Jun Liu

Beyond the Stability-Exploration Dilemma: Environmental Regularization for LLM Policy Optimization

MUR: Momentum Uncertainty guided Reasoning for Large Language Models

Plan before Solving: Problem-Aware Strategy Routing for Mathematical Reasoning

From Static to Dynamic: Adaptive Monte Carlo Search for Mathematical Process Supervision

Deliberation on Priors: Trustworthy Reasoning of Large Language Models on Knowledge Graphs

Causal-R: A Causal-Reasoning Geometry Problem Solver for Optimized Solution Exploration

CoFFT: Chain of Foresight-Focus Thought for Visual Language Models

ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding