ModelsMulti-source

Reka AI 发布 19B 参数全模态模型 Rho-1,覆盖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

Why we picked it

Reka AI 用 320 块 H100 三个月训出 19B 的 Rho-1,文本图像视频加机器人控制一个模型全包,算力开销比主流大模型小得多。

Reka AI 推出 190 亿参数的全模态模型 Rho-1,可在一个神经网络内处理和生成文本、图像、视频以及机器人控制动作。

Body

该模型用 320 块 H100 GPU 训练约三个月完成,算力消耗远低于当前头部模型。Rho-1 不将任务分发给专门系统,而是把所有模态作为 token 放进同一个共享上下文窗口中运行。

Original · Decoder

Reka AI's omni-model Rho-1 handles text, images, video, and robot control in a single model

Reka AI's Rho-1 is a 19-billion-parameter omni-model that processes and generates text, images, video, and robot control actions in a single neural network. Trained on 320 H100 GPUs in about three months, it uses a fraction of the compute today's top models need. Instead of routing tasks to specialized systems, Rho-1 runs all modalities as tokens in one shared context window. The article Reka AI's omni-model Rho-1 handles text, images, video, and robot control in a single model appeared first on The Decoder .

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Reka AI, Rho-1, multimodal, open-source models.

Source attribution: curated from Decoder (@Matthias Bastian). Cross-source corroboration: 3 independent sources have covered this development (including Teortaxes, arXiv cs.LG), confirming industry-wide signal strength.