姓名：徐华

职称：长聘副教授，博士生导师

电话：13810102923

邮件：xuhua@mail.tsinghua.edu.cn

教育背景

学士(计算机科学与技术),西安交通大学,中国,1998

硕士(计算机应用技术),清华大学,中国,2000

博士(计算机应用技术),清华大学,中国,2003

研究领域

多模态智能信息处理，智能优化

研究概况

长期从事多模态智能信息处理、共融机器人智能控制等,研究方向是人工智能领域的智能优化调度和人机自然交互，在北京的国家信息科学与技术研究中心等研究平台上开展研究。近年来，完成国家科技重大专项课题3项、国家自然科学基金项目4项、国家973项目课题2项、国家863项目课题5项以及国际500强企业合作项目13项。曾受邀担任工业和信息化部重大科技项目03号的核心专家，担任“技术支撑经济2020”国家重点研发计划项目验收专家组组长，国家发展和改革委员会国家工业创新中心的咨询专家，Elsevier国际期刊Intell. Syst. Appl.的主编和Expert Syst. Appl.的副主编（第一四分位，SCI影响因子=8.665）。曾获国家科技进步二等奖，北京市科学技术一等奖，行业协会科技一等奖2次，省部级二、三等奖3次。获国家发明专利36项，软件著作权26项，著作3部教材、6部专著。贡献被引用于ACM Comput. Surv等顶级期刊，被国内外6位学院士和30多位IEEE院士引用。在机器人智能优化调度方面，提出了面向多目标优化调度的智能演化理论和多机器人协作的柔性作业车间调度(FJS)方法技术；机器人自然交互方面，研究并建立面向自然交互的情感分析与意图理解方法和开源平台，成为当前机器人智能系统领域进行交互情感感知和对话意图理解的有效方法。

成果链接

1) 研究组主页：https://thuiar.github.io/

2) 成果共享网址：https://github.com/thuiar

奖励与荣誉

中国人工智能学会 科技进步三等奖 （2025）

中国仿真学会科学技术将 自然科学二等奖(2023)

中国物流与采购联合会科技发明奖 一等奖(2015)

北京市科学技术奖 二等奖(2014)

北京市科学技术奖 三等奖(2014)

中国物流与采购联合会科技进步奖 一等奖(2013)

重庆市科学技术奖 三等奖(2011)

PAKDD 2011最佳论文奖(2011)

国家科学技术进步奖 二等奖(2009)

北京市科学技术奖 一等奖(2008)

学术成果

Multimodal Emotion Analysis

[1] Ziqi Yuan, Jingliang Fang, Hua Xu, Kai Gao, Multimodal Consistency-Based Teacher for Semi-Supervised Multimodal Sentiment Analysis[J]. IEEE/ACM Transactions on Audio Speech and Language Processing, 32, 3669–3683,2024.

[2] Baozheng Zhang, Ziqi Yuan, Hua Xu, Kai Gao, Crossmodal Translation Based Meta Weight Adaption for Robust Image-Text Sentiment Analysis[J]. IEEE Transactions on Multimedia, 26, 9949-9961, 2024.

[3] Ziqi Yuan, Baozheng Zhang, Hua Xu, Kai Gao, Meta Noise Adaption Framework for Multimodal Sentiment Analysis with Feature Noise[J]. IEEE Transactions on Multimedia, 26,7265-7277, 2024.

[4] Ziqi Yuan, Baozheng Zhang, Hua Xu, Zhiyun Liang, Kai Gao, OpenVNA: A Framework for Analyzing the Behavior of Multimodal Language Understanding System under Noisy Scenarios[C]//Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. 2024: 9-18, August 11th – 16th, Thailand.

[5] Ziqi Yuan, Yihe Liu, Hua Xu, Kai Gao, Noise Imitation based Adversarial Training for Robust Multimodal Sentiment Analysis[J]. IEEE Transactions on Multimedia, 26, 529-539, 2023.

[6] Huisheng Mao ，Baozheng Zhang, Hua Xu, Ziqi Yuan, Yihe Liu, Robust-MSA: Understanding the impact of modality noise on multimodal sentiment analysis[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2023, 37: 16458-16460, February 7th-14th, Washington DC, USA.

