Libo Huang @ ICT, CAS

About Me LinkedIn

I am a full-time, tenure-track Assistant Professor (Assistant Researcher) at the Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS). I can solely advise Ph.D. and master's students in Computer Science. Prior to joining the faculty, I worked as a postdoctoral researcher (2021.10-2024.8) and an intern researcher (2021.7-2021.10) at ICT, CAS, where I collaborated with Prof. Yongjun Xu and Prof. Zhulin An on deep learning research.

I received my Ph.D. degree in Machine Learning under the joint supervision of Prof. Wing-Kuen Ling at Guangdong University of Technology (GDUT) (2018.09-2021.07) and Prof. Lu Gan at Brunel University of London (2019.10-2020.10). Before that, I earned my M.Eng. degree in Computer Science from GDUT (2016.09-2018.07), supervised by Prof. Zhifeng Hao and Prof. Ruichu Cai, and a B.S. degree in Mathematics from Jiangxi Normal University (2012.09-2016.07).

Research Interests Team Website

My core research focuses on Continual Learning in Open Environments, bridging the gap between fundamental mechanisms and real-world deployment to build reliable, efficient, and self-evolving AI systems. Specifically, my interests span:

Machine Cognition & Efficient Foundation Models: Investigating continual discriminative and generative learning mechanisms, and leveraging model compression techniques (e.g., knowledge distillation and quantization) for efficient representation in open scenarios.
Scene Perception & Multimodal Learning: Tackling 3D few-shot continual learning within noisy and data-scarce physical spaces (e.g., 3D Point Cloud analysis), and exploring the long-term collaborative evolution of multimodal knowledge across vision and language.
Theoretical Foundations & Causal Interpretability: Tracing the underlying mechanisms of catastrophic forgetting and exploring the causal origins of knowledge accumulation (Causal Learning) to empower AI systems with interpretable memory capabilities.

News

[2026.08] I will serve as the Meta Reviewer for MMAsia 2026.
[2026.08] 1 paper accepted to The Innovation 2026: AI for science: Progress, challenges, and perspectives.
[2026.08] 1 paper accepted to IEEE TPAMI 2026: S²Q-VDiT⁺: Accurate Quantized Video Diffusion Transformer with Multi-Resolution Sampling and Structural Distillation. Congrats Weilun!
[2026.07] 1 paper accepted to ACMMM 2026: MorphDreamer: Progressive Particle Splitting for Weighted Entropy Regularized Variational Text-to-3D Generation. Congrats Yingmei!
[2026.06] Recognized as an CVPR 2026 Outstanding Reviewer.
[2026.06] I will serve as the Area Chair for IJCNN 2027.
[2026.05] 1 paper accepted to IEEE TPAMI 2026: MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models with Temporal Distillation. Congrats Weilun!
[2026.05] 1 paper accepted to KDD 2026: PrePrompt: Predictive Prompting for Class Incremental Learning.
[2026.05] 2 papers accepted to ICML 2026: WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching, Fast-SAM3D: 3Dfy Anything in Images but Faster. Congrats Weilun, Mingqiang, and Guoxin!
[2026.04] I will serve as the Area Chair for NeurIPS 2026.
[2026.04] I will serve as the Area Chair for IEEE MLSP 2026.
[2026.03] 1 paper accepted to ICME 2026: DFM: Difference Feature Modeling with Text-Guided Gated Contrastive Loss for Remote Sensing Image Change Captioning. Congrats Yelin!
[2026.02] 4 papers accepted to CVPR 2026: (1) Representation-Steered Incremental Adapter-Tuning for Class-Incremental Learning with Pre-Trained Models, (2) EfficientVPR: Toward Efficient Visual Place Recognition via Scene-Aware Prompt Tuning and Adaptive Feature Enhancement, (3) Parameterized Prompt for Incremental Object Detection, (4) Distilling Out-of-Distribution Knowledge from Large Language Models for CLIP Generalization [findings workshop]. Congrats Jiarui, Wenjing, Zijia, and Qiji!
[2026.01] 3 papers accepted to ICLR 2026: (1) Point-UQ: An Uncertainty-Quantification Paradigm for Point Cloud Few-Shot Class Incremental Learning, (2) Quantized Visual Geometry Grounded Transformer, (3) QuantSparse: Comprehensively Compressing Video Diffusion Transformer with Model Quantization and Attention Sparsification. Congrats Xiangqi and Weilun!
[2025.12] 获中国科学院计算技术研究所2025年度“优秀研究人员”。
[2025.09] 1 paper accepted to NeurIPS 2025: S²Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation. Congrats Weilun!
[2025.07] 1 paper accepted to IEEE Transactions on Circuits and Systems for Video Technology: AF-YOLO: Asymptotic Feature Extraction and Fusion for Aerial Object Detection. Congrats Xiaowei!
[2025.06] 1 paper accepted to Scientific Data: TCMP-300: A Comprehensive Traditional Chinese Medicinal Plant Dataset for Plant Recognition.
[2025.05] 1 survey paper accepted to The Innovation as cover paper: Foundation Models and Intelligent Decision-making: Progress, Challenges, and Perspectives.
[2025.05] 2 papers accepted to ICML 2025: (1) Geometric Feature Embedding for Effective 3D Few-Shot Class Incremental Learning, (2) Q-VDiT: Towards Accurate Quantization of Video-Generation Diffusion Transformers. Congrats Xiangqi and Weilun!
[2025.04] 1 paper accepted to Pattern Recognition: Low-redundancy Distillation for Continual Learning. Congrats Ruiqi!
[2025.04] 1 paper accepted to CVPR 2025: Multi-party Collaborative Attention Control for Image Customization. Congrats Han!
[2025.01] 1 paper accepted to ISCAS 2025: Classification-Based False Alarm Suppression for SAR Target Detection. Congrats Nan!
[2024.12] 3 papers accepted to AAAI 2025 (two orals): (1) MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models, (2) Multi-Teacher Knowledge Distillation with Reinforcement Learning for Visual Recognition, (3) HSRDiff: A Hierarchical Self-Regulation Diffusion Model for Stochastic Semantic Segmentation. Congrats Chuanguang (& Xinqiang), Weilun, and Han!
[2024.12] 2 papers accepted to ICASSP 2025:(1) OLN++: Improved Object Localization Network for Open-world Object Detection, (2) IOR: Inversed Objects Replay for Incremental Object Detection. Congrats Haonan and Zijia!
[2024.09] 1 paper accepted to NeurIPS 2024: Continual Learning in the Frequency Domain. Congrats Ruiqi!
[2024.08] 1 paper accepted to Cognitive Computation: PDD: Pruning Neural Networks During Knowledge Distillation!
[2024.07] 1 paper accepted to ACMMM 2024 as oral: Relational Diffusion Distillation For Efficient Image Generation. Congrats Weilun!
[2024.05] 1 survey paper accepted to IEEE Transactions on Neural Networks and Learning Systems: A Survey on Causal Reinforcement Learning.
[2024.02] 1 paper accepted to ICLR 2024 as oral: KFC: Knowledge Reconstruction and Feedback Consolidation Enable Efficient and Effective Continual Generative Learning.
[2024.01] 2 papers accepted to CSCWD 2024: (1) Online Relational Knowledge Distillation for Image Classification, (2) Class-wise Image Mixture Guided Self-Knowledge Distillation for Image Classification.
[2023.12] 获中国科学院计算技术研究所2023年度“优秀研究人员”。
[2023.12] 获第二届粤港澳大湾区（黄埔）国际算法算例大赛“序列任务的持续学习”殿军（4/725）。
[2023.12] 1 paper accepted to AAAI 2024: eTag: Class-Incremental Learning via Embedding Distillation and Task-Oriented Generation.
[2023.12] 1 paper accepted to IEEE Transactions on Biomedical Engineering: Automatic Spike Sorting with Low-Rank and Sparse Representation.
[2021.09] 1 paper accepted to IEEE Transactions on Neural Networks and Learning Systems: Nonlinear Causal Discovery for High-Dimensional Deterministic Data.
[2021.04] 1 paper accepted to IEEE Transactions on Neural Systems and Rehabilitation Engineering: A Unified Optimization Model of Feature Extraction and Clustering for Spike Sorting.
[2020.06] 1 paper accepted to ICME 2020: Spike Sorting Based On Low-Rank And Sparse Representation.
[2019.04] 1 paper accepted to IEEE Transactions on NanoBioscience: WMsorting: Wavelet Packets' Decomposition and Mutual Information-Based Spike Sorting Method.
[2018.10] 1 paper accepted to BIBM 2018: HASS: High Accuracy Spike Sorting with Wavelet Package Decomposition and Mutual Information.

