Microsoft Research open-sources Rho, a family of 5B VLAs for adaptable physical AI
chris_j_paxton · x · 2026-10-01
Microsoft Research's Andrey Kolobov announced Rho, a family of open-weights 5B VLAs underlying the Rho-alpha VLA+ work, with project page, tech report, code, and models/data all public.
- Motivation: offline SFT — the adaptation stage "owned" by robot operators — is data-hungry because it must simultaneously learn task control and cover many task/environment variations
- Mitigation: Rho ships midtrained checkpoints for i2rt YAM Box, Universal Robots AI Trainer, and FRANKA FR3 Duo platforms
- Aims at physical AI that adapts to new tasks and environments
More from Embodied
- Humanoid robot demo shows real-time perception, hand coordination and human interaction — CurieuxExplorer · 2026-10-01
- Robotics companies aren't taking 'cheapness' seriously enough, argues founder — hudzah · 2026-10-01
- Blogger predicts humanoid robots will soon run hotel services like laundry — CyberRobooo · 2026-10-01
- NVIDIA's Instant NuRec reconstructs a drivable 3DGS world from driving logs in ~1.5 seconds — rsasaki0109 · 2026-10-01
- Yuanyjie Robotics raises seed round to automate restaurant kitchens with embodied AI — 创业邦 · 2026-10-01
- GPT-6 Astra robot evals show strong task decisions but weak physical control — Galbot · 2026-10-01