Figure's Helix 2.5 runs zero-shot whole-body tasks across 30 unseen homes
adcock_brett · x · 2026-09-18
Figure unveils Helix 2.5, its most advanced neural network yet, built to answer a harder question: can a humanoid enter an unseen home and immediately start working with its whole body, autonomously?
Key points:
- Zero-shot whole-body autonomy across 30 real Bay Area homes, with no data collection, fine-tuning, or adaptation in those environments or on the objects handled — claimed as the first demonstration of zero-shot whole-body generalization at this scope on a humanoid.
- A single Index-pretrained base model drives three long-horizon behaviors: tidying living rooms, folding towels, and making beds, spanning locomotion, rigid and deformable manipulation, bimanual coordination, and active perception.
- Index, Figure's global-scale dataset of human behavior, is the key driver of generalization, per ablations holding everything else fixed.
- A companion video shows 4 hours of zero-shot work across 30 rental homes.
Unlike Helix 02, which learned from data collected where robots would operate, Helix 2.5 marks a step toward cross-environment generalization.
More from Embodied
- Mask R-CNN author Georgia Gkioxari argues closed-loop self-improving perception is AI's next leap — CSProfKGD · 2026-09-18
- World's first robot vs human fight set for tomorrow night in SF — cixliv · 2026-09-18
- UChicago neuroscientist decodes brain signals to restore touch and movement via brain-machine interfaces — plopesresearch · 2026-09-18
- Camera-free AI glasses are easy for Meta; shaking the 'pervert glasses' reputation is the hard part — Glittering_Royal6799 · 2026-09-18
- Figure's Home Robot Math: $400-600/Month Lease With a 56% Task Completion Rate — yongqianme · 2026-09-18
- Figure May Have Found a Scaling Law for Robot Pretraining, Predicting 8x-Data Runs — rohanpaul_ai · 2026-09-18