Publications Google Scholar

^# Equal contribution, * Corresponding author.

AI for science: Progress, challenges, and perspectives

Yongjun Xu^#, Zezhi Shao^#, Xin Liu^#, Yuquan Li^#, Zhulin An^#, Chenguang Fu^#, Changping Huang^#, Lin Zhang^#, Feng Gao^#, Jian Li^#, Yuyang Li^#, Fanglong Yao^#, Anquan Xia^#, Kaihua Chen^#, Xiaolong Zheng^#, Chuanguang Yang^#, Libo Huang^#, etc.

The Innovation, 2026. [JCR-Q1]

PDF

@article{xu2026ai,
  title={AI for science: Progress, challenges, and perspectives},
  author={Xu, Yongjun and Shao, Zezhi and Liu, Xin and Li, Yuquan and An, Zhulin and Fu, Chenguang and Huang, Changping and Zhang, Lin and Gao, Feng and Li, Jian and others},
  journal={The Innovation},
  year={2026},
  publisher={Elsevier}
}

S²Q-VDiT⁺: Accurate Quantized Video Diffusion Transformer with Multi-Resolution Sampling and Structural Distillation

Weilun Feng, Chuanguang Yang, Haotong Qin, Yuqi Li, Mingqiang Wu, Guoxin Fan, Xiangqi Li, Zhulin An, Libo Huang, Boyu Diao, Renshuai Tao, Fuzhen Zhuang, Michele Magno, Yongjun Xu, Zhigang Zeng, Tingwen Huang, Yingli Tian

IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2026. [CCF-A]

PDF

@article{feng2026sqvd,
  author={Feng, Weilun and Yang, Chuanguang and Qin, Haotong and Li, Yuqi and Wu, Mingqiang and Fan, Guoxin and Li, Xiangqi and An, Zhulin and Huang, Libo and Diao, Boyu and Tao, Renshuai and Zhuang, Fuzhen and Magno, Michele and Xu, Yongjun and Zeng, Zhigang and Huang, Tingwen and Tian, Yingli},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, 
  title={S$^{2}$Q-VDiT$^+$: Accurate Quantized Video Diffusion Transformer with Multi-Resolution Sampling and Structural Distillation}, 
  year={2026},
  volume={},
  number={},
  pages={1-18},
}

