Lin Yang

Following the Navigation: Enhancing Small Language Models Contextual Reasoning with LLM Guidance

Boosting Multi-Domain Reasoning of LLMs via Curvature-Guided Policy Optimization

Latent-Guided Reasoning: Empowering Small LLMs with Large-Model Thinking

Preference Optimization via Key-step Error Exploration for Multi-step Reasoning in LLMs

CAPO: Conflict-Aware Policy Optimization for Large Language Models

SteadyThought: Mitigating LLM Under-Thinking via Thought-Level Preference Optimization

LogicTree: Improving Complex Reasoning of LLMs via Instantiated Multi-step Synthetic Logical Data

Boosting Multi-Domain Fine-Tuning of Large Language Models through Evolving Interactions between Samples