If you haven't followed Axis on Instagram yet, now is the best time! Our IG is where we share quick, vibrant bites of our progress, community events, and behind-the-scenes moments. It's the best way to catch up, understand what we're building, and dive deeper into the Axis stack—fast. Follow us here 👇 instagram.com/axisrobotics_o…

Physical AI onchain isn't just exciting—it’s accessible to everyone. 🦾 Huge thanks to @baseapac for the feature at SuperAI! We showed that simulation is no longer locked behind expensive rigs. Zero special hardware needed. Anyone can train real robots directly on @base today.

It's AXIS.

Axis Weekly This week was about making AXIS more reliable across the full robotics loop: stabilizing articulated-object TaskGen, scaling randomized-view data collection, improving product reliability for a new embodiment, and tightening the path from attempts to replays to real-world validation. Key updates: - Task Generation: We tested 12 articulated objects across 6 categories, fixed rotation and collision bugs, and prepared the articulated-object pipeline for the next round of internal testing. - Randomized-view data: We added stronger camera-position randomization and collected around 80k demonstrations under randomized views, with the next milestone at 100k demos. - New embodiment reliability: We completed teleoperation for a new embodiment and fixed evaluation issues caused by earlier task versions and inconsistent checker logic. - Product infrastructure: We improved MuJoCo/attempt video export, backend task isolation, and API reliability for replay visualization and debugging workflows. Details below 🧵

physical ai requires more than intelligent models. it requires systems that can learn from feedback, adapt to changing environments, and improve through experience. axis is building the infrastructure layer designed to support that evolution at scale. @axisrobotics

Excited to build robotics on @base. Real energy at SuperAI with @baseapac. We’re just getting started bringing robots, AI, and onchain coordination together.

In our conference submission, we evaluate AXIS as a growable data engine for robot manipulation through three questions: 1. Does AXIS pretraining improve π0.5 on downstream LIBERO-Plus robustness tasks, beyond a matched-volume baseline? 2. Does the gain scale with AXIS data volume, from 25% to 50% to 100% of data volume? 3. Which perturbation axes benefit the most, and do they match the diversity targeted by our augmentation pipeline? Here, “AXIS” refers to our growable manipulation dataset snapshot built around a Franka Research 3 robot: 207 tabletop tasks across 7 scene categories, 50k human demonstrations, and 60k task/scene variants produced through cleaning and semantic-preserving augmentation. Findings below 🧵

GAxis (✱,✱)☀️ New week. New challenges. New access. We’re giving away 10 BitRobot access codes over the next 72 hours. Winners will get access to SN/04 and start earning rewards from both Axis and BitRobot. To join: 1. Follow @axisrobotics & @BitRobotNetwork 2. Like repost this post 3. Comment with a screenshot or photo of where you’re training right now Grinding tasks? Climbing the leaderboard? Show us your journey.