MorphDreamer: Progressive Particle Splitting for Weighted Entropy Regularized Variational Text-to-3D Generation

Yingmei Yu, Libo Huang*, Wentao Xu, Zhulin An*, Chuanguang Yang, Yongjun Xu

ACM International Conference on Multimedia (ACMMM), 2026. [CCF-A]

@article{feng2025mpq,
  title={Mpq-dmv2: Flexible residual mixed precision quantization for low-bit diffusion models with temporal distillation},
  author={Feng, Weilun and Yang, Chuanguang and Qin, Haotong and Li, Yuqi and Li, Xiangqi and An, Zhulin and Huang, Libo and Diao, Boyu and Zhuang, Fuzhen and Magno, Michele and others},
  journal={arXiv preprint arXiv:2507.04290},
  year={2025}
}

MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models with Temporal Distillation

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

IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2026. [CCF-A]

PDF arXiv

@article{feng2026mpq,
  title={Mpq-dmv2: Flexible residual mixed precision quantization for low-bit diffusion models with temporal distillation},
  author={Feng, Weilun and Yang, Chuanguang and Qin, Haotong and Li, Yuqi and Li, Xiangqi and An, Zhulin and Huang, Libo and Diao, Boyu and Zhuang, Fuzhen and Magno, Michele and others},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2026},
  publisher={IEEE}
}

PrePrompt: Predictive Prompting for Class Incremental Learning

Libo Huang, Xiangqi Li, Jiarui Zhao, Zhulin An*, Chuanguang Yang, Boyu Diao, Fei Wang, Yan Zeng, Zhifeng Hao, Yongjun Xu

SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2026. [CCF-A]

Project PDF arXiv Code

@inproceedings{huang2026preprompt,
  title={PrePrompt: Predictive prompting for class incremental learning},
  author={Libo Huang, Xiangqi Li, Jiarui Zhao, Zhulin An, Chuanguang Yang, Boyu Diao, Fei Wang, Yan Zeng, Zhifeng Hao, Yongjun Xu},
  booktitle={Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)},
  year={2026}
}

WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching

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

International Conference on Machine Learning (ICML), 2026. [CCF-A]

arXiv Code

@article{feng2026worldcache,
  title={WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching},
  author={Feng, Weilun and Fan, Guoxin and Qin, Haotong and Yang, Chuanguang and Wu, Mingqiang and Li, Yuqi and Li, Xiangqi and An, Zhulin and Huang, Libo and Wang, Dingrui and others},
  journal={arXiv preprint arXiv:2603.06331},
  year={2026}
}

Fast-SAM3D: 3Dfy Anything in Images but Faster

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

International Conference on Machine Learning (ICML), 2026. [CCF-A]

arXiv Code

@article{feng2026fast,
  title={Fast-SAM3D: 3Dfy Anything in Images but Faster},
  author={Feng, Weilun and Wu, Mingqiang and Chen, Zhiliang and Yang, Chuanguang and Qin, Haotong and Li, Yuqi and Liu, Xiaokun and Fan, Guoxin and An, Zhulin and Huang, Libo and others},
  journal={arXiv preprint arXiv:2602.05293},
  year={2026}
}

DFM: Difference Feature Modeling with Text-Guided Gated Contrastive Loss for Remote Sensing Image Change Captioning

Yelin Wang, Zijia Song, Chuanguang Yang, Miaoyu Wang, Zhulin An, Libo Huang, Yongjun Xu

IEEE International Conference on Multimedia & Expo (ICME), 2026.

PDF

@article{wang2026dfm,
  title={DFM: Difference Feature Modeling with Text-Guided Gated Contrastive Loss for Remote Sensing Image Change Captioning},
  author={Wang, Yelin and Song, Zijia and Yang, Chuanguang and Wang, Miaoyu and An, Zhulin and Huang, Libo and Xu, Yongjun},
  journal={arXiv preprint arXiv:2606.27410},
  year={2026}
}

Representation-Steered Incremental Adapter-Tuning for Class-Incremental Learning with Pre-Trained Models

Jiarui Zhao, Libo Huang*, Xiangqi Li, Zhulin An*, Chuanguang Yang, Yu Wang, Boyu Diao, Yongjun Xu

Conference on Computer Vision and Pattern Recognition (CVPR), 2026. [CCF-A]

PDF Code

@inproceedings{zhao2026representation,
  title={Representation-Steered Incremental Adapter-Tuning for Class-Incremental Learning with Pre-Trained Models},
  author={Zhao, Jiarui and Huang, Libo and Li, Xiangqi and An, Zhulin and Yang, Chuanguang and Wang, Yu and Diao, Boyu and Xu, Yongjun},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={18010--18020},
  year={2026}
}

EfficientVPR: Toward Efficient Visual Place Recognition via Scene-Aware Prompt Tuning and Adaptive Feature Enhancement

Wenjing Tang, Chuanguang Yang, Zhulin An, Libo Huang, Boyu Diao, Yongjun Xu

Conference on Computer Vision and Pattern Recognition (CVPR), 2026. [CCF-A]

PDF Code

@inproceedings{tang2026efficientvpr,
  title={EfficientVPR: Toward Efficient Visual Place Recognition via Scene-Aware Prompt Tuning and Adaptive Feature Enhancement},
  author={Tang, Wenjing and Yang, Chuanguang and An, Zhulin and Huang, Libo and Diao, Boyu and Xu, Yongjun},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={33738--33748},
  year={2026}
}

