RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model

Alibaba DAMO Academy

Research official 1 src. ~1 min

DAMO Academy's RynnBrain 1.1 is a family of embodied foundation models (2B, 9B, 122B-A10B parameters) unifying spatio-temporal and physics-grounded reasoning for perception, spatial reasoning, localization, and planning, adding contact-point prediction and native 3D grounding for smaller variants. The companion RynnBrain-VLA introduces a cross-embodiment action space deployed across three distinct robot platforms, with the 122B model outperforming existing proprietary and open-source baselines.

Why it matters

This paper has 171 upvotes on HuggingFace Daily Papers, signaling significant community attention to a major embodied-AI foundation model release from a large industrial lab.

Importance: 3/5

HF Daily Papers top-voted (171 upvotes, >=100 threshold) -> +1 bump from base 2.

Sources