Haoran Cai

Amplify Adjacent Token Differences: Enhancing Long Chain-of-Thought Reasoning with Shift-FFN

EDCO: Dynamic Curriculum Orchestration for Domain-specific Large Language Model Fine-tuning

Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent

Boosting Document Layout Analysis with Graphic Multi-modal Data Fusion and Spatial Geometric Transformation