Parameterized Prompt for Incremental Object Detection

Zijia An, Boyu Diao, RuiQi Liu, Libo Huang, Chuanguang Yang, Fei Wang, Zhulin An, Yongjun Xu

Conference on Computer Vision and Pattern Recognition (CVPR), 2026. [CCF-A]

PDF arXiv Code

@inproceedings{an2026parameterized,
  title={Parameterized Prompt for Incremental Object Detection},
  author={An, Zijia and Diao, Boyu and Liu, Ruiqi and Huang, Libo and Yang, Chuanguang and Wang, Fei and An, Zhulin and Xu, Yongjun},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={27600--27610},
  year={2026}
}

Distilling Out-of-Distribution Knowledge from Large Language Models for CLIP Generalization

Qiji Ma, Chuanguang Yang, Zhulin An, Libo Huang, Yuqi Li, Erhu Zhao, Yongjun Xu

Conference on Computer Vision and Pattern Recognition (CVPR) findings, 2026.

PDF

@inproceedings{ma2026distilling,
  title={Distilling Out-of-Distribution Knowledge from Large Language Models for CLIP Generalization},
  author={Ma, Qiji and Yang, Chuanguang and An, Zhulin and Huang, Libo and Zhao, Erhu and Li, Yuqi and Xu, Yongjun},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={9531--9541},
  year={2026}
}

Point-UQ: An Uncertainty-Quantification Paradigm for Point Cloud Few-Shot Class Incremental Learning

Xiangqi Li, Libo Huang*, Jiarui Zhao, Weilun Feng, Chuanguang Yang, Zhulin An*, Yongjun Xu

International Conference on Learning Representations (ICLR), 2026. [CCF-A]

PDF

@article{li2025point,
    title={Point-UQ: An Uncertainty-Quantification Paradigm for Point Cloud Few-Shot Class Incremental Learning},
    author={Li, Xiangqi and Huang, Libo and Zhao, Jiarui and Feng, Weilun and Yang, Chuanguang and An, Zhulin and Xu, Yongjun},
    journal={International Conference on Learning Representations (ICLR)},
    year={2026}
}

QuantSparse: Comprehensively Compressing Video Diffusion Transformer with Model Quantization and Attention Sparsification

Weilun Feng, Chuanguang Yang, Haotong Qin, Mingqiang Wu, Yuqi Li, Xiangqi Li, Zhulin An, Libo Huang, Yulun Zhang, Michele Magno, Yongjun Xu

International Conference on Learning Representations (ICLR), 2026. [CCF-A]

PDF Code

@article{feng2025quantsparse,
    title={QuantSparse: Comprehensively Compressing Video Diffusion Transformer with Model Quantization and Attention Sparsification},
    author={Feng, Weilun and Yang, Chuanguang and Qin, Haotong and Wu, Mingqiang and Li, Yuqi and Li, Xiangqi and An, Zhulin and Huang, Libo and Zhang, Yulun and Magno, Michele and others},
    journal={arXiv preprint arXiv:2509.23681},
    year={2025}
}

Quantized Visual Geometry Grounded Transformer

Weilun Feng, Haotong Qin, Mingqiang Wu, Chuanguang Yang, Yuqi Li, Xiangqi Li, Zhulin An, Libo Huang, Yulun Zhang, Michele Magno, Yongjun Xu

International Conference on Learning Representations (ICLR), 2026. [CCF-A]

PDF Code

@article{feng2025quantized,
    title={Quantized Visual Geometry Grounded Transformer},
    author={Feng, Weilun and Qin, Haotong and Wu, Mingqiang and Yang, Chuanguang and Li, Yuqi and Li, Xiangqi and An, Zhulin and Huang, Libo and Zhang, Yulun and Magno, Michele and others},
    journal={arXiv preprint arXiv:2509.21302},
    year={2025}
}

S²Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation

Weilun Feng, Haotong Qin, Chuanguang Yang, Xiangqi Li, Han Yang, Yuqi Li, Zhulin An, Libo Huang, Michele Magno, Yongjun Xu

Annual Conference on Neural Information Processing Systems (NeurIPS), 2026. [CCF-A]

PDF Code

@article{feng2025s,
    title={S $\^{} 2$ Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation},
    author={Feng, Weilun and Qin, Haotong and Yang, Chuanguang and Li, Xiangqi and Yang, Han and Li, Yuqi and An, Zhulin and Huang, Libo and Magno, Michele and Xu, Yongjun},
    journal={arXiv preprint arXiv:2508.04016},
    year={2025}
}

Q-VDiT: Towards Accurate Quantization of Video-Generation Diffusion Transformers

Weilun Feng, Chuanguang Yang, Haotong Qin, Xiangqi Li, Yu Wang, Zhulin An, Libo Huang, Boyu Diao, Zixiang Zhao, Yongjun Xu, Michele Magno

International Conference on Machine Learning (ICML), 2025. [CCF-A]

PDF Code

@inproceedings{feng2025q,
    title={Q-VDiT: Towards Accurate Quantization and Distillation of Video-Generation Diffusion Transformers},
    author={Feng, Weilun and Yang, Chuanguang and Qin, Haotong and Li, Xiangqi and Wang, Yu and An, Zhulin and Huang, Libo and Diao, Boyu and Zhao, Zixiang and Xu, Yongjun and others},
    booktitle={International Conference on Machine Learning},
    pages={16956--16976},
    year={2025},
    organization={PMLR}
}

Geometric Feature Embedding for Effective 3D Few-Shot Class Incremental Learning

Xiangqi Li^#, Libo Huang^#, Zhulin An*, Weilun Feng, Chuanguang Yang, Boyu Diao, Fei Wang, Yongjun Xu

