跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-23AI 評分43

RynnUnify:邁向統一具身大腦

RynnUnify: Towards Unified Embodied Brain

AI 導讀

RynnUnify 是一款 16B 統一具身模型,整合視覺規劃、物理推理與機械人控制,並在長時程具身任務取得最先進成果。其 Rynn-VP 整體分數較 Cosmos 3 Nano 高 9.75 分,智能體擴展版的 Rynn-GEU 平均分較直接推理高 6.0 分。世界動作擴展版在 20 項指定複合 RoboCasa365 任務的成功率為 51.5%,三項真實機械人任務的平均成功率為 46.7%。

正文

Published on Oct 23

Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

RynnUnify is a 16B unified embodied model that integrates visual planning, physical reasoning, and robot control, achieving state-of-the-art results on long-horizon embodied tasks.

We introduce RynnUnify, a 16B unified embodied model that combines strong embodied understanding with long-horizon visual planning through interleaved video--language reasoning. With capabilities spanning spatial reasoning, physical prediction, and grounding, RynnUnify connects an understanding of the physical world with visual anticipation of how it evolves across successive subtasks. Building on these capabilities, we further develop an agentic extension through reinforcement learning to selectively use video predictions for reasoning about unobserved states and interaction outcomes. We also develop a world-action extension of the full RynnUnify model, translating its understanding and prediction capabilities into robot control. To evaluate these capabilities, we introduce Rynn-VP and Rynn-GEU for long-horizon visual planning and anticipatory reasoning. Experiments show that RynnUnify achieves the highest average embodied understanding score among the evaluated unified multimodal models and improves the Rynn-VP overall score by 9.75 points over Cosmos 3 Nano. Its agentic extension improves the Rynn-GEU average by 6.0 points over direct reasoning, while the world-action extension achieves 51.5\% success on 20 selected composite RoboCasa365 tasks and 46.7\% average success across three real-robot tasks. Together, these results establish RynnUnify as a shared foundation for embodied understanding, visual planning, and robot control, taking a step toward a unified embodied brain.

View arXiv page View PDF Project page GitHub 7 Add to collection

Get this paper in your agent:

hf papers read 2610.32965

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.32965 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.32965 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.32965 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co