姓名：安竹林
性别：男
邮箱：anzhulin@ict.ac.cn
学位/职称：博士/副研究员
出生年月：1980年4月
学科专业：计算机系统结构
研究方向：人工智能，重点关注面向计算机视觉的神经网络轻量化与加速、持续学习等方面。近年主持国家科学基金面上项目1项，主持省部级项目10余项。发表学术论文70余篇，其中作为通讯或者共同通讯作者发表的CCF-A类论文30余篇，授权国家发明专利20余项。
出版著作及代表性论文：
[1] Weilun Feng, Chuanguang Yang, Haotong Qin, Yuqi Li, Xiangqi Li, Zhulin An*, Libo Huang, Boyu Diao, Fuzhen Zhuang, Michele Magno, Yongjun Xu, Yingli Tian, Tingwen Huang. MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models With Temporal Distillation. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). 2026. (CCF-A)
[2] Yingmei YU, Libo Huang*, Wentao Xu, Zhulin An*, Chuanguang Yang, Yongjun Xu. MorphDreamer: Progressive Particle Splitting for Weighted Entropy Regularized Variational Text-to-3D Generation. ACM Multimedia 2026 (ACM MM), 2026. (CCF-A)
[3] Libo Huang, Xiangqi Li, Jiarui Zhao, Zhulin An*, Chuanguang Yang, Boyu Diao, Fei Wang, Yan Zeng, Zhifeng Hao, Yongjun Xu. PrePrompt: Predictive prompting for class incremental learning. 32nd SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2026. (CCF-A)
[4] Weilun Feng, Guoxin Fan, Haotong Qin, Chuanguang Yang*, Mingqiang Wu, Yuqi Li, Xiangqi Li, Zhulin An*, Libo Huang, Dingrui Wang, Longlong Liao, Michele Magno, Yongjun Xu. WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching. Forty-third International Conference on Machine Learning (ICML), 2026. (CCF-A)
[5] Weilun Feng†, Mingqiang Wu†, Zhiliang Chen, Chuanguang Yang*, Haotong Qin, Yuqi Li, Xiaokun Liu, Guoxin Fan, Zhulin An*, Libo Huang, Yulun Zhang, Michele Magno, Yongjun Xu. Fast-SAM3D: 3Dfy Anything in Images but Faster. Forty-third International Conference on Machine Learning (ICML), 2026. (CCF-A)
[6] Jiarui Zhao, Libo Huang*, Xiangqi Li, Zhulin An*, Chuanguang Yang, Yu Wang, Boyu Diao, Yongjun Xu. Representation-Steered Incremental Adapter-Tuning for Class-Incremental Learning with Pre-Trained Models. The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026. (CCF-A)
[7] Wenjing Tang, Chuanguang Yang*, Zhulin An*, Libo Huang, Boyu Diao, Yongjun Xu. EfficientVPR: Toward Efficient Visual Place Recognition via Scene-Aware Prompt Tuning and Adaptive Feature Enhancement. The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026. (CCF-A)
[8] Yingcheng Hu, Haowen Gong, Chuanguang Yang, Zhulin An*, Yongjun Xu, Songhua Liu*. MultiAnimate: Pose-Guided Image Animation Made Extensible. The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026. (CCF-A)
[9] Weilun Feng, Chuanguang Yang*, Haotong Qin, Mingqiang Wu, Yuqi Li, Xiangqi Li, Zhulin An*, Libo Huang, Yulun Zhang, Michele Magno, Yongjun Xu. QuantSparse: Comprehensively Compressing Video Diffusion Transformer with Model Quantization and Attention Sparsification. The Fourteenth International Conference on Learning Representations (ICLR), 2026. (CCF-A)
[10] Weilun Feng, Haotong Qin, Mingqiang Wu, Chuanguang Yang*, Yuqi Li, Xiangqi Li, Zhulin An*, Libo Huang, Yulun Zhang, Michele Magno, Yongjun Xu. Quantized Visual Geometry Grounded Transformer. The Fourteenth International Conference on Learning Representations (ICLR), 2026. (CCF-A)
[11] Xiangqi Li, Libo Huang*, Jiarui Zhao, Weilun Feng, Chuanguang Yang, Zhulin An*, Yongjun Xu. Point-UQ: An Uncertainty-Quantification Paradigm for Point Cloud Few-Shot Class Incremental Learning. The Fourteenth International Conference on Learning Representations (ICLR), 2026. (CCF-A)
[12] Yanling Zhang, Wanhui Sun, Chuanguang Yang, Libo Huang, Zhulin An*, Weilun Feng, Wenjing Tang, Yongjun Xu. TCMP-300: A Comprehensive Traditional Chinese Medicinal Plant Dataset for Plant Recognition. Scientific Data. 12(1):1166, 2025. (SCI Q1 IF:6.9)