International Conference on Machine Learning (ICML), 2025. [CCF-A]

PDF Code

@inproceedings{li2025geometric,
    title={Geometric Feature Embedding for Effective 3D Few-Shot Class Incremental Learning},
    author={Li, Xiangqi and Huang, Libo and An, Zhulin and Feng, Weilun and Yang, Chuanguang and Diao, Boyu and Wang, Fei and Xu, Yongjun},
    booktitle={International Conference on Machine Learning},
    pages={34674--34687},
    year={2025},
    organization={PMLR}
}

Low-Redundancy Distillation for Continual Learning

Ruiqi Liu, Boyu Diao, Libo Huang, Zijia An, Hangda Liu, Zhulin An, Yongjun Xu

Pattern Recognition (PR), 2025. [JCR-Q1]

PDF Code

@article{liu2025low,
    title={Low-Redundancy Distillation for Continual Learning},
    author={Liu, Ruiqi and Diao, Boyu and Huang, Libo and An, Zijia and Liu, Hangda and An, Zhulin and Xu, Yongjun},
    journal={Pattern Recognition},
    pages={111712},
    year={2025},
    publisher={Elsevier}
}

AF-YOLO: Asymptotic Feature Extraction and Fusion for Aerial Object Detection

Lve Huang, Xiaowei Yu, Huabiao Yan, Libo Huang*, Zhulin An, Yongjun Xu

IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2025. [JCR-Q1]

PDF Code

@article{huang2026af,
    title={AF-YOLO: Asymptotic Feature Extraction and Fusion for Aerial Object Detection},
    author={Huang, Lve and Yu, Xiaowei and Yan, Huabiao and Huang, Libo and An, Zhulin and Xu, Yongjun},
    journal={IEEE Transactions on Circuits and Systems for Video Technology},
    year={2026},
    volume={36},
    number={1},
    pages={63-78},
    publisher={IEEE}
}

TCMP-300: A Comprehensive Traditional Chinese Medicinal Plant Dataset for Plant Recognition

Yanling Zhang, Wanhui Sun, Chuanguang Yang*, Libo Huang*, Zhulin An*, Weilun Feng, Wenjing Tang, Yongjun Xu

Scientific Data, 2025. [JCR-Q1]

PDF Code

@article{zhang2025tcmp,
    title={TCMP-300: A Comprehensive Traditional Chinese Medicinal Plant Dataset for Plant Recognition},
    author={Zhang, Yanling and Sun, Wanhui and Yang, Chuanguang and Huang, Libo and An, Zhulin and Feng, Weilun and Tang, Wenjing and Xu, Yongjun},
    journal={Scientific Data},
    volume={12},
    number={1},
    pages={1166},
    year={2025},
    publisher={Nature Publishing Group UK London}
}

Foundation Models and Intelligent Decision-Making: Progress, Challenges, and Perspectives

Jincai Huang^#, Yongjun Xu^#, Qi Wang^#, Qi (Cheems) Wang^#, Xingxing Liang^#, Fei Wang^#, Zhao Zhang^#, Wei Wei^#, Boxuan Zhang^#, Libo Huang^#, etc.

The Innovation, 2025. [JCR-Q1]

Cover Paper PDF

@article{HUANG2025100948,
    title = {Foundation Models and Intelligent Decision-Making: Progress, Challenges, and Perspectives},
    journal = {The Innovation},
    pages = {100948},
    year = {2025},
    issn = {2666-6758},
    author = {Jincai Huang and Yongjun Xu, etc.},
}

Classification-Based False Alarm Suppression for SAR Target Detection

Nan Yang, Libo Huang*, Zhulin An, Yongjun Xu, Xia Hong, Wing-Kuen Ling

IEEE International Symposium on Circuits and Systems (ISCAS), 2025

PDF

@inproceedings{yang2025classification,
    title={Classification-Based False Alarm Suppression for SAR Target Detection},
    author={Yang, Nan and Huang, Libo and An, Zhulin and Xu, Yongjun and Hong, Xia and Ling, Wing-Kuen},
    booktitle={2025 IEEE International Symposium on Circuits and Systems (ISCAS)},
    pages={1--5},
    year={2025},
    organization={IEEE}
}

HSRDiff: A Hierarchical Self-Regulation Diffusion Model for Stochastic Semantic Segmentation

Han Yang, Chuanguang Yang, Zhulin An, Libo Huang, Yongjun Xu

AAAI Conference on Artificial Intelligence (AAAI), 2025. [CCF-A]

PDF Code

@inproceedings{yang2025hsrdiff,
    title={HSRDiff: A Hierarchical Self-Regulation Diffusion Model for Stochastic Semantic Segmentation},
    author={Yang, Han and Yang, Chuanguang and An, Zhulin and Huang, Libo and Xu, Yongjun},
    booktitle={Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)},
    volume={39},
    number={2},
    pages={1701--1709},
    year={2025}
}

Multi-Teacher Knowledge Distillation with Reinforcement Learning for Visual Recognition

Chuanguang Yang, Xinqiang Yu, Han Yang, Zhulin An, Chengqing Yu, Libo Huang, Yongjun Xu

AAAI Conference on Artificial Intelligence (AAAI), 2025. [CCF-A]