[7] Huisheng Mao, Ziqi Yuan, Hua Xu, Wenmeng Yu, Yihe Liu, Kai Gao, M-SENA: An integrated platform for multimodal sentiment analysis[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations. 2022: 204-213, May 22th-27th, Dublin.

[8] Yihe Liu, Ziqi Yuan, Huisheng Mao, Zhiyun Liang, Wanqiuyue Yang, Yuanzhe Qiu, Tie Cheng, Xiaoteng Li, Hua Xu, Kai Gao, Make acoustic and visual cues matter: Ch-sims v2. 0 dataset and av-mixup consistent module[C]//Proceedings of the 2022 international conference on multimodal interaction. 2022: 247-258, August 22, Bengaluru, India.

[9] Wenmeng Yu, Hua Xu, Co-Attentive Multi-Task Convolutional Neural Network for Facial Expression Recognition[J]. Pattern Recognition, 123, 108401, 2022.

[10] Ziqi Yuan,Wei Li, Hua Xu, Wenmeng Yu. Transformer-based Feature Reconstruction Network for Robust Multimodal Sentiment Analysis[C]//Proceedings of the 29th ACM international conference on multimedia. 2021: 4400-4407, October 20th-24th, Chengdu, China.

[11] Hua Xu, Ziqi Yuan, Kang Zhao, Yunfeng Xu, Jiyun Zou, Kai Gao, GAR-Net: A Graph Attention Reasoning Network for Conversation understanding[J]. Knowledge-Based Systems, 240, 108055, 2022.

[12] Wenmeng Yu, Hua Xu, Ziqi Yuan, Jiele Wu, Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis[C]//Proceedings of the AAAI conference on artificial intelligence. 2021, 35: 10790-10797, February 02th, Virtual.

[13] Kaicheng Yang, Hua Xu, Kai Gao. CM-BERT: Cross-Modal BERT for Text-Audio Sentiment Analysis[C]//Proceedings of the 28th ACM international conference on multimedia. 2020: 521-528, October 12th-16th, Seattle, USA.

[14] Wenmeng Yu, Hua Xu, Fanyang Meng, Yilin Zhu, Yixiao Ma, Jiele Wu, Jiyun Zou, Kaicheng Yang. CH-SIMS: A Chinese Multimodal Sentiment Analysis Dataset with Fine-grained Annotations of Modality [C]//Proceedings of the 58th annual meeting of the association for computational linguistics. 2020: 3718-3727, July 5th-10th, Seattle, USA.

[15] Yunfeng Xu, Hua Xu, Jiyun Zou. HGFM: A Hierarchical Grained and Feature Model for Acoustic Emotion Recognition [C]//ICASSP 2020-2020 IEEE international conference on acoustics, speech and signal processing. 2020: 6499-6503, May 4th - 8th, Barcelona, Spain.

[16] Huadong Li, Hua Xu, Deep Reinforcement Learning for Robust Emotional Classification in Facial Expression Recognition[J]. Knowledge-Based Systems, 204, 106172, 2020.

[17] Xili Wang, Hua Xu, Xiaomin Sun and Guangcan Tao, Combining Fine-Tuning with a Feature-Based Approach for Aspect Extraction on Reviews [C]//Proceedings of the AAAI conference on artificial intelligence. 2020, 34: 13951-13952, February 7th - 12th, New York, USA.

[18] Yu Cao, Hua Xu, SATNet: Symmetric Adversarial Transfer Network Based on Two-Level Alignment Strategy towards Cross-Domain Sentiment Classification[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2020, 34(10): 13763-13764, February 7th - 12th, New York, USA.

Multimodal Intent Understanding

[1] Qianrui Zhou, Hua Xu, Yunjin Gu, Yifan Wang, Songze Li, Hanlei Zhang, Evolutionary Multimodal Reasoning via Hierarchical Semantic Representation for Intent Recognition[C]. IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2026.

[2] Yuetian Zou, Hanlei Zhang, Hua Xu, Songze Li, Long Xiao, Ellipsoid-Based Decision Boundaries for Open Intent Classification [C]//Proceedings of the AAAI conference on artificial intelligence. 2026, January 20th -27th, Singapore.

[3] Hanlei Zhang, Zhuohang Li, Yeshuang Zhu, Hua Xu, Peiwu Wang, Haige Zhu, Jie Zhou, Jinchao Zhang, Can Large Language Models Help Multimodal Language Analysis? MMLA: A Comprehensive Benchmark[C]//The Thirty-ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track. 2025, December 2th – 7th, U.S.A.

[4] Qianrui Zhou, Hua Xu, Yifan Wang, Xinzhi Dong, Hanlei Zhang, LLM-Guided Semantic Relational Reasoning for Multimodal Intent Recognition[C]//Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025: 22221-22237, November 5th - 9th, Suzhou, China.

[5] Hanlei Zhang, Qianrui Zhou, Hua Xu, Jianhua Su, Roberto Evans, Kai Gao, Multimodal Classification and Out-of-Distribution Detection for Multimodal Intent Understanding[J]. IEEE Transactions on Multimedia, 27, 9887–9901, 2025.

[6] Xiaohan Zhang, Runmin Cao, Yifan Wang, Songze Li, Hua Xu, Kai Gao, Lunsong Huang, A unified Prompt-based Framework for Few-shot Multimodal Language Analysis[J]. Intelligent Systems with Applications, 26, 200498,2025.

[7] Hanlei Zhang, Hua Xu, Xin Wang, Fei Long, Kai Gao, A Clustering Framework for Unsupervised and Semi-supervised New Intent Discovery[J]. IEEE Transactions on Knowledge and Data Engineering, 36, 5468-5481, 2024.

[8] Hanlei Zhang, Hua Xu, Fei Long, Xin Wang, Kai Gao, Unsupervised Multimodal Clustering for Semantics Discovery in Multimodal utterances[C]//Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. 2024: 18-35, August 11th – 16th, Thailand.

[9] Hanlei Zhang, Xin Wang, Hua Xu, Qianrui Zhou, Kai Gao, MIntRec2. 0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations[C]//The Twelfth International Conference on Learning Representations. 2024, May 7th-11th, Vienna Austria.

[10] Qianrui Zhou, Hua Xu, Hao Li, Hanlei Zhang, Xiaohan Zhang, Token-level contrastive learning with modality-aware prompting for multimodal intent recognition[C]//Proceedings of the AAAI conference on artificial intelligence. 2024, 38: 17114-17122, February 20 - 27, Vancouver, Canada.

[11] Hanlei Zhang, Hua Xu, Shaojie Zhao, Qianrui Zhou, Learning discriminative representations and decision boundaries for open intent detection[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 31, 1611-1623, 2023.

[12] Hanlei Zhang, Hua Xu, Xin Wang, Qianrui Zhou, Shaojie Zhao, Jiayan Teng, Mintrec: A new Dataset for Multimodal Intent Recognition[C]//Proceedings of the 30th ACM international conference on multimedia. 2022: 1688-1697, October 10 - 14, Lisbon, Portugal.

[13] Hanlei Zhang, Xiaoteng Li, Hua Xu, Panpan Zhang, Kang Zhao, Kai Gao, TEXTOIR: An Integrated and Visualized Platform for Text Open Intent Recognition [C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations. 2021: 167-174, August 1th - 6th, Virtual.

[14] Hanlei Zhang, HuaXu, Ting-En Lin and Rui Lv, Discovering New Intents with Deep Aligned Clustering [C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2021, 35: 14365-14373, February 02th, Virtual.

[15] Hanlei Zhang, Hua Xu, Ting-En Lin, Deep Open Intent Classification with Adaptive Decision Boundary[C]//Proceedings of the AAAI conference on artificial intelligence. 2021, 35: 14374-14382, February 02th, Virtual.

[16] Ting-En Lin, Hua Xu, Hanlei Zhang, Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinement [C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2020, 34: 8360-8367, February 7th-12th, 2020，New York, USA.

[17] Ting-En Lin, Hua Xu, Hanlei Zhang, Constrained Self-supervised Clustering for Discovering New Intents[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2020, 34: 13863-13864, February 7th - 12th, New York, USA.

Reading Comprehension Related to Question Answering

[1] Songze Li, Zhijing Wu, Runmin Cao, Xiaohan Zhang, Yifan Wang, Hua Xu, Kai Gao, Learning how to transfer: A lifelong Domain Knowledge Distillation Framework for Continual MRC[J]. Intelligent Systems with Applications, 26, 200497,2025.

[2] Jingliang Fang, Hua Xu, Zhijing Wu, Kai Gao, Xiaoyin Che,Haotian Hui. Robustness-Eva-MRC: Assessing and Analyzing the Robustness of Neural Models in Extractive Machine Reading Comprehension[J]. Intelligent Systems with Applications, 20, 200287, 2023.

[3] Zhijing Wu, Hua Xu, Trustworthy machine reading comprehension with conditional adversarial calibration[J]. Applied Intelligence, 53, 14298-14315, 2023.

[4] Zhijing Wu，Jingliang Fang ，Hua Xu ，Kai Gao, An In-depth Interactive and Visualized Platform for Evaluating and Analyzing MRC Models[C]//Proceedings of the 31st ACM International Conference on Information & Knowledge Management. 2022: 5044-5048, October 17-21，Atlanta, USA.

[5] Zhijing Wu ，Hua Xu，Jingliang Fang , Continual Machine Reading Comprehension via Uncertainty-aware Fixed Memory and Adversarial Domain Adaptation[C]//Findings of the Association for Computational Linguistics: NAACL 2022. 2022: 2330-2339, July 10th –15th，Seattle, Washington.

[6] Zhijing Wu, Hua Xu, Improving the Robustness of Machine Reading Comprehension Model with Hierarchical Knowledge and Auxiliary Unanswerability Prediction[J]. Knowledge-Based Systems, 203, 106075, 2020.

[7] Zhijing Wu, Hua Xua, A Multi-Task Learning Machine Reading Comprehension Model for Noisy Document[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2020, 34: 13963-13964, February 7th - 12th, New York, USA.

Entity Recognition and Relation Extraction for Interactive Information

[1] Kang Zhao, Hua Xu, Jiangong Yang, Kai Gao, Consistent Representation Learning for Continual Relation Extraction [C]//Findings of the association for computational linguistics: ACL 2022. 2022: 3402-3411, May 22th - 27th, Dublin.

[2] Kang Zhao, Hua Xu, Yue Cheng, Xiaoteng Li, Kai Gao, Representation Iterative Fusion Based on Heterogeneous Graph Neural Network for Joint Entity and Relation Extraction[J]. Knowledge-Based Systems, 219, 106888, 2021.

[3] Yuxiang Xie, Hua Xu, Jiaoe Li, Congcong Yang, Kai Gao, Heterogeneous Graph Neural Networks for Noisy Few-Shot Relation Classification[J]. Knowledge-Based Systems, 194, 105548, 2020.

[4] Yuxiang Xie, Hua Xu, Congcong Yang, Kai Gao, Multi-Channel Convolutional Neural Networks with Adversarial Training for Few-Shot Relation Classification[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2020, 34: 13967-13968, February 7th - 12th, New York, USA.

Fast Large-Scale Optimization Algorithms

[1] Zhixiao Xiong, Huigen Ye, Hua Xu, Carlos A. Coello Coello: HEQP: A Hypergraph Neural Network-Based Evolutionary Method for Large-Scale QCQPs[J]. IEEE Transactions on Cybernetics. 2026.

[2] Huigen Ye, Hua Xu, Carlos A. Coello Coello: Light-EvoOPT: A Lightweight Evolutionary Optimization Framework for Ultra-Large-Scale Mixed Integer Linear Programs[J]. IEEE Transactions on Evolutionary Computation, 30, 333-347,2026

[3] Hua Xu, Xiaodong Li, Sun Yuan, Intelligent Evolution Optimization: Guided fromDeep Learning to Large Language Model[C]//Proceedings of the Genetic and Evolutionary Computation Conference. 2025, July 14th – 18th, Spain.

[4] Huigen Ye, Hua Xu, An Yan, Large Language Model-driven Large Neighborhood Searchfor Large-Scale MlLP Problems[C]//Forty-second International Conference on MachineLearning. 2025, July 13th – 19th, Canada.

[5] Huigen Ye, Yaoyang Cheng, Hua Xu, Zhiguang Cao, Hanzhang Qin, MILPBench: A Large-scale Benchmark Test Suite for Mixed Integer Linear Programming Problems[C]//Proceedings of the Genetic and Evolutionary Computation Conference. 2025: 94-103, July 14th - 18th, Málaga.

[6] Tianxing Yang, Huigen Ye, Hua Xu, Learning to generate scalable milp instances[C]//Proceedings of the Genetic and Evolutionary Computation Conference Companion. 2024: 159-162, July 14th - 18th, Melbourne VIC Australia.

[7] Huigen Ye, Hua Xu, Hongyan Wang, Light-MILPopt: Solving Large-scale Mixed Integer Linear Programs with Lightweight Optimizer and Small-scale Taining Dataset[C]//The Twelfth International Conference on Learning Representations. 2024, May 7th-11th, Vienna Austria.

[8] Huigen Ye, Hua Xu, Hongyan Wang, Chengming Wang, Yu Jiang, GNN&GBDT-guided fast optimizing framework for large-scale integer programming[C]// International Conference on MachineLearning. 2023, July 23th - 29th, Honolulu, Hawaii.

[9] Huigen Ye, Hongyan Wang, Hua Xu, Chengming Wang, Yu Jiang, Adaptive Constraint Partition based Optimization Framework for Large-scale Integer Linear Programming[C]//Proceedings of the AAAI conference on artificial intelligence. 2023, February 7th-14th, Washington DC, USA.

[10] Li Chen, Hua Xu, Ziteng Wang, Chengming Wangand Yu Jiang, Self-paced learning based graph convolutional neural network for mixed integer programming [C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2023, 37: 16188-16189, February 7th - 14th, 2023 Washington DC, USA.

[11] Li Chen, Hua Xu, MFENAS: Multifactorial Evolution for Neural Architecture Search[C]//Proceedings of the Genetic and Evolutionary Computation Conference Companion. 2022: 631-634, July 9th-13th, Boston, MA, USA.

[12] Li Chen, Hua Xu, CORAL-DMOEA: Correlation Alignment-based Information Transfer for Dynamic Multi-objective Optimization [C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2020, 34: 13765-13766, February 7th - 12th, New York, USA.

Bayesian Optimization

[1] Hongyan Wang, Hua Xu, Zeqiu Zhang, High-dimensional Multi-objective Bayesian Optimization with Block Coordinate Updates[J]. IEEE Transactions on Intelligent Transportation Systems, 25, 884-895, 2022.

[2] Hongyan Wang, Hua Xu, Yuan Yuan, Zeqiu Zhang, An Adaptive Batch Bayesian Optimization Approach for Expensive Multi-Objective Optimization problems[J]. Information Sciences, 611, 446-463, 2022.

[3] Wang Hongyan, Hua Xu, Yuan Yuan, High-dimensional Expensive Multi-objective Optimization via Additive Structure[J]. Intelligent Systems with Applications, 14, 200062, 2022.

Smart healthcare

[1] Huilin Liu, Runmin Cao, Songze Li, Yifan Wang, Xiaohan Zhang, Hua Xu, ViT-Based Face Diagnosis Images Analysis for Schizophrenia Detection[J]. Brain Sci, 15, 30, 2024.

[2] Hua Xu, Xiaofei Chen, Peng Qian, Fufeng Li, A Two-stage Segmentation of Sublingual Veins Based on Compact Fully Convolutional Networks for Traditional Chinese Medicine Images[J]. Health Information Science and Systems, 11, 19, 2023.

[3] Xiaofei Chen, Hua Xu, Peng Qian, Yunfeng Xu, Fufeng Li, Shengwang Li, Multi-kernel convolutional neural network for wrist pulse signal classification[C]//2022 32nd Conference of Open Innovations Association. 2022: 75-86, November 9th – 11th, Helsinki, Finland.

[4] Huisheng Mao, Baozheng Zhang, Hua Xu, Kai Gao, An End-to-End Traditional Chinese Medicine Constitution Assessment System Based on Multimodal Clinical Feature Representation and Fusion[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2022, 36: 13200-13202, February 22, Vancouver, Canada.