructions on the fly without restarting.
The same weights that predict camera images also drive robot movements. To work around scarce robot training data, Reka AI built an inverse dynamics model that pulls control signals from ordinary internet videos. Rho-1 trained on 320 H100 GPUs over about three months.
Reka AI isn't new to multimodal AI. In April 2024, the company shipped Reka Core , a multimodal language model that competed with GPT-4, Claude 3, and Gemini Ultra on benchmarks. The release fits a broader push in AI research toward so-called world models .