Oral PDF Code

@inproceedings{yang2025multi,
    title={Multi-Teacher Knowledge Distillation with Reinforcement Learning for Visual Recognition},
    author={Yang, Chuanguang and Yu, Xinqiang and Yang, Han and An, Zhulin and Yu, Chengqing and Huang, Libo and Xu, Yongjun},
    booktitle={Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)},
    volume={39},
    number={9},
    pages={9148--9156},
    year={2025}
}

MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models

Weilun Feng, Haotong Qin, Chuanguang Yang, Zhulin An, Libo Huang, Boyu Diao, Fei Wang, Renshuai Tao, Yongjun Xu, Michele Magno

AAAI Conference on Artificial Intelligence (AAAI), 2025. [CCF-A]

Oral PDF Code

@inproceedings{feng2025mpq,
    title={MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models},
    author={Feng, Weilun and Qin, Haotong and Yang, Chuanguang and An, Zhulin and Huang, Libo and Diao, Boyu and Wang, Fei and Tao, Renshuai and Xu, Yongjun and Magno, Michele},
    booktitle={Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)},
    volume={39},
    number={16},
    pages={16595--16603},
    year={2025}
}

OLN++: Improved Object Localization Network for Open-world Object Detection

Haonan Mai, Libo Huang*, Zhulin An*, Jiarui Zhao, Chuanguang Yang, Erhu Zhao, Yongjun Xu

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025

PDF

@inproceedings{mai2025oln++,
    title={OLN++: Improved Object Localization Network for Open-world Object Detection},
    author={Mai, Haonan and Huang, Libo and An, Zhulin and Zhao, Jiarui and Yang, Chuanguang and Zhao, Erhu and Xu, Yongjun},
    booktitle={ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
    pages={1--5},
    year={2025},
    organization={IEEE}
}

IOR: Inversed Objects Replay for Incremental Object Detection

Zijia An, Boyu Diao, Libo Huang, Ruiqi Liu, Zhulin An, Yongjun Xu

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025

PDF Code

@inproceedings{an2025ior,
    title={IOR: Inversed Objects Replay for Incremental Object Detection},
    author={An, Zijia and Diao, Boyu and Huang, Libo and Liu, Ruiqi and An, Zhulin and Xu, Yongjun},
    booktitle={ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
    pages={1--5},
    year={2025},
    organization={IEEE}
}

Multi-party Collaborative Attention Control for Image Customization

Han Yang, Chuanguang Yang, Qiuli Wang, Zhulin An, Weilun Feng, Libo Huang, Yongjun Xu

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025. [CCF-A]

arXiv Code

@inproceedings{yang2025multi,
  title={Multi-party collaborative attention control for image customization},
  author={Yang, Han and Yang, Chuanguang and Wang, Qiuli and An, Zhulin and Feng, Weilun and Huang, Libo and Xu, Yongjun},
  booktitle={Proceedings of the Computer Vision and Pattern Recognition Conference},
  pages={7942--7951},
  year={2025}
}

PDD: pruning neural networks during knowledge distillation

Xi Dan, Wenjie Yang, Fuyan Zhang, Yihang Zhou, Zhuojun Yu, Zhen Qiu, Boyuan Zhao, Zeyu Dong, Libo Huang*, Chuanguang Yang*

Cognitive Computation, 2024. [JCR-Q1]

PDF Code

@article{dan2024pdd,
  title={Pdd: pruning neural networks during knowledge distillation},
  author={Dan, Xi and Yang, Wenjie and Zhang, Fuyan and Zhou, Yihang and Yu, Zhuojun and Qiu, Zhen and Zhao, Boyuan and Dong, Zeyu and Huang, Libo and Yang, Chuanguang},
  journal={Cognitive Computation},
  volume={16},
  number={6},
  pages={3457--3467},
  year={2024},
  publisher={Springer}
}

Continual Learning in the Frequency Domain

RuiQi Liu, Boyu Diao, Libo Huang, Zijia An, Zhulin An, Yongjun Xu

Annual Conference on Neural Information Processing Systems (NeurIPS), 2024. [CCF-A]

PDF Code

@inproceedings{liu2024continual,
    title={Continual Learning in the Frequency Domain},
    author={Liu, RuiQi and Diao, Boyu and Huang, Libo and An, Zijia and An, Zhulin and Xu, Yongjun},
    booktitle={Annual Conference on Neural Information Processing Systems (NeurIPS)},
    volume={37},
    pages={85389--85411},
    year={2024}
}

A Survey on Causal Reinforcement Learning

Yan Zeng, Ruichu Cai, Fuchun Sun, Libo Huang, Zhifeng Hao

IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS), 2024. [JCR-Q1]

PDF Code

@article{zeng2024survey,
    title={A Survey on Causal Reinforcement Learning},
    author={Zeng, Yan and Cai, Ruichu and Sun, Fuchun and Huang, Libo and Hao, Zhifeng},
    journal={IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS)},
    year={2024},
    volume={36},
    number={4},
    pages={5942-5962},
    publisher={IEEE}
}

Relational Diffusion Distillation For Efficient Image Generation

Weilun Feng, Chuanguang Yang, Zhulin An, Libo Huang, Boyu Diao, Fei Wang, Yongjun Xu

ACM International Conference on Multimedia (ACMMM), 2024. [CCF-A]

Oral PDF Code

@inproceedings{feng2024relational,
    title={Relational Diffusion Distillation For Efficient Image Generation},
    author={Feng, Weilun and Yang, Chuanguang and An, Zhulin and Huang, Libo and Diao, Boyu and Wang, Fei and Xu, Yongjun},
    booktitle={Proceedings of the 32nd ACM International Conference on Multimedia (ACMMM)},
    pages={205--213},
    year={2024}
}

