Publications

2026

1. CVPR

   

   On Token’s Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models

   Chongyang Zhao, Mingsong Li, Haodong Lu, and Dong Gong

   IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

   arXiv HTML Code Website
2. CVPR

   

   Let Your Image Move with Your Motion! – Implicit Multi-Object Multi-Motion Transfer

   Yuze Li, Dong Gong, Xiao Cao, Junchao Yuan, Dongsheng Li, Lei Zhou, Yun Sing Koh, Cheng Yan, and Xinyu Zhang

   IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

   arXiv HTML Code Website
3. CVPR

   

   Hierarchical Point-Patch Fusion with Adaptive Patch Codebook for 3D Shape Anomaly Detection

   Xueyang Kang, Zizhao Li, Tian Lan, Dong Gong, Kourosh Khoshelham, and Liangliang Nan

   IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

   Code
4. ICLR

   

   I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?

   Yuhang Liu, Dong Gong, Yichao Cai, Erdun Gao, Zhen Zhang, Biwei Huang, Mingming Gong, Anton van den Hengel, and Javen Qinfeng Shi

   International Conference on Learning Representations (ICLR), 2026

   arXiv HTML
5. ICLR

   

   Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning

   Yuhang Liu, Zhen Zhang, Dong Gong, Erdun Gao, Biwei Huang, Mingming Gong, Anton van den Hengel, Kun Zhang, and Javen Qinfeng Shi

   International Conference on Learning Representations (ICLR), 2026

   arXiv HTML
6. JMLR

   

   Identifying Weight-Variant Latent Causal Models

   Yuhang Liu, Zhen Zhang, Dong Gong, Mingming Gong, Biwei Huang, Anton van den Hengel, Kun Zhang, and Javen Qinfeng Shi

   Journal of Machine Learning Research (JMLR), 2026

   arXiv HTML Code
7. AAAI

   

   Socrates or Smartypants: Testing Logic Reasoning Capabilities of Large Language Models with Logic Programming-Based Test Oracles

   Zihao Xu, Junchen Ding, Yiling Lou, Kun Zhang, Dong Gong, and Yuekang Li

   AAAI Conference on Artificial Intelligence (AAAI), 2026

   arXiv HTML
8. arXiv

   

   HyperAlign: Hypernetwork for Efficient Test-Time Alignment of Diffusion Models

   Xin Xie, Jiaxian Guo, and Dong Gong

   arXiv preprint arXiv:2601.15968, 2026

   arXiv HTML Website
9. arXiv

   

   Concept Component Analysis: A Principled Approach for Concept Extraction in LLMs

   Yuhang Liu, Erdun Gao, Dong Gong, Anton van den Hengel, and Javen Qinfeng Shi

   arXiv preprint arXiv:2601.20420, 2026

   arXiv HTML
10. arXiv

    

    Adaptive Rank, Reduced Forgetting: Continual Learning with Dynamic Rank-Selective LoRA

    Haodong Lu, Chongyang Zhao, Jason Xue, Lina Yao, Kristen Moore, and Dong Gong

    arXiv preprint arXiv:2412.01004, 2026

    arXiv HTML Code
11. arXiv

    

    Little by Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts

    Haodong Lu, Chongyang Zhao, Jason Xue, Lina Yao, Kristen Moore, and Dong Gong

    arXiv preprint arXiv:2506.21035, 2026

    arXiv HTML

2025

1. CVPR

   

   DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling

   Xin Xie and Dong Gong

   IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

   arXiv HTML Code Website
2. CVPR

   

   Self-Expansion of Pre-Trained Models with Mixture of Adapters for Continual Learning

   Huiyi Wang, Haodong Lu, Lina Yao, and Dong Gong

   IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

   arXiv HTML Code
3. CVPR

   

   D^ 3CTTA: Domain-Dependent Decorrelation for Continual Test-Time Adaption of 3D LiDAR Segmentation

   Jichun Zhao, Haiyong Jiang, Haoxuan Song, Jun Xiao, and Dong Gong

   IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

   HTML
4. NeurIPS

   

   Model Inversion with Layer-Specific Modeling and Alignment for Data-Free Continual Learning

   Ruilin Tong, Haodong Lu, Yuhang Liu, and Dong Gong

   Advances in Neural Information Processing Systems (NeurIPS), 2025

   arXiv HTML Code
5. NeurIPS

   

   FlashMo: Geometric Interpolants and Frequency-Aware Sparsity for Scalable Efficient Motion Generation

   Zeyu Zhang, Yiran Wang, Danning Li, Dong Gong, Ian Reid, and Richard Hartley

   Advances in Neural Information Processing Systems (NeurIPS), 2025

   arXiv HTML Website
6. ICLR

   