[13] Weilun Feng†, Haotong Qin†, Chuanguang Yang*, Xiangqi Li, Han Yang, Yuqi Li, Zhulin An*, Libo Huang, Michele Magno, Yongjun Xu. S^2Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation. The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS), 2025. (CCF-A)
[14] Yanming Chen, Zixin Ma, Chuanguang Yang*, Zhulin An*, Yiwen Zhang. Accelerating Diffusion Models via Parallel Denoising. ACM Multimedia 2025 (ACM MM), 2025. (CCF-A)
[15] Xiangqi Li†, Libo Huang†, Zhulin An*, Weilun Feng, Chuanguang Yang, Boyu Diao, Fei Wang, Yongjun Xu. Geometric Feature Embedding for Effective 3D Few-Shot Class Incremental Learning. Forty-second International Conference on Machine Learning (ICML), 2025. (CCF-A)
[16] Weilun Feng, Chuanguang Yang*, Haotong Qin, Xiangqi Li, Yu Wang, Zhulin An*, Libo Huang, Boyu Diao, Zixiang Zhao, Yongjun Xu, Michele Magno. Q-VDiT: Towards Accurate Quantization of Video-Generation Diffusion Transformers. Forty-second International Conference on Machine Learning (ICML), 2025. (CCF-A)
[17] Han Yang, Chuanguang Yang*, Qiuli Wang, Zhulin An*, Weilun Feng, Libo Huang, Yongjun Xu. Multi-party Collaborative Attention Control for Image Customization. The Thirty-Fifth IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025. (CCF-A)
[18] Chuanguang Yang, Xinqiang Yu, Han Yang, Zhulin An*, Chengqing Yu, Libo Huang, Yongjun Xu. Multi-Teacher Knowledge Distillation with Reinforcement Learning for Visual Recognition. The 39th AAAI Conference on Artificial Intelligence (AAAI), 2025. (CCF-A)
[19] Weilun Feng†, Haotong Qin†, Chuanguang Yang*, Zhulin An*, Libo Huang, Boyu Diao, Fei Wang, Renshuai Tao, Yongjun Xu, Michele Magno. MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models. The 39th AAAI Conference on Artificial Intelligence (AAAI), 2025. (CCF-A)
[20] Han Yang, Chuanguang Yang*, Zhulin An*, Libo Huang, Yongjun Xu. HSRDiff: A Hierarchical Self-Regulation Diffusion Model for Stochastic Semantic Segmentation. The 39th AAAI Conference on Artificial Intelligence (AAAI), 2025. (CCF-A)
[21] Chuanguang Yang, Zhulin An*, Linhang Cai, and Yongjun Xu. Knowledge Distillation Using Hierarchical Self-Supervision Augmented Distribution. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 35(2), 2024. (SCI Q1 IF:10.4)
[22] Weilun Feng, Chuanguang Yang*, Zhulin An*, Libo Huang, Boyu Diao, Fei Wang, Yongjun Xu. Relational Diffusion Distillation For Efficient Image Generation. ACM Multimedia 2024 (ACM MM), 2024.(CCF-A)
[23] Yuting Zhang, Zhao Zhang, Yiqing Wu, Ying Sun, Fuzhen Zhuang*, Wenhui Yu, Lantao Hu, Han Li, Kun Gai, Zhulin An*, Yongjun Xu. Tag Tree-Guided Multi-grained Alignment for Multi-Domain Short Video Recommendation. ACM Multimedia 2024 (ACM MM), 2024.(CCF-A)
[24] Yuting Zhang, Yiqing Wu, ruidong han, Ying Sun, Yongchun Zhu, Xiang Li, Wei Lin, Fuzhen Zhuang*, Zhulin An*, Yongjun Xu. Unified Dual-Intent Translation for Joint Modeling of Search and Recommendation. 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2024. (CCF-A, ADS Track)
[25] Chuanguang Yang, Zhulin An*, Libo Huang, Junyu Bi, XinQiang Yu, Han Yang, Boyu Diao, Yongjun Xu*. CLIP-KD: A Comprehensive Study of Distilling CLIP Models. The Thirty-Fourth IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. (CCF-A)
[26] Libo Huang, Yan Zeng, Chuanguang Yang, Zhulin An*, Boyu Diao, Yongjun Xu. eTag: Class-Incremental Learning via Embedding Distillation and Task-Oriented Generation. 36th AAAI Conference on Artificial Intelligence (AAAI), 2024. (CCF-A)
