Voxel51

Join Voxel51 and Nebius at MotionLab.Berlin on Sept 26 for an afternoon of Physical AI talks and a hands-on robotics workshop - https://lnkd.in/gC_m4DPZ * A hands-on workshop taking real robot logs all the way to a trained detector * We’ll curate, embed, auto-label, and fine-tune YOLO11n in one sitting using Nebius Serverless AI Jobs * Explore multimodal robot data — camera, proprioception, and language on one synced timeline in FiftyOne. No ROS install required. Bring a laptop. Space is limited. Pre-registration is mandatory. #PhysicalAI #Robotics #ComputerVision #MachineLearning #FiftyOne #berlin

Join Voxel51 and Nebius at Impact Hub Stuttgart on Sept 22 for an evening of Physical AI talks and a hands-on robotics workshop - https://lnkd.in/gNuiWtR9 * Lightning talks from Dhia Abdelli at Lumanaa * A hands-on workshop taking real robot logs all the way to a trained detector * We’ll curate, embed, auto-label, and fine-tune YOLO11n in one sitting using Nebius Serverless AI Jobs * Explore multimodal robot data — camera, proprioception, and language on one synced timeline in FiftyOne. No ROS install required. Bring a laptop. Space is limited. Pre-registration is mandatory. #PhysicalAI #Robotics #ComputerVision #MachineLearning #FiftyOne #stuttgart

Join Voxel51 and Nebius at Impact Hub Munich on Sept 23 for an evening of Physical AI talks and a hands-on robotics workshop - https://lnkd.in/gxAhMcDf * Lightning talks from Jayabalaji Sathiyamoorthi at Intel and Alexander Nenninger at NTT DATA * A hands-on workshop taking real robot logs all the way to a trained detector * We’ll curate, embed, auto-label, and fine-tune YOLO11n in one sitting using Nebius Serverless AI Jobs * Explore multimodal robot data — camera, proprioception, and language on one synced timeline in FiftyOne. No ROS install required. Bring a laptop. Space is limited. Pre-registration is mandatory. #PhysicalAI #Robotics #ComputerVision #MachineLearning #FiftyOne #munich

Join Voxel51 at w3.hub in Berlin on Sept 25 for the AI, ML and Computer Vision Meetup - https://lnkd.in/gSqXtC9e Talks will include: * Toward the best ROI: choosing algorithms for AI-powered workstations - Anton Maltsev at RemBrain * One Pipeline, Any Device: Swap the Reader, Not the Pipeline - Tom Kaltofen at mloda.ai * Building Real-World Computer Vision Systems - Dan Gural at Voxel51 #PhysicalAI #Robotics #ComputerVision #MachineLearning #FiftyOne #berlin

you have budget for a few hundred annotations and a pool of thousands of unlabeled images. pick randomly and you relabel what you already understand while the classes you need most stay uncovered on a real 1,754-image drone inspection dataset: random sampling finds the hardest class 12.9% of the time. targeted search + embedding-based prioritization finds it 100%. same labeling budget live workshop, the full loop: 1. embed the pool once 2. compress duplicates 3. search with a few labeled examples 4. prioritize what's left 5. fine-tune, then correct instead of relabel aug 20 · free · hands-on in fiftyone register: https://lnkd.in/gRdnqm6z

One of the best parts of working closely with MLEs is getting to learn from teams actually shipping physical AI in production. Rare classes and long-tail coverage come up again and again, which is why I’m looking forward to my colleague Harpreet S.'s workshop this Thursday. Join us for a hands-on walkthrough of rare-class mining in Voxel51: find the needles in your unlabeled pool, prioritize them for annotation, and prove a small curated set beats brute-force labeling. If you're wrestling with rare-class detection, make sure to join us and bring your questions. Register here: https://lnkd.in/eXSN8JMz