MIT Uses LLMs to Teach Robots to Understand Vague Commands
MIT_CSAIL · x · 2026-07-04
MIT introduced "Masked IRL," leveraging LLMs to help robots perform tasks like household chores despite ambiguous instructions by focusing on crucial details. One model clarifies the user's vague prompts, while the other filters out irrelevant information.
More from Research
- Causal-only attention for non-generative tasks is wasteful, argues HF engineer — antoine_chaffin · 2026-09-11
- Catholic University of Chile researcher: scaling AI feedback is key to sustainable medical education — julianvarascom · 2026-09-11
- Nature paper images cellular activity across all organs, revealing body-wide circuits — arjunrajlab · 2026-09-11
- SignNet 1M Dataset Released for Sign Language Research — ducha_aiki · 2026-09-11
- ECCV26 Oral: Flow Matching Enables Single-Stage Multi-View Point Cloud Registration — ducha_aiki · 2026-09-11
- InFlux++ Method Released — ducha_aiki · 2026-09-11