[27] Chuanguang Yang, Zhulin An*, Helong Zhou, Fuzhen Zhuang, Yongjun Xu, Qian Zhang. Online Knowledge Distillation via Mutual Contrastive Learning for Visual Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 45(8), 2023. (CCF-A, SCI Q1 IF:24.314)
[28] Yuting Zhang, Ying Sun, Fuzhen Zhuang*, Yongchun Zhu, Zhulin An*, Yongjun Xu. Triple Dual Learning for Opinion-Based Explainable Recommendation. ACM Transactions on Information Systems (TOIS), 42(3), 2023. (CCF-A, SCI Q1 IF:5.6)
[29] Yuting Zhang, Yiqing Wu, Ran Le, Yongchun Zhu, Fuzhen Zhuang*, Ruidong Han, Xiang Li, Wei Lin, Zhulin An*, Yongjun Xu. Modeling Dual Period-Varying Preferences for Takeaway Recommendation. 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2023. (CCF-A, ADS Track)
[30] Zhao Zhang, Zhanpeng Guan, Fuwei Zhang, Fuzhen Zhuang*, Zhulin An*, Fei Wang, Yongjun Xu. Weighted Knowledge Graph Embedding. 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2023. (CCF-A)
[31] Chuanguang Yang, Helong Zhou, Zhulin An*, Xue Jiang, Yongjun Xu, Qian Zhang. Cross-Image Relational Knowledge Distillation for Semantic Segmentation. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022. (CCF-A)
[32] Chuanguang Yang, Zhulin An*, Linhang Cai, Yongjun Xu. Mutual Contrastive Learning for Visual Representation Learning. 36th AAAI Conference on Artificial Intelligence (AAAI), 2022. (CCF-A)
[33] Linhang Cai, Zhulin An*, Chuanguang Yang, Yangchun Yan, Yongjun Xu. Prior Gradient Mask Guided Pruning-aware Fine-tuning. 36th AAAI Conference on Artificial Intelligence (AAAI), 2022. (CCF-A)
[34] Chuanguang Yang, Zhulin An*, Linhang Cai, Yongjun Xu. Hierarchical Self-supervised Augmented Knowledge Distillation. 30th International Joint Conference on Artificial Intelligence (IJCAI), 2021. (CCF-A)
[35] Chuanguang Yang, Zhulin An*, Hui Zhu, Xiaolong Hu, Kun Zhang, Kaiqiang Xu, Chao Li, Yongjun Xu. Gated Convolutional Networks with Hybrid Connectivity for Image Classification. 34th AAAI Conference on Artificial Intelligence (AAAI), 2020. (CCF-A)
主持及参与的科研项目：
[1]基于知识蒸馏的扩散模型训练和推理优化方法研究，国家自然科学基金，面上项目，主持，2025。
科研成果（获奖、专利等）：
[1] 跨时空多源数据挖掘与态势认知关键技术及应用，中国指挥与控制学会科学技术进步奖(技术发明类)，一等奖，2025，排名3
[2] CN202411828017.6，基于混合精度量化的扩散模型极低比特量化方法及装置，安竹林;冯伟伦;杨传广;黄礼泊;徐勇军
[3] CN202310174287.9，基于多模型联合对比学习的图像分类方法及系统，杨传广;安竹林;于新强;徐勇军
[4] CN202310773530.9，一种基于变分自编码器生成重放的增量学习方法，安竹林; 黄礼泊; 支相; 徐勇军
[5] CN202010937149.8，一种基于局部关系指导的图像分割方法，安竹林; 许开强; 程坦; 徐勇军
[6] CN202010162181.3，一种深度神经网络的可解释生成方法，安竹林; 胡小龙; 程坦; 徐勇军
[7] CN202010059647.7，一种相似特征测试数据集生成方法，安竹林; 孙涛; 程坦; 徐勇军
[8] CN202010937140.7，一种基于增强特征表示的图像分割方法，安竹林; 许开强; 程坦; 徐勇军
[9] CN202110918571.3，一种多特征融合计算识别胶质瘤复发与坏死的方法，蔡小红; 张勤; 安竹林
[10] CN202110598353.6，一种实体标准化方法，曾志贤; 马涛; 倪斌; 汪姿如; 庄福振; 安竹林
[11] CN202011186817.4，一种基于主动学习的样本标注方法，陈能; 安竹林; 徐勇军; 程坦
[12] CN202110623005.X，一种基于视频的行人垃圾扔投次数统计方法，何森勖; 程坦; 徐勇军; 安竹林
[13] CN202011086121.4，一种多图片集曝光分布差异的衡量方法，何森勖; 程坦; 徐勇军; 安竹林
[14]CN202011182517.9，一种基于结构光摄像头的3D人脸识别方法，胡雨; 安竹林; 张章斌; 徐勇军; 程坦
[15] CN202011099237.1，一种基于BERT与先验知识特征的关系五元组抽取方法，马涛; 倪斌; 童逸琦; 汪姿如; 庄福振; 安竹林; 等
[16] CN202011182518.3，一种融合知识的对话生成方法，倪斌; 庄福振; 安竹林; 程坦; 徐勇军; 陆晓蕾; 马涛; 童逸琦
[17] CN202011186818.9，一种基于元学习的领域增量方法，王杰龙; 安竹林; 程坦; 徐勇军
[18] CN202110521364.4，一种基于数据转换和知识蒸馏的域增量学习方法，王杰龙; 安竹林; 程坦; 徐勇军
[19] CN202110571011.5，一种在方舱类建筑中生成动线规划的方法，余孟达; 安竹林
[20] CN202010186717.5，一种基于不同粒度特征匹配一致性的物体重识别方法，钟剑斌; 安竹林; 程坦; 徐勇军
[21] CN202011182514.5，一种乳腺钼靶图像中胸肌和乳头区域的分割预标注方法，钟剑斌; 徐勇军; 程坦; 安竹林
[22] CN202111157928.7，一种基于运动增强特征的水流测速方法，钟剑斌; 徐勇军; 程坦; 安竹林