Online Policy Distillation with Decision-Attention

Xinqiang Yu, Chuanguang Yang*, Chengqing Yu, Libo Huang*, Zhulin An*, Yongjun Xu

International Joint Conference on Neural Networks (IJCNN), 2024

PDF

@inproceedings{yu2024online,
    title={Online Policy Distillation with Decision-Attention},
    author={Yu, Xinqiang and Yang, Chuanguang and Yu, Chengqing and Huang, Libo and An, Zhulin and Xu, Yongjun},
    booktitle={International Joint Conference on Neural Networks (IJCNN)},
    pages={1--8},
    year={2024},
    organization={IEEE}
}

eTag: Class-Incremental Learning via Hierarchical Embedding Distillation and Task-Oriented Generation

Libo Huang, Yan Zeng, Chuanguang Yang, Zhulin An*, Boyu Diao, Yongjun Xu

AAAI Conference on Artificial Intelligence (AAAI), 2024. [CCF-A]

PDF Slides Code

@inproceedings{huang2024etag,
    title={eTag: Class-Incremental Learning via Embedding Distillation and Task-Oriented Generation},
    author={Huang, Libo and Zeng, Yan and Yang, Chuanguang and An, Zhulin and Diao, Boyu and Xu, Yongjun},
    booktitle={Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)},
    volume={38},
    number={11},
    pages={12591--12599},
    year={2024}
}

CLIP-KD: An Empirical Study of CLIP Model Distillation

Chuanguang Yang, Zhulin An, Libo Huang, Junyu Bi, Xinqiang Yu, Han Yang, Boyu Diao, Yongjun Xu

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. [CCF-A]

PDF Code

@inproceedings{yang2024clip,
    title={CLIP-KD: An Empirical Study of CLIP Model Distillation},
    author={Yang, Chuanguang and An, Zhulin and Huang, Libo and Bi, Junyu and Yu, Xinqiang and Yang, Han and Diao, Boyu and Xu, Yongjun},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    pages={15952--15962},
    year={2024}
}

KFC: Knowledge Reconstruction and Feedback Consolidation Enable Efficient and Effective Continual Generative Learning

Libo Huang, Zhulin An*, Yan Zeng, Xiang Zhi, Yongjun Xu

International Conference on Learning Representations (ICLR) Tiny Papers Track, 2024

Oral PDF Code

@inproceedings{huang2024kfc,
    title={KFC: Knowledge Reconstruction and Feedback Consolidation Enable Efficient and Effective Continual Generative Learning},
    author={Huang, Libo and An, Zhulin and Zeng, Yan and Xu, Yongjun and others},
    booktitle={International Conference on Learning Representations (ICLR) Tiny Papers Track},
    year={2024}
}

Automatical Spike Sorting with Low-Rank and Sparse Representation

Libo Huang, Lu Gan, Yan Zeng, Bingo Wing-Kuen Ling*

IEEE Transactions on Biomedical Engineering (IEEE TBE), 2023. [JCR-Q1]

PDF

@article{huang2023automatical,
    title={Automatical Spike Sorting with Low-Rank and Sparse Representation},
    author={Huang, Libo and Gan, Lu and Zeng, Yan and Ling, Bingo Wing-Kuen},
    journal={IEEE Transactions on Biomedical Engineering (IEEE TBE)},
    volume={71},
    number={5},
    pages={1677--1686},
    year={2023},
    publisher={IEEE}
}

Nonlinear Causal Discovery with Multiple High-Dimensional Observations

Yan Zeng, Zhifeng Hao, Ruichu Cai, Feng Xie, Libo Huang, Shohei Shimizu

IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS), 2021. [JCR-Q1]

PDF Code

@article{zeng2021nonlinear,
    title={Nonlinear Causal Discovery with Multiple High-Dimensional Observations},
    author={Zeng, Yan and Hao, Zhifeng and Cai, Ruichu and Xie, Feng and Huang, Libo and Shimizu, Shohei},
    journal={IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS)},
    volume={34},
    number={5},
    pages={2234--2245},
    year={2021},
    publisher={IEEE}
}

A Unified Optimization Model of Feature Extraction and Clustering for Spike Sorting

Libo Huang, Lu Gan, Bingo Wing-Kuen Ling*

IEEE Transactions on Neural Systems and Rehabilitation Engineering (IEEE TNSRE), 2021. [JCR-Q1]

PDF Code

@article{huang2021unified,
    title={A Unified Optimization Model of Feature Extraction and Clustering for Spike Sorting},
    author={Huang, Libo and Gan, Lu and Ling, Bingo Wing-Kuen},
    journal={IEEE Transactions on Neural Systems and Rehabilitation Engineering (IEEE TNSRE)},
    volume={29},
    pages={750--759},
    year={2021},
    publisher={IEEE}
}

Spike Sorting Based On Low-Rank And Sparse Representation

Libo Huang*, Bingo Wing-Kuen Ling, Yan Zeng, Lu Gan

IEEE International Conference on Multimedia and Expo (ICME), 2020

Oral PDF Slides

@inproceedings{huang2020spike,
    title={Spike Sorting Based On Low-Rank And Sparse Representation},
    author={Huang, Libo and Ling, Bingo Wing-Kuen and Zeng, Yan and Gan, Lu},
    booktitle={IEEE International Conference on Multimedia and Expo (ICME)},
    pages={1--6},
    year={2020},
    organization={IEEE}
}

