Machenta shows robots learning new tasks from a single demonstration
Ed__Johns · x · 2026-10-29
Machenta argues steerability is key in robot learning: a pre-trained robot model must genuinely condition on teaching demonstrations rather than replaying pre-trained tasks. Their model is instantly steerable from one demonstration — the same set of objects can teach the robot three different interactions by changing only the demonstration.
Related event: Machenta Unveils Instant Robot Learning from a Single Demonstration(2 posts)→
More from Embodied
- Neuralink says brain implants now turn neural signals into speech at conversational speed — Polymarket · 2026-10-29
- Robotics team hosts Sim2Real playoff: win in sim, control a real robot — cixliv · 2026-10-29
- NVIDIA's ProtoMotions lets you race the same policy that drives a real Unitree G1 — xbpeng4 · 2026-10-29
- Confetti: a YC-backed platform that turns plain English into shipped hardware parts — ycombinator · 2026-10-29
- Waymo doors won't open or close, support never calls — rider may switch back to humans — henloitsjoyce · 2026-10-29
- SuperMimic demo: vision-conditioned pi+ traverses stepped pit grid in sim — ChongZzZhang · 2026-10-29