AI.info

Liuyu Xiang

Explore Liuyu Xiang on AI.info.

• A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM
• Omni-RRM: Advancing Omni Reward Modeling via Automatic Rubric-Grounded Preference Synthesis
• Select-Then-Decompose: From Empirical Analysis to Adaptive Selection Strategy for Task Decomposition in Large Language Models