教育经历（按时间倒序）：

• 2009-2012：香港城市大学 计算机科学 博士学位
• 2005-2008：中国科学技术大学 计算机科学与技术 硕士学位
• 2001-2005：长安大学 计算机科学与技术 学士学位

工作经历（按时间倒序）：

• 2017.07-至今：中山大学大学计算机学院 教授
• 2014.01-2017.05：新加坡科技研究局资讯通信研究院 研究科学家
• 2012.09-2013.12：香港城市大学翻译及语言学系 博士后研究员

权小军，博士，教授，深圳河套学院。博士毕业于香港城市大学计算机系，曾在罗格斯大学商学院和普渡大学计算机系访学，先后任职于香港城市大学翻译及语言学系、新加坡科技研究局资讯通信研究院及中山大学计算机学院。主要研究方向为自然语言处理（NLP）、大语言模型（LLMs）及模型压缩与轻量化，在 IEEE T-PAMI、ACL、ICML、NeurIPS、ICLR 等国际顶级期刊与会议发表论文百余篇，主持多项国家及省部级科研项目。提出多源异构大模型融合研究问题，研发FuseLLM、FuseChat系列模型并获得广泛关注。欢迎NLP与LLMs方向的科研合作与研究生报考。

Ÿ Tianyuan Shi, Fanqi Wan, Canbin Huang, Xiaojun Quan, Chenliang Li, Ming Yan, Ji Zhang, Minhua Huang, Wu Kai. ProFuser: Progressive Fusion of Large Language Models. AAAI 2026.

Ÿ Canbin Huang, Tianyuan Shi, Yuhua Zhu, Ruijun Chen, Xiaojun Quan. Lookahead Routing for Large Language Models. NeurIPS 2025.

Ÿ Runjia Zeng, James Chenhao Liang, Cheng Han, Zhiwen Cao, Jiahao Liu, Xiaojun Quan, Yingjie Victor Chen, Lifu Huang, Tong Geng, Qifan Wang, Dongfang Liu. Probabilistic Token Alignment for Large Language Model Fusion. NeurIPS 2025.

Ÿ Guosheng Liang, Longguang Zhong, Ziyi Yang, Xiaojun Quan. ThinkSwitcher: When to Think Hard, When to Think Fast. EMNLP 2025.

Ÿ Ruijun Chen, Jiajian Guo, Hongzhan Chen, Fanqi Wan, Qifan Wang, Xiaojun Quan. ReAlign: Structured Revision for Small Language Model Alignment. EMNLP 2025.

Ÿ Fanqi Wan, Longguang Zhong, Ziyi Yang, Ruijun Chen, Xiaojun Quan. FuseChat: Knowledge Fusion of Chat Models. EMNLP 2025.

Ÿ Tianyuan Shi, Canbin Huang, Fanqi Wan, Longguang Zhong, Ziyi Yang, Weizhou Shen, Xiaojun Quan, Ming Yan. Mutual-Taught for Co-adapting Policy and Reward Models. ACL 2025.

Ÿ Cong Liu, Xiaojun Quan, Yan Pan, Weigang Wu, Xu Chen, Liang Lin. Cool-Fusion: Fuse Large Language Models without Training. ACL 2025.

Ÿ Longguang Zhong, Fanqi Wan, Ruijun Chen, Xiaojun Quan, Liangzhi Li. BlockPruner: Fine-grained Pruning for Large Language Models. ACL 2025.

Ÿ Hongzhan Chen, Tao Yang, Shiping Gao, Ruijun Chen, Xiaojun Quan, Hongtao Tian, Ting Yao. Discriminative Policy Optimization for Token-Level Reward Models. ICML 2025, 2025.

Ÿ Ziyi Yang, Fanqi Wan, Longguang Zhong, Tianyuan Shi, Xiaojun Quan. Weighted-Reward Preference Optimization for Implicit Model Fusion. ICLR 2025, Poster, 2025.

Ÿ Shiping Gao, Fanqi Wan, Jiajian Guo, Xiaojun Quan, Qifan Wang. Advantage-Guided Distillation for Preference Alignment in Small Language Models. ICLR 2025, Spotlight, 2025.

Ÿ Weizhou Shen, Chenliang Li, Hongzhan Chen, Ming Yan, Xiaojun Quan, Hehong Chen, Ji Zhang, Fei Huang. Small LLMs Are Weak Tool Learners: A Multi-LLM Agent. EMNLP 2024, 16658-16680, 2024.

Ÿ Ruijun Chen, Jiehao Liang, Shiping Gao, Fanqi Wan, Xiaojun Quan. Self-Evolution Fine-Tuning for Policy Optimization. EMNLP (Findings) 2024, 4120-4137, 2024.

Ÿ Fanqi Wan, Xinting Huang, Leyang Cui, Xiaojun Quan, Wei Bi, Shuming Shi. Knowledge Verification to Nip Hallucination in the Bud. EMNLP 2024: 2616-2633.

Ÿ Haihui Yang, Xiaojun Quan. Alignment-Enhanced Chinese Grammatical Error Corrector. ACL 2024, 2024.

Ÿ Hongzhan Chen, Hehong Chen, Ming Yan, Wenshen Xu, Gao Xing, Weizhou Shen, Xiaojun Quan, Chenliang Li, Ji Zhang, Fei Huang. SocialBench: Sociality Evaluation of Role-Playing Conversational Agents. ACL 2024, 2024.

Ÿ Fanqi Wan, Xinting Huang, Deng Cai, Xiaojun Quan, Wei Bi, Shuming Shi. Knowledge Fusion of Large Language Models. ICLR 2024, 2024.

Ÿ Tianyuan Shi, Liangzhi Li, Zijian Lin, Tao Yang, Xiaojun Quan, Qifan Wang. Dual-Feedback Knowledge Retrieval for Task-Oriented Dialogue Systems. EMNLP 2023, Main Conference, 6566–6580, December 6-10, 2023.

Ÿ Weizhou Shen, Yingqi Gao, Canbin Huang, Fanqi Wan, Xiaojun Quan, Wei Bi. Retrieval-Generation Alignment for End-to-End Task-Oriented Dialogue System. EMNLP 2023, Main Conference, 8261–8275, December 6-10, 2023.

Ÿ Fanqi Wan, Xinting Huang, Tao Yang, Xiaojun Quan, Wei Bi, Shuming Shi. Explore-Instruct: Enhancing Domain-Specific Instruction Coverage through Active Exploration. EMNLP 2023, Main Conference, 8261–8275, 2023.

Ÿ Qifan Wang, Yuning Mao, Jingang Wang, Hanchao Yu, Shaoliang Nie, Sinong Wang, Fuli Feng, Lifu Huang, Xiaojun Quan, Zenglin Xu, Dongfang Liu. APrompt: Attention Prompt Tuning for Efficient Adaptation of Pre-trained Language Models. EMNLP 2023, Main Conference, 2023.

Ÿ Hongzhan Chen, Siyue Wu, Xiaojun Quan, Rui Wang, Ming Yan, Ji Zhang. MCC-KD: Multi-CoT Consistent Knowledge Distillation. EMNLP 2023, Findings, 6805–6820, 2023.

Ÿ Tao Yang, Tianyuan Shi, Fanqi Wan, Xiaojun Quan, Qifan Wang, Bingzhe Wu, Jiaxiang Wu. PsyCoT: Psychological Questionnaire as Powerful Chain-of-Thought for Personality Detection. EMNLP 2023, Findings, 2023.

Ÿ Siyue Wu, Hongzhan Chen, Xiaojun Quan, Qifan Wang and Rui Wang. AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression. ACL 2023, Main Conference, 2023.

Ÿ Fanqi Wan, Weizhou Shen, Ke Yang, Xiaojun Quan and Wei Bi. Multi-Grained Knowledge Retrieval for End-to-End Task-Oriented Dialog. ACL 2023, Main Conference, 2023.

Ÿ Zihong Liang, Xiaojun Quan and Qifan Wang. Disentangled Phonetic Representation for Chinese Spelling Correction. ACL 2023, Main Conference, 2023.

Ÿ Qifan Wang, Jingang Wang, Xiaojun Quan, Fuli Feng, Zenglin Xu, Shaoliang Nie, Sinong Wang, Madian Khabsa, Hamed Firooz and Dongfang Liu. MUSTIE: Multimodal Structural Transformer for Web Information Extraction. ACL 2023, Main Conference, 2023.

Ÿ Jinghao Deng, Fanqi Wan, Tao Yang, Xiaojun Quan and Rui Wang. Clustering-Aware Negative Sampling for Unsupervised Sentence Representation. ACL 2023, Findings, 2023.

Ÿ Weizhou Shen, Yeyun Gong, Yelong Shen, Song Wang, Xiaojun Quan, Nan Duan and Weizhu Chen. Joint Generator-Ranker Learning for Natural Language Generation. ACL 2023, Findings, 2023.

Ÿ Li Yang, Qifan Wang, Jingang Wang, Xiaojun Quan, Fuli Feng, Yu Chen, Madian Khabsa, Sinong Wang, Zenglin Xu and Dongfang Liu. MixPAVE: Mix-Prompt Tuning for Few-shot Product Attribute Value Extraction. ACL 2023, Findings, 2023.

Ÿ Xiaojun Quan, Siyue Wu, Junqing Chen, Weizhou Shen, and Jianxing Yu. Multi-Party Conversation Modeling for Emotion Recognition. IEEE Transactions on Affective Computing, 1-17, DOI: 10.1109/TAFFC.2023.3273589, 2023.

