Register and share your invite link to earn from video plays and referrals.

WUJI
@wuji_global
To provide the physical world infrastructure that accelerates the arrival of general purpose robots. Founder & CEO: @Yunzhe_Pan Email: ceo.office@wuji.tech
95 Following    3.7K Followers
We made the hand. @amrhkzp and the team taught it to walk. Love this!
I taught a robotic hand to walk on its fingertips. Usually an arm takes the hand to the work. We wanted it to get there without one, then use the same fingers to do the job. Meet Fingers as Legs. Video: Paper:
Show more
WUJI Salon | Pittsburgh · #IROS2026# Toward an Embodied Future Bringing together robotics researchers, developers and industry partners for a CEO keynote, guest talks, dinner and networking. Sept 29 · 6:30–9:00 PM EDT Scan the QR code to register. #EmbodiedAI# #Robotics# #WUJI# #WUJIHand# #DexterousHand#
Show more
Glad to support OpenWAM with compute resources and WUJI Hand for real-world dexterous manipulation evaluation. Excited to see more open research connecting world models with real-world robot actions.🤖
Show more
🤖 World Action Models predict the future to act better. However, WAM research remains fragmented in code, ad hoc in design, and unprincipled at scale. 💡 Today, we release 𝗢𝗽𝗲𝗻𝗪𝗔𝗠: 𝗔𝗻 𝗢𝗽𝗲𝗻, 𝗠𝗼𝗱𝘂𝗹𝗮𝗿 𝗘𝘅𝗽𝗹𝗼𝗿𝗮𝘁𝗶𝗼𝗻 𝗧𝗼𝘄𝗮𝗿𝗱𝘀 𝗦𝘆𝘀𝘁𝗲𝗺𝗮𝘁𝗶𝗰 𝗪𝗼𝗿𝗹𝗱–𝗔𝗰𝘁𝗶𝗼𝗻 𝗠𝗼𝗱𝗲𝗹 𝗣𝗿𝗲𝘁𝗿𝗮𝗶𝗻𝗶𝗻𝗴 to change this. 🌐 🧵1/14
Show more
MINT is now open source. From first-person RGB video, MINT reconstructs 3D camera trajectories and bimanual hand motion in a shared world coordinate system. Reconstructed human hand motion can also be retargeted to WUJI Hand. The release includes model weights, training and inference code, visualization and evaluation tools, EgoPipeline reference code, and structured annotations for 560,649 episodes covering 1,021 hours of first-person video. Project: Code: #MINT# #EmbodiedAI# #Robotics# #WUJIHand#
Show more
Congrats to @safe_sentinel_ on the release! The latest work explores dexterous data collection, robot learning, and real-world manipulation, with Wuji Hand included in the setup. Looking forward to what comes next.
Show more
This is a new era of dexterity. 🧵
TRON 2 × Wuji Hand 2 takes on a multi-step TCM pharmacy workflow, from picking and weighing to grinding and packaging. Glad to support @LimX_Dynamics in this scenario validation and see Wuji Hand 2 integrated into a complete mobile manipulation system.
Show more
TRON 2 × Wuji Hand 2 handles TCM pharmacy work: picking, weighing, grinding and packaging. The omnidirectional base frees the hands, while precise gripping and dual-arm force control enable mid-air operations. LimX Dynamics advances embodied AI through hardware-software synergy.
Show more
Huge congrats to @DynaRobotics on Dyna-2. 1M+ hours of egocentric human video. No robot data during pre-training. Scaling still shows up on unseen robot data and real-robot evaluation. Great to see Wuji Hand used in the real-robot demos. We'll keep building dexterous robot hardware with ecosystem partners to bring general-purpose robots closer to real-world deployment. #WujiTech# #WujiHand# #Dyna2# #Robotics# #WorldModels#
Show more
Today we are introducing Dyna-2, a world-action model pre-trained on one million hours of human video. At this scale, for the first time, we discovered several new scaling laws: • world-action models exhibit scaling law on human data across four orders of magnitude, from 1000 to 1,000,000 hours, • this human data scaling law implied a scaling law on never seen robot data, • both data and objective matter; world modeling and scaling on video data are essential for cross-embodiment scaling transfer to emerge 🧵
Show more
Wuji Tech × Alibaba DAMO Academy RynnBrain 1.1 is tested with Wuji Hand on real-robot dexterous manipulation tasks. The demo spans grasping spatulas, flipping steak, plating, serving dishes, and pouring wine. A good testbed for connecting embodied perception, contact reasoning, and reliable execution in continuous manipulation. #WujiTech# #WujiHand# #RynnBrain# #EmbodiedAI# #Robotics# #DexterousManipulation#
Show more
Excited to see WUJI as part of the @NVIDIA Isaac Teleop ecosystem. Wuji Glove captures human hand motion. Wuji Hand brings it into dexterous robot execution. Looking forward to exploring what comes next with NVIDIA and the broader Physical AI ecosystem. #WujiTech# #NVIDIA# #WujiHand# #WujiHand2# #DexterousHand# #Robotics# #PhysicalAI# #DexterousManipulation#
Show more
TopoRetarget enables a dexterous manipulation RL mimic pipeline from human demonstrations to real-world robot execution. With TopoRetarget + RL tracking, we achieve zero-shot sim-to-real pen spinning on the Wuji Hand.🎉🎉🎉 We collect human hand-object motion with Wuji Glove, retarget the human demonstration to wuji hand while preserving hand-object interaction information, and train a RL policy to track the resulting hand-object reference. Paper: Project page:
Show more
Human data → robot skills. Excited to see more work built on large-scale human demonstrations to advance dexterous manipulation. Great work from the team!
Introducing Human Universal Grasping (HUG): dexterous grasping learned entirely from human hands, with zero robot data. 🌐 Website: 📄 Paper: 💻 Code:
Show more
The future of manipulation isn't hand-only. Locomotion and dexterity are deeply coupled problems. Interesting work from the Current Robotics team.
Introducing Curr-0: When Loco-Manipulation Meets Dexterity Robots have learned to walk. Robots have learned to use their hands. But in the real world, you can't do one without the other. Your stance determines your reach. Your torso determines your balance. Your whole body moves before your fingers ever act. This is what makes loco-dexterous manipulation hard — and what most robots still can't do. Curr-0 is our humanoid foundation system for loco-dexterous manipulation. Locomotion, whole-body coordination, and dexterous hand control, learned together as one coupled behavior. Trained on 21k hours of real human data — including 3k hours of whole-body demonstrations — deployed on a near 70-DoF embodiment. One model. One policy. Whole body. This is Curr-0. And this is just the beginning. Tech Report →
Show more
Wuji Hand 2 Makes Its Global Debut at ICRA 2026 Next-generation dexterous hand with 20 DOF, backdrivable actuation, and improved thermal design for sustained operation. Built for real-world dexterous manipulation. #WujiTech# #WujiHand# #ICRA2026# #DexterousHand# #Robotics# #EmbodiedAI#
Show more
During ICRA 2026, we hosted a salon bringing together researchers, founders, and industry partners. Our founder, Yunzhe Pan, shared the story behind Wuji Tech. The conversation moved beyond just our product, extending to data, training systems, Sim-to-Real, and commercialization in embodied AI. While the questions varied, they all focus on one truth: what it takes to make embodied intelligence work in the real world. Thank you to everyone who joined and shared their perspectives. #ICRA2026# #Robotics# #EmbodiedAI# #WujiTech# #WujiHand# #DexterousaHand# #DexterousManipulation#
Show more