News

CSAIL’s approach uses an LLM to plan how to answer complex reasoning tasks, then divides the legwork of that strategy among smaller language models. Their method helps LMs provide more accurate responses than leading LLMs and approach the precision of top reasoning systems, while being more efficient than both (Credit: Alex Shipps/MIT CSAIL).

New method enables small language models to solve complex reasoning tasks

MIT researchers found that many so-called “ineffective” networks may simply start from less-than-ideal starting points, and that short-term guidance can strengthen their performance (Credit: Alex Shipps/MIT CSAIL).

Guided learning lets "untrainable" neural networks realize their potential

MIT researchers are teaching robots to understand their own limits while still achieving their goals, ensuring the machines move safely and never overextend themselves (Credits: Maximilian Stölzle and Joey Impoza Roberts).

New control system teaches soft robots the art of staying safe

Spotlighted News

New method enables small language models to solve complex reasoning tasks

Guided learning lets "untrainable" neural networks realize their potential

New control system teaches soft robots the art of staying safe