BeingBeyond

Introducing BeingBeyond U1, the world’s first Real DexUMI. U1 brings embodiment-agnostic dexterous hand data collection to real-world manipulation, taking a major step toward general-purpose dexterous manipulation models. From data collection to transfer, deployment, and execution, U1 pushes UMI beyond the gripper era and into the age of dexterous hands.

Big month at BeingBeyond 🎉 We’re excited to share that in the past month we’ve had 8 papers accepted across top conferences and journals: CVPR’26 ×5, ICLR’26 ×1, ICRA’26 ×1, RAL ×1. Check our papers below👇 [CVPR'26] DemoFunGrasp: Universal Dexterous Functional Grasping via Demonstration-Editing Reinforcement Learning research.beingbeyond.com/demofungrasp arxiv.org/pdf/2512.13380 [CVPR'26] End-to-End Language-Action Model for Humanoid Whole Body Control arxiv.org/pdf/2511.19236 [CVPR'26] Joint-Aligned Latent Action: Towards Scalable VLA Pretraining in the Wild (To appear) [CVPR'26] OpenT2M: No-frill Motion Generation with Open-source, Large-scale, High-quality Data (To appear) [CVPR'26] Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos research.beingbeyond.com/vipa-vla arxiv.org/pdf/2512.13080 [ICLR'26] DemoGrasp: Universal Dexterous Grasping from a Single Demonstration research.beingbeyond.com/demograsp arxiv.org/pdf/2509.22149 [ICRA'26] Towards Proprioception-Aware Embodied Planning for Dual-Arm Humanoid Robots arxiv.org/pdf/2510.07882 [RAL] DemoHLM: From One Demonstration to Generalizable Humanoid Loco-Manipulation research.beingbeyond.com/demohlm arxiv.org/pdf/2510.11258 We’ll keep focusing on VLA models, Dexterous Manipulation, and Whole-Body Control. BeingBeyond looks forward to seeing everyone at the venues!🥳

@eddybuild Thx Eddy! Egocentric-10k is really a great help to the robotics community!🔥

built with build ai data! very cool

@_akhaliq Check more details about our work👇 Blog: research.beingbeyond.com/being-h05 Paper: arxiv.org/pdf/2601.12993 Github: github.com/BeingBeyond/Be… Hugging Face: huggingface.co/collections/Be…

Thx @_akhaliq for sharing our work!🚀🚀We’re actively continuing to open-source the Being-H series. Weights and training scripts are already out, and we’ll be gradually releasing the training data soon. Hope this brings more value to the VLA community!

@_akhaliq Thx @_akhaliq for sharing our work!🚀📷We’re actively continuing to open-source the Being-H series. Weights and training scripts are already out, and we’ll be gradually releasing the training data soon. Hope this brings more value to the VLA community!

Being-H0.5 Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization

8/8 For more details, please check out our blog and paper. We've also open-sourced the training code and model weights, and we’ll continue releasing the training data over time, stay tuned. 👇 Blog🏠: research.beingbeyond.com/being-h05 Paper📑: research.beingbeyond.com/projects/being… Github💻: github.com/BeingBeyond/Be… Hugging Face🤗: huggingface.co/collections/Be…

7/8 We deploy and evaluate across five very different real robots (upper-body humanoid, dexterous arm/hand, legged humanoid + hand, etc.). Across task suites (spatial / long-horizon / bimanual / generalization), Being-H0.5 performs strongly, with both specialist and single-checkpoint generalist variants. And we saw a surprising behavior we didn't want to oversell but couldn't ignore: embodiment-level zero-shot — the generalist checkpoint sometimes initiates qualitatively correct multi-step structure on previously unseen task–embodiment pairs in resembling environments.

(thread 1/8) We're releasing Being-H0.5🔥🔥🔥: a foundation VLA model aimed at one big goal — cross-embodiment generalization. Instead of training a new brain for every robot, we want a single model to carry skills across bodies (arms, humanoids, dexterous hands). Here's an overview of Being-H0.5 👇