4 papers
AlgoPilot: Fully Autonomous Program Synthesis Without Human-Written Programs
Xiaoxin Yin
Program synthesis has traditionally relied on human-provided specifications, examples, or prior knowledge to generate functional algorithms. Existing methods either emulate human-w…
"Turing Tests" For An AI Scientist
Xiaoxin Yin
While LLMs have shown impressive capabilities in solving math or coding problems, the ability to make scientific discoveries remains a distinct challenge. This paper proposes a "Tu…
Transformer-based Parameter Estimation in Statistics
Xiaoxin Yin, David S. Yin
Parameter estimation is one of the most important tasks in statistics, and is key to helping people understand the distribution behind a sample of observations. Traditionally param…
Automated Discovery of Integral with Deep Learning
Xiaoxin Yin
Recent advancements in the realm of deep learning, particularly in the development of large language models (LLMs), have demonstrated AI's ability to tackle complex mathematical pr…