Erxue Min

CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs

Dataset Regeneration for Cross Domain Recommendation

Solving the Granularity Mismatch: Hierarchical Preference Learning for Long-Horizon LLM Agents

Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding

Cog-Rethinker: Hierarchical Metacognitive Reinforcement Learning for LLM Reasoning

Hgformer: Hyperbolic Graph Transformer for Collaborative Filtering