RynnBrain: Open Embodied Foundation Models

• URL: http://arxiv.org/abs/2602.14979v1
• Date: Fri, 13 Feb 2026 18:59:56 GMT
• Title: RynnBrain: Open Embodied Foundation Models
• Abstract summary: We introduce RynnBrain, an open-source foundation model for embodied intelligence.<n>RynnBrain strengthens four core capabilities in a unified framework.<n>The RynnBrain family comprises three foundation model scales and four post-trained variants.
• Score: 91.13999239177097
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite rapid progress in multimodal foundation models, embodied intelligence community still lacks a unified, physically grounded foundation model that integrates perception, reasoning, and planning within real-world spatial-temporal dynamics. We introduce RynnBrain, an open-source spatiotemporal foundation model for embodied intelligence. RynnBrain strengthens four core capabilities in a unified framework: comprehensive egocentric understanding, diverse spatiotemporal localization, physically grounded reasoning, and physics-aware planning. The RynnBrain family comprises three foundation model scales (2B, 8B, and 30B-A3B MoE) and four post-trained variants tailored for downstream embodied tasks (i.e., RynnBrain-Nav, RynnBrain-Plan, and RynnBrain-VLA) or complex spatial reasoning tasks (i.e., RynnBrain-CoP). In terms of extensive evaluations on 20 embodied benchmarks and 8 general vision understanding benchmarks, our RynnBrain foundation models largely outperform existing embodied foundation models by a significant margin. The post-trained model suite further substantiates two key potentials of the RynnBrain foundation model: (i) enabling physically grounded reasoning and planning, and (ii) serving as a strong pretrained backbone that can be efficiently adapted to diverse embodied tasks.

