Robotics Night is coming to Seoul 🇰🇷🤖 Presenting at #ICML2026? Deep into robotics AI? Come spend an evening with fellow researchers at RLWRLD's Seoul research lab on July 8: live RLDX-1 demos on real robot hands, drinks, and casual talk with the people building the model. 👇🏻 🤝 Who you'll meet: ICML authors and presenters across VLA, world models, manipulation, and dexterity, mingling with the RLWRLD researchers who built RLDX-1 🤖 Live RLDX-1 demos on real robot hands, our dexterity-first foundation model for true five-finger dexterity 📍 July 8 (Wed), 7:30 PM · RLWRLD Lab, Gangnam, Seoul (2 blocks from COEX where ICML2026 is) 🎟️ Invite-only, seats are limited Want in? Find someone from RLWRLD at ICML, or DM @junh0ch0 (Jacey) and we'll get you on the list. 👀 Preview of what runs live that night 👉 youtube.com/watch?v=H90bt8S8… Here's our story 👉 youtube.com/watch?v=KRD9yMqP… Check out the RLDX-1 tech blog 👉 rlwrld.ai/rldx-1 #RLDX #RLWRLD #ICML2026 #PhysicalAI #Robotics #DexterousManipulation #RoboticsFoundationModel #VLA #WorldModel

We're thrilled to share that Robotics & Automation News has covered our collaboration with @nvidia , @NVIDIARobotics to co-develop next-generation industry standards for humanoid robot dexterity. What we're building together 1) DexBench: an open benchmark built from real industrial environments, defining 5 dexterity domains and 18 Key Atomic Tasks, integrated with NVIDIA Isaac Lab-Arena for dual simulation and real-world validation 2) 5-Finger Dexterity Data Standard: a shared data format for dexterous manipulation training, designed to be compatible with NVIDIA Isaac Lab pipelines and openly accessible to robot manufacturers and research institutions worldwide 3) Isaac Platform Integration: end-to-end pipeline from data collection through model training to deployment The Physical AI space is moving fast. But without a common language for measuring and reproducing dexterous manipulation, progress stays fragmented. That's exactly what #DexBench is designed to solve. RLDX-1 has already achieved state-of-the-art results across 8 global simulation benchmarks — but the bigger opportunity is building the infrastructure that lets the entire industry level up together. Full coverage: roboticsandautomationnews.co… #HumanoidAI #PhysicalAI #Robotics #NVIDIA #RLWRLD #Dexterity #RoboticsFoundationModel #RLDX1

Today, RLWRLD unveils RLDX-1 — our proprietary Robotics Foundation Model. Across all 8 public benchmarks, RLDX-1 outperforms leading SOTA models including #NVIDIA #GR00T and Physical Intelligence #π0 — delivering state-of-the-art performance among open robotics foundation models. 🎯 A 'Dexterity-First' Philosophy The industry assumes dexterity will follow once intelligence is solved. We see it the other way around. Dexterity isn't downstream of intelligence — it's the path intelligence must take to act in the physical world. Real industrial work with five-finger robotic hands depends on signals vision alone can't capture: force (torque), tactile feedback, and the precise moment of contact. 🧠 MSAT — Multi-Stream Action Transformer Where conventional VLAs collapse every input into a single transformer stream, MSAT gives each modality — vision, language, action, touch, memory — its own dedicated stream, then unifies them through joint attention. Force, tactile signals, and long-term memory are handled by purpose-built Physics and Memory modules. The result: one model that can see, feel, remember, and adapt. 📊 Performance Highlights RoboCasa Kitchen — 70.6: the first VLA model to cross the 70-point threshold GR-1 Tabletop — 58.7: 10.7 percentage points over NVIDIA GR00T N1.6 LIBERO-Plus — 86.7%: top score across 7 robustness variables Pot-to-Cup Pouring on WIRobotics ALLEX — 70.8%: nearly 2× the comparison models, which remained in the high-30% range. We're also releasing DexBench — our industry-grounded benchmark for dexterous manipulation, defined across five domains: Grasp Diversity, Spatial Precision, Temporal Precision, Contact Precision, and Context Awareness. 🔓 Open Release Three checkpoints (8.1B parameters each), live now on GitHub and Hugging Face: RLDX-1-PT — pre-training RLDX-1-MT-ALLEX — mid-training for ALLEX RLDX-1-MT-DROID — mid-training for DROID ⚙️ Built on NVIDIA's Cloud-to-Edge Stack Training and simulation on Isaac GR00T, Isaac Lab, Isaac Sim, and cuRobo. Compute on NVIDIA H100 and A100 GPUs. Edge inference on Jetson AGX Thor with TensorRT. Our collaborations with NVIDIA, AWS, and Microsoft continue across both research and deployment. 🌍 What's Next: The 4D World Model Video-based world models will never surface what isn't in the pixels — contact torque, tactile signals, robot state. Our 4D World Model integrates these directly with vision, language, and action across the temporal dimension, predicting and generating the full physical world. RLDX-1 is the first milestone on that roadmap. 📍 Join us at Dexterity Night in San Francisco on May 13 — followed by launch events in Japan and Korea. 🔗 Explore RLDX-1 on GitHub and Hugging Face. rlwrld.ai/ko/rldx-1 #RLWRL #RLDX1 #PhysicalAI #RoboticsFoundationModel #VLA #Humanoid #Dexterity #FoundationModel #Robotics #AI

most people talk about AI robots like it's 10 years away. i've been going deep on the actual tech stack and it's already here. OpenVLA - a 7B vision-language-action model - takes a camera image a text instruction and outputs real robot movements. no scripting. no pre-programmed paths. just pure learned intelligence. "pick up the cup" → model sees the scene → predicts exact end-effector movements → robot moves. trained on nearly 1 million real manipulation demos across multiple robots. and @konnex_world plugged this directly into their permissionless AI marketplace - so now anyone can deploy OpenVLA as a competing policy, get scored on real metrics, and earn if their model wins. the gap between "AI understands language" and "AI moves objects in the physical world" just closed. 🤖 thread incoming on how VLA models actually work 👇 #konnex #konnexworld #OpenVLA #robotics #physicalai #web3 #roboticsfoundationmodel