Galaxea Dynamics (@galaxeadynamics) 's Twitter Profile
Galaxea Dynamics

@galaxeadynamics

Working on humanoids and mobile manipulation. In scaling law, we trust.
E-mail: [email protected]

ID: 1794943340477288448

calendar_today27-05-2024 04:07:03

39 Tweet

671 Takipçi

16 Takip Edilen

Galaxea Dynamics (@galaxeadynamics) 's Twitter Profile Photo

R1 Pro at #IROS—a fully intelligent demo in action. With precise recognition, autonomous reasoning, and smooth gesture following, it completes closed-loop tasks seamlessly in one continuous take—achieving nearly 100% success rate!

Chengshu Li (@chengshuericli) 's Twitter Profile Photo

We are excited to release MoMaGen, a data generation method for multi-step bimanual mobile manipulation. MoMaGen turns 1 human-teleoped robot trajectory into 1000s of generated trajectories automatically.🚀 Website: momagen.github.io arXiv: arxiv.org/abs/2510.18316

PINE-Lab-NTU (@ntulab38456) 's Twitter Profile Photo

🤖 Join the RoCo Challenge @ AAAI 2026! 🏁 The RoCo Challenge 2026 invites researchers and innovators worldwide to explore the future of Human-Robot Collaboration (HRC). Hosted during AAAI 2026, this competition—jointly organized by Nanyang Technological University (NTU),

🤖 Join the RoCo Challenge @ AAAI 2026!

🏁 The RoCo Challenge 2026 invites researchers and innovators worldwide to explore the future of Human-Robot Collaboration (HRC). Hosted during AAAI 2026, this competition—jointly organized by Nanyang Technological University (NTU),
Galaxea Dynamics (@galaxeadynamics) 's Twitter Profile Photo

🤖 NTU PINE-Lab-NTU launches RoCo Challenge 2026 @ AAAI! Defining the benchmark for embodied AI in industrial collaboration.RoCo invites global teams to explore the frontier of Human–Robot Collaboration (HRC). 🔗 rocochallenge.github.io/RoCo2026/ #AAAI2026 #RoCo2026 #EmbodiedAI #Robotics

a16z (@a16z) 's Twitter Profile Photo

Fei-Fei Li: “There’s nothing artificial about AI. It’s inspired by people. It’s created by people. And most importantly, it impacts people.” Watch the full interview with World Labs CEO Fei-Fei Li on Lenny's Podcast (Lenny Rachitsky): youtube.com/watch?v=Ctjiat…

Michael Chen (@chenouttaten) 's Twitter Profile Photo

When training RFMs, in the wild data has shown to be the most effective. But, collecting data for real world applications like our mobile bin-picking is still labor intensive. At Yondu AI, we answered a key question, how can robot operators do the least amount of work? How can we

RoboChallenge (@robochallengeai) 's Twitter Profile Photo

📢 RoboChallenge Committee Established! To bridge the gap to Action Intelligence, we need real benchmark. 🦾 Partners: Dexmal , Hugging Face, BAAI, AgiBot,Galaxea Dynamics,X Square Robot,Qwen,GOSIM Foundation & others. Define the standard for real-world robot eval.🌐

📢 RoboChallenge Committee Established!

To bridge the gap to Action Intelligence, we need real benchmark. 🦾
Partners: <a href="/Dexmal_AI/">Dexmal</a> , <a href="/huggingface/">Hugging Face</a>, BAAI, <a href="/AgiBot_zhiyuan/">AgiBot</a>,<a href="/GalaxeaDynamics/">Galaxea Dynamics</a>,<a href="/XSquareRobot/">X Square Robot</a>,Qwen,<a href="/gosimfoundation/">GOSIM Foundation</a> &amp; others.
Define the standard for real-world robot eval.🌐
Ilir Aliu - eu/acc (@iliraliu_) 's Twitter Profile Photo

Robotics keeps getting better at seeing the world, but very few models can explain... HOW actions change it. [ 📍 Everything is open-sourced] Most benchmarks test passive perception. Almost none test interaction. That is why ENACT stands out. It asks a simple question with big