3 citations · 6 across the 9 of their papers we have counts for
4 papers · 1 filter
From Content Generation to Learning Support: Pedagogy-Guided Generative Video Tutors for STEM Learning
Xinchen Ma, Shuimu Wang, Gaole He +4
Generative AI enables scalable production of educational videos, but current systems largely focus on producing visually coherent content rather than supporting learning. As a resu…
Progress-SQL: Improving Reinforcement Learning for Text-to-SQL via Progressive Rewards
Shihao Zhang, Xiaoman Wang, Yuan Liu +2
Reinforcement learning has recently shown promise in improving large language models for Text-to-SQL generation, yet existing methods typically optimize one-shot rewards defined ov…
Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning
Jiapeng Zhu, Jianxiang Yu, Yibo Zhao +5
Equipping large language models with explicit skills has emerged as a promising paradigm for enabling autonomous agents to solve complex tasks. Agent skills can be inherently divid…
TagRAG: Tag-guided Hierarchical Knowledge Graph Retrieval-Augmented Generation
Wenbiao Tao, Xinyuan Li, Yunshi Lan +1
Retrieval-Augmented Generation enhances language models by retrieving external knowledge to support informed and grounded responses. However, traditional RAG methods rely on fragme…