TLDR Tech / Hardware
Figure's Helix 2.5 walks into 30 unseen homes and gets to work with zero fine-tuning
Figure pretrained Helix 2.5 entirely on Index, its crowdsourced human video dataset, then fine-tuned three whole-body behaviors - tidying rooms, folding towels, making beds - before deploying a single fixed checkpoint into 30 Bay Area homes it had never seen, with no data collection or adaptation on-site and objects it had never encountered. The key isolation test: training two otherwise identical policies on the same task-specific data, one from random initialization and one from Index-pretrained weights, showed Index pretraining alone lifted zero-shot success from 9% to 56%, over 6x higher, with success requiring full task completion and no partial credit.
Read the full story