Gamow Labs builds eval to close the gap between model-perceived and actual robot pose in wet labs
danielmckinn0n · x · 2026-11-03
Gamow Labs, whose mission is democratizing rare-disease diagnosis, relies on robotics for wet-lab automation. One-shot experimental design and execution fails today partly because of the gap between model-perceived and actual robot pose.
Quoted engineer @zdql explains why robotics RL is hard: real-world rollouts are unaffordable in high-consequence settings like wet labs, so teams must simulate — and the key open questions are proving simulation realism and ensuring sim-to-real transfer. Their latest LabRobotBench update iterates to close the sim-to-real gap, enabling faster learning via simulation rollouts and more robust production behavior by catching failures in simulation.
The team invites collaborators working at the intersection of AI and wet-lab automation.
More from Embodied
- Robotics researchers lead AI citation growth: Sergey Levine tops monthly gains at +4.83% — ksprdk · 2026-11-03
- Robot sims should prioritize accurate physics over visuals, turning sim creation into an auto-research loop — wellecks · 2026-11-03
- Bleu Robotics raises €5M pre-seed to deploy humanoids in factories with just 10 demos per task — lukas_m_ziegler · 2026-11-03
- Machenta exits stealth with $40M seed, largest ever for a UK robotics startup — lukas_m_ziegler · 2026-11-03
- World model that predicts the future directly in 3D, fully open-sourced — YunzhuLiYZ · 2026-11-03
- Dream-1 zero-shot robot test: 100 public episodes show real skills but poor instruction following — paigeinsf · 2026-11-03