基于CUDA的多信道锋电位实时分类方法

蔡瑞初, 赵坤垚*, 黄礼泊, 何炯, 陈瑶

计算机工程与设计, 2020

PDF

@article{ruicc2020cuda,
    title={基于CUDA的多信道锋电位实时分类方法},
    author={蔡瑞初, 赵坤垚, 黄礼泊, 何炯, 陈瑶},
    journal={计算机工程与设计},
    volume={41},
    number={2},
    pages={391--396},
    year={2020}
}

WMsorting: Wavelet Packets' Decomposition and Mutual Information-based Spike Sorting Method

Libo Huang, Bingo Wing-Kuen Ling*, Ruichu Cai*, Yan Zeng, Jiong He, Yao Chen

IEEE Transactions on NanoBioscience (IEEE TNB), 2019

PDF

@article{huang2019wmsorting,
    title={WMsorting: Wavelet Packets' Decomposition and Mutual Information-based Spike Sorting Method},
    author={Huang, Libo and Ling, Bingo Wing-Kuen and Cai, Ruichu and Zeng, Yan and He, Jiong and Chen, Yao},
    journal={IEEE Transactions on NanoBioscience (IEEE TNB)},
    volume={18},
    number={3},
    pages={283--295},
    year={2019},
    publisher={IEEE}
}

HASS: High Accuracy Spike Sorting with Wavelet Package Decomposition and Mutual Information

Yao Chen, Libo Huang*, Jiong He, Kunyao Zhao, Ruichu Cai, Zhifeng Hao

IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2018

Oral PDF

@inproceedings{chen2018hass,
    title={HASS: High Accuracy Spike Sorting with Wavelet Package Decomposition and Mutual Information},
    author={Chen, Yao and Huang, Libo and He, Jiong and Zhao, Kunyao and Cai, Ruichu and Hao, Zhifeng},
    booktitle={IEEE International Conference on Bioinformatics and Biomedicine (BIBM)},
    pages={831--838},
    year={2018},
    organization={IEEE}
}

Others

Services

: Outstanding Reviewer

Conference Area Chair / Meta Reviewer: MMAsia (2026), IJCNN (2027), IEEE MLSP (2026), NeurIPS (2026),
Conference Program Committee Member: AAAI (2027), BMVC (2026), ICMR (2026), WACV (2026, 2027), ICCV (2025), IJCNN (2025), ICML (2025, 2026), ICLR (2025, 2026), CVPR (2025, 2026 ), ICASSP (2025), AISTATS (2025, 2026), NeurIPS (2024, 2025), ECCV (2024, 2026), ICDM (2024, 2025, 2026), ICME (2024, 2025, 2026), ACM-MM (2023, 2024, 2025, 2026), ISCAS (2020), CSNDSP (2020), INDIN (2020),
Journal Reviewer: IJCV (2026-), PR (2026-), IEEE-TBD (2026-), IEEE-TPAMI (2025-), IEEE-TCE (2024-), IEEE-TCSVT (2023-), The Innovation (2022-), IEEE-SPL (2021-), IEEE-TIP (2020-),
Professional Service: CSIAM [中国工业与应用数学学会] (2026-), CICC [中国指挥与控制学会] (2025-), CAAI [中国人工智能学会] (2021-), IEEE (2019-), CCF [中国计算机学会] (2017-),

Students Supervision

Co-supervised with: Prof. Zhulin An, Prof. Yongjun Xu, Prof. Chuanguang Yang, and external advisors (alphabetical).

2026 Cohort: Guoxin Fan (M.S.), Jitao Lu (M.S.), Siyi Wang (M.S.),
2025 Cohort: Wenjing Tang (M.S.), Mingqiang Wu (M.S.),
2024 Cohort: Weilun Feng (Ph.D.), Xiangqi Li (M.S.), Jiachen Xie (M.S.), Wentao Xu (M.S.), Yingmei Yu (M.S.),
2023 Cohort: Chaoyi Liu (Ph.D.), Yu Wang (Ph.D.), Jiarui Zhao (Ph.D.),
Alumni
- Jindi Guo (DPTechnology [深势科技] after M.S. 2023-2026)
- Yingcheng Hu (Hong Kong University of Science and Technology (Guangzhou) [香港科技大学（广州）] after M.S. 2023-2026)
- Haonan Mai (DOBOT [越疆机器人] after M.S. 2023-2026)
- Qiji Ma ([TBD] after M.S. 2023-2026)
- Zhexin Tang (Ph.D. @ ShanghaiTech University [上海科技大学] after M.S. 2023-2026)
- Yelin Wang (Ph.D. @ Great Bay University [大湾区大学] after M.S. 2023-2026)
- Xiaowei Yu (Civil Servant @ Yantai, Shandong [山东烟台选调生] after M.S. 2023-2026)
- Han Yang (ByteDance [字节跳动] after M.S. 2022-2025)
- Nan Yang (Shanghai Customs District P.R.China [上海海关] after M.S. 2022-2025)
- Shichao Dong (Tencent [腾讯] after M.S. 2021-2024)
- Xinqiang Yu (Galbot [银河通用] after M.S. 2021-2024)
- Xiang Zhi (Umetrip [航旅纵横] after M.S. 2020-2023)
- …

Useful Link

Archived Portfolio: libohuang.google.site (2018-2021)
Collaborator (alphabetical):
- Dr. Boyu Diao (2021-)
- Dr. Yao Chen (2016-)
- Dr. Jiong He (2016-)
- Dr. Fei Wang (2021-)
- Dr. Feng Xie (2016-)
- Dr. Yan Zeng (2016-)
- …