Wenhao Yu

New methods enhance robot navigation in complex environments using vision technology and context-aware systems.

This study measures LLMs’ performance in complex math dialogues.

Legged robots are evolving to meet diverse challenges across various fields.

Introducing reflective augmentation to improve language models’ math problem-solving skills.

Robots improve navigation by understanding both speech and images.

DocBench benchmarks LLM-based systems for reading and responding to various document formats.

Cognitive Kernel is an open-source system that autonomously handles tasks and gathers information.

This study enhances quadrupedal robots' ability to jump continuously over obstacles.