Related papers

• RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model [96.30193688355489]
  We present RynnBrain 1.1, a family of embodied foundation models spanning 2B, 9B, and 122B-A10B scales.<n>RynnBrain 1.1 supports embodied perception, spatial reasoning localization, and planning.<n>We also develop RynnBrain-VLA with a unified cross-embodiment action space and embodiment-specific masking, and deploy it on Unitree G1, Astribot-S1, and Tianji-Wuji.
  arXiv  Detail & Related papers  (2026-07-20T14:13:27Z)
• BrainNext: A General-Purpose Self-Supervised Foundation Model for Brain MRI Analysis [5.596045804901233]
  We present BrainNext, a general-purpose self-supervised foundation model for brain MRI analysis.<n>BrainNext learns rich anatomical representations from 60,551 unlabeled brain MRI examinations spanning multiple MRI modalities.<n>We evaluate BrainNext on the Foundation Models for Medical Imaging (FOMO) 2025 Method Track, encompassing classification, segmentation, and brain-age estimation.
  arXiv  Detail & Related papers  (2026-07-20T10:15:02Z)
• Toward a Multi-View Brain Network Foundation Model: Cross-View Consistency Learning Across Arbitrary Atlases [62.33465338932216]
  MV-BrainFM is a multi-view brain network foundation model designed to learn generalizable and scalable representations from brain networks constructed with arbitrary atlases.<n>Experiments on more than 20K subjects from 17 fMRI datasets show that MV-BrainFM consistently outperforms 14 existing brain network foundation models.
  arXiv  Detail & Related papers  (2026-03-20T11:55:00Z)
• World2Mind: Cognition Toolkit for Allocentric Spatial Reasoning in Foundation Models [25.135316296678187]
  Existing methods either overfit statistical shortcuts via 3D grounding data or remain confined to 2D visual perception.<n>We propose World2Mind, a training-free spatial intelligence toolkit.<n>We show that World2Mind boosts the performance of frontier models, such as GPT-5.2, by 5%18%.
  arXiv  Detail & Related papers  (2026-03-10T15:12:14Z)
• Brain-OF: An Omnifunctional Foundation Model for fMRI, EEG and MEG [2.783700146328046]
  We propose Brain-OF, the first brain foundation model jointly pretrained on fMRI, MEG and EEG inputs within a unified framework.<n>Brain-OF is pretrained on a large-scale corpus comprising around 40 datasets and demonstrates superior performance across diverse downstream tasks.
  arXiv  Detail & Related papers  (2026-02-26T15:47:13Z)
• Guiding the Inner Eye: A Framework for Hierarchical and Flexible Visual Grounded Reasoning [6.800544911407401]
  GRiP (Guided Reasoning and Perception) is a novel training framework for visual grounded reasoning.<n> GRiP cultivates robust and flexible visual grounded reasoning by explicitly guiding the model's perceptual focus and logical pathways.<n> GRiP achieves state-of-the-art results among open-source models on the highly challenging TreeBench and V* Bench.
  arXiv  Detail & Related papers  (2025-11-27T07:18:25Z)
• SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models [73.19077622773075]
  We present a comprehensive methodology for building spatial intelligence progressively.<n>We introduce SpatialLadder-26k, a multimodal dataset containing 26,610 samples spanning object localization, single image, multi-view, and video spatial reasoning tasks.<n>We design a three-stage progressive training framework that establishes spatial perception through object localization, develops spatial understanding through multi-dimensional spatial tasks, and strengthens complex reasoning via reinforcement learning with verifiable rewards.
  arXiv  Detail & Related papers  (2025-10-09T17:50:54Z)
• How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspective [103.44502230776352]
  We present a systematic investigation of Visual Spatial Reasoning (VSR) in Vision-Language Models (VLMs)<n>We categorize spatial intelligence into three levels of capability, ie, basic perception, spatial understanding, spatial planning, and curate SIBench, a spatial intelligence benchmark encompassing nearly 20 open-source datasets across 23 task settings.
  arXiv  Detail & Related papers  (2025-09-23T12:00:14Z)
• CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG Decoding [57.90382885533593]
  We propose a Cross-scale Spatiotemporal Brain foundation model for generalized decoding EEG signals.<n>We show that CSBrain consistently outperforms task-specific and foundation model baselines.<n>These results establish cross-scale modeling as a key inductive bias and position CSBrain as a robust backbone for future brain-AI research.
  arXiv  Detail & Related papers  (2025-06-29T03:29:34Z)
• CodeBrain: Towards Decoupled Interpretability and Multi-Scale Architecture for EEG Foundation Model [52.466542039411515]
  EEG foundation models (EFMs) have emerged to address the scalability issues of task-specific models.<n>We present CodeBrain, a two-stage EFM designed to fill this gap.<n>In the first stage, we introduce the TFDual-Tokenizer, which decouples heterogeneous temporal and frequency EEG signals into discrete tokens.<n>In the second stage, we propose the multi-scale EEGSSM architecture, which combines structured global convolution with sliding window attention.
  arXiv  Detail & Related papers  (2025-06-10T17:20:39Z)
• Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning [58.86928947970342]
  Embodied-R is a framework combining large-scale Vision-Language Models for perception and small-scale Language Models for reasoning.<n>After training on only 5k embodied video samples, Embodied-R with a 3B LM matches state-of-the-art multimodal reasoning models.<n>Embodied-R also exhibits emergent thinking patterns such as systematic analysis and contextual integration.
  arXiv  Detail & Related papers  (2025-04-17T06:16:11Z)
• MM-IQ: Benchmarking Human-Like Abstraction and Reasoning in Multimodal Models [5.02953506943752]
  MM-IQ is a comprehensive evaluation framework that comprises a large-scale training set with 4,776 visual reasoning problems and 2,710 meticulously curated test items spanning 8 distinct reasoning paradigms.<n>Our benchmark reveals striking limitations: even state-of-the-art architectures achieve only marginally superior performance to random chance.<n>Inspired by the recent surge of large reasoning models, we also release a multimodal reasoning model as the baseline that is trained via reinforcement learning with verifiable reward functions.
  arXiv  Detail & Related papers  (2025-02-02T07:12:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.