collaborators

5 papers

cs.DB2026

Query-Centric Optimization of AI Workflows via Approximate Query Processing and Proxy Models

Huayi Wang, Jun Xu, Gromit Yeuk-Yin Chan

Many modern AI workflows, ranging from LLM post-training pipelines to agentic reasoning tasks, can be expressed as declarative queries whose expensive predicate is evaluated by a l…

cs.AI2025

Thinker: Training LLMs in Hierarchical Thinking for Deep Search via Multi-Turn Interaction

Jun Xu, Xinkai Du, Yu Ao +17

Efficient retrieval of external knowledge bases and web pages is crucial for enhancing the reasoning abilities of LLMs. Previous works on training LLMs to leverage external retriev…

cs.CL2025

KAG-Thinker: Interactive Thinking and Deep Reasoning in LLMs via Knowledge-Augmented Generation

Dalong Zhang, Jun Xu, Jun Zhou +16

In this paper, we introduce KAG-Thinker, which upgrade KAG to a multi-turn interactive thinking and deep reasoning framework powered by a dedicated parameter-light large language m…

cs.CL2025

MAQInstruct: Instruction-based Unified Event Relation Extraction

Jun Xu, Mengshu Sun, Zhiqiang Zhang +1

Extracting event relations that deviate from known schemas has proven challenging for previous methods based on multi-class classification, MASK prediction, or prototype matching.…

cs.CL2025

Improving Natural Language Understanding for LLMs via Large-Scale Instruction Synthesis

Lin Yuan, Jun Xu, Honghao Gui +4

High-quality, large-scale instructions are crucial for aligning large language models (LLMs), however, there is a severe shortage of instruction in the field of natural language un…