Yukun Yan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yukun Yan has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Zhenghao Liu
Northeastern University, Shenyang, China
8 shared publications - Ge Yu
Northeastern University, Shenyang, China
7 shared publications - Yu Gu
Northeastern University
6 shared publications - Shuo Wang
Tsinghua University, Beijing, China
5 shared publications - Shi Yu
Tsinghua University, Beijing, China
4 shared publications - Zhipeng Xu
Northeastern University, Shenyang, China
4 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 9294-9303
Mitigating Visual Hallucinations via Evidence-Guided Multi-Image Reasoning in Visual Retrieval-Augmented Generation
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 9294-9303
Open AccessMitigating Visual Hallucinations via Evidence-Guided Multi-Image Reasoning in Visual Retrieval-Augmented Generation
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1440-1450
Mixture-of-Retrieval Experts for Reasoning-Guided Multimodal Knowledge Exploitation
Multimodal Retrieval-Augmented Generation (MRAG) has shown promise in mitigating hallucinations in Multimodal Large Language Models (MLLMs) by incorporating external knowledge. However, existing methods typically adhere to rigid retrieval paradigms by mimicking fixed retrieval trajectories and thus fail to fully exploit the knowledge of different retrieval experts through dynamic interaction based on the model's knowledge needs or evolving reasoning states. To overcome this limitation, we introduce Mixture-of-Retrieval Experts (MoRE), a novel framework that enables MLLMs to collaboratively interact with diverse retrieval experts for more effective knowledge exploitation. Specifically, MoRE learns to dynamically determine which expert to engage with, conditioned on the evolving reasoning state. To effectively train this capability, we propose Stepwise Group Relative Policy Optimization (Step-GRPO), which goes beyond sparse outcome-based supervision by encouraging MLLMs to interact with multiple retrieval experts and synthesize fine-grained rewards, thereby teaching the MLLM to fully coordinate all experts when answering a given query. Experimental results on diverse open-domain QA benchmarks demonstrate the effectiveness of MoRE, achieving average performance gains of over 7% compared to competitive baselines. Notably, MoRE exhibits strong adaptability by dynamically coordinating heterogeneous experts to precisely locate relevant information, validating its capability for robust, reasoning-driven expert collaboration. All codes and data are released on https://github.com/OpenBMB/MoRE.
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1440-1450
Open AccessMixture-of-Retrieval Experts for Reasoning-Guided Multimodal Knowledge Exploitation
Multimodal Retrieval-Augmented Generation (MRAG) has shown promise in mitigating hallucinations in Multimodal Large Language Models (MLLMs) by incorporating external knowledge. However, existing methods typically adhere to rigid retrieval paradigms by mimicking fixed retrieval trajectories and thus fail to fully exploit the knowledge of different retrieval experts through dynamic interaction based on the model's knowledge needs or evolving reasoning states. To overcome this limitation, we introduce Mixture-of-Retrieval Experts (MoRE), a novel framework that enables MLLMs to collaboratively interact with diverse retrieval experts for more effective knowledge exploitation. Specifically, MoRE learns to dynamically determine which expert to engage with, conditioned on the evolving reasoning state. To effectively train this capability, we propose Stepwise Group Relative Policy Optimization (Step-GRPO), which goes beyond sparse outcome-based supervision by encouraging MLLMs to interact with multiple retrieval experts and synthesize fine-grained rewards, thereby teaching the MLLM to fully coordinate all experts when answering a given query. Experimental results on diverse open-domain QA benchmarks demonstrate the effectiveness of MoRE, achieving average performance gains of over 7% compared to competitive baselines. Notably, MoRE exhibits strong adaptability by dynamically coordinating heterogeneous experts to precisely locate relevant information, validating its capability for robust, reasoning-driven expert collaboration. All codes and data are released on https://github.com/OpenBMB/MoRE.
