4 papers
DAG-FM: A Foundation Model for Causal Discovery under Heterogeneous Causal Mechanisms
Yikang Chen, Zhengkang Guan, Haoyuan Qian +5
The paper presents DAG-FM, a transformer‑based foundation model that discovers causal directed acyclic graphs from tabular data by sequentially predicting leaf and parent nodes and…
DCD-PFN: A Decoupling-Aware Foundation Model for Causal Discovery
Zhengkang Guan, Yikang Chen, Yi He +5
Causal discovery is critical for understanding complex data-generating mechanisms, yet traditional algorithms often struggle with highly non-linear and noisy systems, or suffer fro…
Enhancing LLM Tool Use with High-quality Instruction Data from Knowledge Graph
Jingwei Wang, Zai Zhang, Hao Qian +7
Teaching large language models (LLMs) to use tools is crucial for improving their problem-solving abilities and expanding their applications. However, effectively using tools is ch…
Relation-Aware Graph Foundation Model
Jianxiang Yu, Jiapeng Zhu, Hao Qian +3
In recent years, large language models (LLMs) have demonstrated remarkable generalization capabilities across various natural language processing (NLP) tasks. Similarly, graph foun…