Paper link for FLEX: robots generalize language corrections into preferences
JafarNajafov · x · 2026-11-11
Author JafarNajafov replies to his own thread about MIT/NYU's FLEX robot learning system with the arXiv paper link. The substance is the quoted thread: FLEX uses GPT-4o to generalize a single language correction ("don't spill coffee on my laptop") into a broader preference (avoid all electronics), and outperformed baselines across all 7 simulated navigation scenarios.
More from Embodied
- Lighthouse extends Obsidian welding foundation model to run on any robotic platform — bennash · 2026-11-11
- Sipeed's MaixStation Dock PCB returns, 14-layer SOM still in fab — AIFlow_ML · 2026-11-11
- NAE EU-US Frontiers of Engineering symposium explores AI-driven materials, robotics, neuromorphic computing — ProfBuehlerMIT · 2026-11-11
- MIT and NYU's FLEX lets robots generalize a single spoken correction into broad preferences — JafarNajafov · 2026-11-11
- AI lets robotics research thrive in labs with no robotics experts — 4310sy · 2026-11-11
- Tektronix launches ~$500 12-bit DPO scope with AI MCP support in closed beta — IgorCarron · 2026-11-11