Benyou Wang

5 papers The Chinese University of Hong Kong, Shenzhen

• QFFT, Question-Free Fine-Tuning for Adaptive Reasoning
• Teaching Language Models to Reason with Tools
• The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models
• TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets
• Video-R1: Reinforcing Video Reasoning in MLLMs