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 2162-2173
ReAlign: Optimizing the Visual Document Retriever with Reasoning-Guided Fine-Grained Alignment
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 2162-2173
Open AccessReAlign: Optimizing the Visual Document Retriever with Reasoning-Guided Fine-Grained Alignment
- Open Access
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1650-1661
LISRec: Modeling User Preferences with Learned Item Shortcuts for Sequential Recommendation
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1650-1661
Open AccessLISRec: Modeling User Preferences with Learned Item Shortcuts for Sequential Recommendation
- Open Access
- 1 January 2026
- Published by KEAI Publishing in AI Open
- Vol. 7, 18-44
Knowledge intensive agents
- 1 January 2026
- Published by KEAI Publishing in AI Open
- Vol. 7, 18-44
Open AccessKnowledge intensive agents
- Open Access
- 6 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 292-302
Learning Refined Document Representations for Dense Retrieval via Deliberate Thinking
- 6 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 292-302
Open AccessLearning Refined Document Representations for Dense Retrieval via Deliberate Thinking
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 4817-4826
Benchmarking Retrieval-Augmented Generation in Multi-Modal Contexts
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 4817-4826
Open AccessBenchmarking Retrieval-Augmented Generation in Multi-Modal Contexts
- Open Access
- 17 January 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 43 (2) , 1-25
Building a Coding Assistant via the Retrieval-Augmented Language Model
Pretrained language models have shown strong effectiveness in code-related tasks, such as code retrieval, code generation, code summarization, and code completion tasks. In this article, we propose COde assistaNt viA retrieval-augmeNted language model (CONAN), which aims to build a code assistant by mimicking the knowledge-seeking behaviors of humans during coding. Specifically, it consists of a code structure-aware retriever (CONAN-R) and a dual-view code representation-based retrieval-augmented generation model (CONAN-G). CONAN-R pretrains CodeT5 using Code-Documentation Alignment and Masked Entity Prediction tasks to make language models code structure-aware and learn effective representations for code snippets and documentation. Then CONAN-G designs a dual-view code representation mechanism for implementing a retrieval-augmented code generation model. CONAN-G regards the code documentation descriptions as prompts, which help language models better understand the code semantics. Our experiments show that CONAN achieves convincing performance on different code generation tasks and significantly outperforms previous retrieval augmented code generation models. Our further analyses show that CONAN learns tailored representations for both code snippets and documentation by aligning code-documentation data pairs and capturing structural semantics by masking and predicting entities in the code data. Additionally, the retrieved code snippets and documentation provide necessary information from both program language and natural language to assist the code generation process. CONAN can also be used as an assistant for Large Language Models (LLMs), providing LLMs with external knowledge in shorter code document lengths to improve their effectiveness on various code tasks. It shows the ability of CONAN to extract necessary information and help filter out the noise from retrieved code documents.
- 17 January 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 43 (2) , 1-25
Open AccessBuilding a Coding Assistant via the Retrieval-Augmented Language Model
Pretrained language models have shown strong effectiveness in code-related tasks, such as code retrieval, code generation, code summarization, and code completion tasks. In this article, we propose COde assistaNt viA retrieval-augmeNted language model (CONAN), which aims to build a code assistant by mimicking the knowledge-seeking behaviors of humans during coding. Specifically, it consists of a code structure-aware retriever (CONAN-R) and a dual-view code representation-based retrieval-augmented generation model (CONAN-G). CONAN-R pretrains CodeT5 using Code-Documentation Alignment and Masked Entity Prediction tasks to make language models code structure-aware and learn effective representations for code snippets and documentation. Then CONAN-G designs a dual-view code representation mechanism for implementing a retrieval-augmented code generation model. CONAN-G regards the code documentation descriptions as prompts, which help language models better understand the code semantics. Our experiments show that CONAN achieves convincing performance on different code generation tasks and significantly outperforms previous retrieval augmented code generation models. Our further analyses show that CONAN learns tailored representations for both code snippets and documentation by aligning code-documentation data pairs and capturing structural semantics by masking and predicting entities in the code data. Additionally, the retrieved code snippets and documentation provide necessary information from both program language and natural language to assist the code generation process. CONAN can also be used as an assistant for Large Language Models (LLMs), providing LLMs with external knowledge in shorter code document lengths to improve their effectiveness on various code tasks. It shows the ability of CONAN to extract necessary information and help filter out the noise from retrieved code documents.
- Open Access
- 11 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 39545-39554
ZoomNet for Topic-Oriented Fragment Recognition in Long Documents
This work introduces a new information extraction task called Topic-Oriented Fragment Recognition (TOFR) , whose goal is to recognize information related to a specific topic in long documents from professional fields. In this paper, we introduce two TOFR datasets to study the problems of processing long documents. We propose a novel neural framework named Zooming Network (ZoomNet) , which overcomes the challenge of combining information over long distances with limited computing resources by flexibly switching between skimming and intensive reading in processing long documents. In general, ZoomNet first establishes a hierarchical representation aligned to the text structure, which relieves the conflict between local information and extensive contextual information. Then, it synthesizes different levels of information to assign tags via multi-scale actions. We combine supervised and reinforcement learning methods to train our model. Experiments show that the proposed model outperforms several state-of-the-art sequence labeling models, including BiLSTM-CRF, BERT, XLNET, RoBERTa, and ELECTRA, on both TOFR datasets with big margins.
- 11 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 39545-39554
Open AccessZoomNet for Topic-Oriented Fragment Recognition in Long Documents
This work introduces a new information extraction task called Topic-Oriented Fragment Recognition (TOFR) , whose goal is to recognize information related to a specific topic in long documents from professional fields. In this paper, we introduce two TOFR datasets to study the problems of processing long documents. We propose a novel neural framework named Zooming Network (ZoomNet) , which overcomes the challenge of combining information over long distances with limited computing resources by flexibly switching between skimming and intensive reading in processing long documents. In general, ZoomNet first establishes a hierarchical representation aligned to the text structure, which relieves the conflict between local information and extensive contextual information. Then, it synthesizes different levels of information to assign tags via multi-scale actions. We combine supervised and reinforcement learning methods to train our model. Experiments show that the proposed model outperforms several state-of-the-art sequence labeling models, including BiLSTM-CRF, BERT, XLNET, RoBERTa, and ELECTRA, on both TOFR datasets with big margins.