Our latest embodied foundation model, DM0.5, is officially OUT! 🤖 We reject using predefined tasks to fake the unknown physical world. DM0.5 is built for the gritty, real-world scenes—and we brought the deployment threshold down to a single consumer-level GPU.⬇️

Dexbotic 2.0 Feature Spotlight: Faster DM0.5 Inference ⚡ Inference speed is the real test of a VLA in deployment. Dexbotic 2.0's new optional inference component makes DM0.5 up to ~5× faster, with no change to the model, accuracy or hardware. Your call: go fast, or stay on the default. Open sourced: github.com/dexmal/dexbotic

Understanding the structure and behavior of the physical world is a big goal for AI. For robotics, that understanding must also translate into action. At Dexmal, we’re working across world models, robot policies, training, inference, and real-world execution—connecting each step so robots can learn and act in the physical world. A thoughtful perspective from @drfeifei on where this field is headed. Congratulations to World Labs and AMD on this next chapter!

What happens when the camera shifts in the middle of a task? The pixels change. The task doesn’t. Dexmal DM0.5 remains robust to significant viewpoint shifts, recognizing the current task state and continuing execution without losing track.

A different object on the table shouldn’t become another task on a developer’s to-do list. Dexmal DM0.5 uses the same model weights to recognize, locate, and grasp objects across different shapes, materials, and positions—even with external disruptions. No model swaps or parameter tweaks required. That's less repetitive engineering for developers, and faster adaptation to whatever the next scenario throws at it. Watch DM0.5 in action 👇

Some things are easier said than typed. Some tasks are easier shown than described. With Dexmal’s DM0.5, a human demonstration becomes a Video Prompt. Native long-horizon memory lets it track the full sequence, align with the demonstration, and execute each step in real time.

Memory is one of the hardest problems in embodied intelligence. A robot doesn't just need to see what's in front of it. It needs to remember what happened before, especially across long, multi-step tasks. Dexmal DM0.5 carries native memory of up to 60 seconds, enough to hold the full arc of a multi-step task without losing track. In this desktop-cleaning demo, the robot remembers exactly where each object came from. Every item goes back to its original spot, in the right order.

What happens when you keep interrupting a robot mid-task? Dexmal DM0.5 maintains instruction understanding under interference and adapts its actions as the environment changes — without losing track of the task.

Back in July, we gave Dexmal a complete brand reset. A new logo, a new visual system, and a clearer way to express what we’re building toward. The idea underneath it never changed. Build better models, build systems that actually work, and build trust by testing them in the real world. This was the film we made to tell that story. Intelligent. Useful. Trustworthy.

GPT-6 Astra is genuinely impressive. It's sparking a debate: if a general-purpose model can see, reason, and pilot a robot arm, does embodied AI still need its own foundation model? We think it still does. Astra can do this because it was trained on robot data — that's not proof physical intelligence emerges from language and vision alone. Robotics doesn't get the shortcuts coding did. It still needs real robot data, real-world evaluation, and contact-rich physical interaction that no amount of general scale replaces. General intelligence is getting better at understanding the physical world. Embodied intelligence is about learning how to act in it.

Your embodied model works in the lab. Can developers actually run it? DexDev MaaS makes general-purpose embodied models as accessible as any cloud API. A single instruction is enough to start — the model perceives its environment, understands the task, and acts. Teams working with their own data, whether in LeRobot v3 format or otherwise, can take the full post-training workflow online, from upload to fine-tuning to deployment. Inference, fine-tuning, and deployment all happening in one place. maas.dexmal.com

Intelligence meets infrastructure. Dexmal × ATOMIX brings embodied AI into real-world warehouse operations at scale. From automation to autonomy.

A powerful model is only as good as the body carrying it. So we built Apex — a general-purpose robot designed from the ground up for real-world tasks. Its modular body can swap bases, arms and end effectors in under a minute, without rebooting the system. Perception, control and reasoning are built together, not bolted together. It's built to work, not just to demo — with a 1,000+ hour MTBF target, 24/7 operation, and 30-second battery swaps while the system stays online. Meet Dexmal Apex.

We've officially wrapped up our DM0.5 demos from WRC. During the exhibition, DM0.5 took on parcel sorting, food manipulation, and precision assembly — three completely different tasks, one generalist brain. WRC was one stop. More demos, more training, more capabilities, and more real-world challenges ahead. What should DM0.5 try next? Drop your ideas below!

We handed a kid our DM0.5 × SO101 setup, and here's what happened. With a small amount of data and fine-tuning, DM0.5 quickly adapts to SO101 — handling new colors, shifted positions, and even human interference without missing a beat. Model, dataset, and the full LoRA/SFT workflow are open source on @huggingface.

Open source is becoming infrastructure. Congrats @NVIDIA @huggingface. We're doing the same for embodied intelligence at Dexmal — open source on Hugging Face: huggingface.co/Dexmal2026