MIT and NYU Introduce FLEX for Language-Guided Robot Preference Learning

MIT CSAIL and NYU researchers introduced FLEX, presented at CoRL 2026, which lets robots iteratively edit task representations from natural-language corrections and generalize user preferences from a single piece of feedback.

2026-11-11 ~ 2026-11-11 · 3 related posts

• MIT's FLEX pipeline lets robots refine task representations from natural language corrections — andreea7b · 2026-11-11
• MIT and NYU's FLEX lets robots generalize a single spoken correction into broad preferences — JafarNajafov · 2026-11-11
• Paper link for FLEX: robots generalize language corrections into preferences — JafarNajafov · 2026-11-11