Jin Peng Zhou

Introducing REFACTOR, a system for automatic theorem extraction from mathematical proofs.

DTV method enhances reliability of answers from large language models in math problems.

A new algorithm improves code refinement using LLMs more efficiently.

QuAN model efficiently analyzes complex quantum systems for improved understanding.

Gemma 2 offers high performance in a compact size for language tasks.

RAG improves language models but faces challenges from misinformation attacks.