Assistant Professor, The Hong Kong University of Science and Technology (Guangzhou)
3 papers at NeurIPS 2025
The Atom of Thoughts leverages a Markovian reasoning process to enhance test-time scaling efficiency in LLMs, decomposing reasoning into low-complexity atomic units for scalable, high-performance inference.
DeepFund introduces a live benchmarking framework that prevents LLMs from 'cheating' by using live market data, revealing that most current LLMs struggle to make profitable trading decisions in real-time market conditions.