Liyuan Liu

5 papers Microsoft Research

• Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation
• Mixture of Inputs: Text Generation Beyond Discrete Token Sampling
• Reinforcement Learning for Reasoning in Large Language Models with One Training Example
• Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection
• Training Language Models to Generate Quality Code with Program Analysis Feedback