Andi Peng


Natural language boosts LLM performance in coding, planning, and robotics

May 3, 2024

Three neurosymbolic methods help language models find better abstractions within natural language, then use those representations to execute complex tasks.

Reasoning and reliability in AI

January 22, 2024

PhD students interning with the MIT-IBM Watson AI Lab look to improve natural language usage.

A faster way to teach a robot

August 10, 2023

A new technique helps a nontechnical user understand why a robot failed, and then fine-tune it with minimal effort to perform a task effectively.