Ÿ Tao Yang, Jinghao Deng, Xiaojun Quan, and Qifan Wang. Orders Are Unwanted: Dynamic Deep Graph Convolutional Network for Personality Detection. AAAI 2023, to appear, 2023.

Ÿ Weizhou Shen, Xiaojun Quan, and Ke Yang. Generic Dependency Modeling for Multi-Party Conversation. ICASSP 2023, 04-10 June, 2023.

Ÿ Tao Yang, Jinghao Deng, Xiaojun Quan, Qifan Wang, Shaoliang Nie. AD-DROP: Attribution-Driven Dropout for Robust Language Model Fine-Tuning. NeurIPS 2022, to appear, 2022.

Ÿ Qifan Wang, Li Yang, Xiaojun Quan, Fuli Feng, Dongfang Liu, Zenglin Xu, Sinong Wang and Hao Ma. Learning to Generate Question by Asking Question: A Primal-Dual Approach with Uncommon Word Generation. EMNLP 2022, to appear, 2022.

Ÿ Fang Ma, Chen Zhang, Lei Ren, Jingang Wang, Qifan Wang, Wei Wu, Xiaojun Quan and Dawei Song. XPrompt: Exploring the Extreme of Prompt Tuning. EMNLP 2022, to appear, 2022.

Ÿ Guanhuang Huang, Xiaojun Quan and Qifan Wang. Autoregressive Entity Generation for End-to-End Task-Oriented Dialog. COLING 2022, to appear, 2022.

Ÿ Liqi Yan, Yiming Cui, Qifan Wang, Xiangyu Zhang, Fuli Feng, Dongfang Liu, Xiaojun Quan. GL-RG: Global-Local Representation Granularity for Video Captioning. IJCAI 2022, to appear, 2022.

Ÿ Qifan Wang, Yi Fang, Anirudh Ravula, Fuli Feng, Xiaojun Quan and Dongfang Liu. WebFormer: The Web-page Transformer for Structure Information Extraction. WWW 2022, to appear, 2022.

Ÿ Xiaojun Quan, Zhengcheng Min, Kun Li, and Yunyi Yang. Compound Aspect Extraction by Augmentation and Constituency Lattice. IEEE Transactions on Affective Computing, DOI: 10.1109/TAFFC.2022.3161683, 2022.

Ÿ Feifan Yang, Tao Yang, Xiaojun Quan and Qinliang Su. Learning to Answer Psychological Questionnaire for Personality Detection. EMNLP 2021 (Findings), pages 1131–1142, 2021.

Ÿ Weizhou Shen, Siyue Wu, Yunyi Yang and Xiaojun Quan. Directed Acyclic Graph Network for Conversational Emotion Recognition. ACL 2021, Main Conference, Pages 1551–1560, August 1–6, 2021.

Ÿ Tao Yang, Feifan Yang, Haolan Ouyang and Xiaojun Quan. Psycholinguistic Tripartite Graph Network for Personality Detection. ACL 2021, Main Conference, Pages 4229–4239, August 1–6, 2021.

Ÿ Zenan Xu, Daya Guo, Duyu Tang, Qinliang Su, Linjun Shou, Ming Gong, Wanjun Zhong, Xiaojun Quan, Daxin Jiang and Nan Duan. Syntax-Enhanced Pre-trained Model. ACL 2021, Main Conference, Pages 5412–5422, August 1–6, 2021.

Ÿ Ruikun Luo, Guanhuan Huang and Xiaojun Quan. Bi-Granularity Contrastive Learning for Post-Training in Few-Shot Scene. ACL 2021, Findings, Pages 1733–1742, August 1–6, 2021.

Ÿ Yunhao Li, Yunyi Yang, Xiaojun Quan and Jianxing Yu. Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memory. ACL 2021, Findings, Pages 447–459, August 1–6, 2021.

Ÿ Jianxing Yu; Qinliang Su; Xiaojun Quan; Jian Yin. Multi-hop Reasoning Question Generation and Its Application. IEEE Transactions on Knowledge and Data Engineering, 10.1109/TKDE.2021.3073227, 2021.

Ÿ Jiahao Wang, Minqian Liu, Xiaojun Quan. Progressive Dialogue State Tracking for Multi-Domain Dialogue Systems. ICASSP 2021, Pages 7668–7672, 2021.

Ÿ Weizhou Shen, Junqing Chen, Xiaojun Quan, Zhixian Xie. DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition. AAAI 2021, Pages 13789-13797, 2021.

Ÿ Yunyi Yang, Yunhao Li, Xiaojun Quan. UBAR: Towards Fully End-to-End Task-Oriented Dialog System with GPT-2. AAAI 2021, Pages 14230-14238, 2021.

Ÿ FeiFan Yang, Xiaojun Quan, Yunyi Yang, Jianxing Yu. Multi-Document Transformer for Personality Detection. AAAI 2021, Pages 14221-14229, 2021.