   Coreset Selection via Reducible Loss in Continual Learning

   Ruilin Tong, Yuhang Liu, Javen Qinfeng Shi, and Dong Gong

   International Conference on Learning Representations (ICLR), 2025

   HTML Code
7. ICLR

   

   Analytic DAG Constraints for Differentiable DAG Learning

   Zhen Zhang, Ignavier Ng, Dong Gong, Yuhang Liu, Mingming Gong, Biwei Huang, Kun Zhang, Anton van den Hengel, and Javen Qinfeng Shi

   International Conference on Learning Representations (ICLR), 2025

   arXiv HTML
8. ICLR

   

   Mining Your Own Secrets: Diffusion Classifier Scores for Continual Personalization of Text-to-Image Diffusion Models

   Saurav Jha, Shiqi Yang, Masato Ishii, Mengjie Zhao, Christian Simon, Muhammad Jehanzeb Mirza, Dong Gong, Lina Yao, Shusuke Takahashi, and Yuki Mitsufuji

   International Conference on Learning Representations (ICLR), 2025

   arXiv HTML
9. ACM MM

   

   Let Your Video Listen to Your Music!–Beat-Aligned, Content-Preserving Video Editing with Arbitrary Music

   Xinyu Zhang, Dong Gong, Zicheng Duan, Anton van den Hengel, and Lingqiao Liu

   ACM International Conference on Multimedia (ACM MM), 2025

   arXiv HTML
10. WWW

    

    Balancing Plasticity and Stability via Dual-Branch Learning in Online Continual Learning

    Xu Han^*, Haodong Lu^*, Huiyi Wang, and Dong Gong

    ACM The Web Conference (WWW), 2025

    HTML
11. IJCAI

    

    Seeing the Unseen: Composing Outliers for Compositional Zero-Shot Learning

    Chenchen Jing, Mingyu Liu, Hao Chen, Yuling Xi, Xingyuan Bu, Dong Gong, and Chunhua Shen

    International Joint Conference on Artificial Intelligence (IJCAI), 2025

    HTML
12. TMLR

    

    Continual Learning on CLIP via Incremental Prompt Tuning with Intrinsic Textual Anchors

    Haodong Lu, Xinyu Zhang, Kristen Moore, Jason Xue, Lina Yao, Anton van den Hengel, and Dong Gong

    Transactions on Machine Learning Research (TMLR), 2025

    arXiv HTML Code
13. TMLR

    

    Latent Covariate Shift: Unlocking Partial Identifiability for Multi-Source Domain Adaptation

    Yuhang Liu, Zhen Zhang, Dong Gong, Mingming Gong, Biwei Huang, Anton van den Hengel, Kun Zhang, and Javen Qinfeng Shi

    Transactions on Machine Learning Research (TMLR), 2025

    arXiv HTML
14. TMLR

    

    Highway Graph to Accelerate Reinforcement Learning

    Zidu Yin, Zhen Zhang, Dong Gong, Stefano V Albrecht, and Javen Q Shi

    Transactions on Machine Learning Research (TMLR), 2025

    arXiv HTML

2024

1. arXiv

   

   Learning Mamba as a Continual Learner: Meta-Learning Selective State Space Models for Efficient Continual Learning

   Chongyang Zhao and Dong Gong

   arXiv preprint arXiv:2412.00776, 2024

   arXiv HTML
2. NeurIPS

   

   CLAP4CLIP: Continual Learning with Probabilistic Finetuning for Vision-Language Models

   Saurav Jha, Dong Gong, and Lina Yao

   Advances in Neural Information Processing Systems (NeurIPS), 2024

   arXiv HTML Code
3. ACM MM

   

   EGGen: Image Generation with Multi-Entity Prior Learning Through Entity Guidance

   Zhenhong Sun, Junyan Wang, Zhiyu Tan, Daoyi Dong, Hailan Ma, Hao Li, and Dong Gong

   ACM International Conference on Multimedia (ACM MM), 2024

   HTML
4. IROS

   

   SDGE: Stereo Guided Depth Estimation for 360° Camera Sets

   Jialei Xu, Wei Yin, Dong Gong, Junjun Jiang, and Xianming Liu

   International Conference on Intelligent Robots and Systems (IROS), 2024

   arXiv HTML
5. ICLR

   

   Learning with Mixture of Prototypes for Out-of-Distribution Detection

   Haodong Lu, Dong Gong, Shuo Wang, Jason Xue, Lina Yao, and Kristen Moore

   International Conference on Learning Representations (ICLR), 2024

   arXiv HTML Code
6. ICLR

   

   Identifiable Latent Neural Causal Models

   Yuhang Liu, Zhen Zhang, Dong Gong, Mingming Gong, Biwei Huang, Anton van den Hengel, Kun Zhang, and Javen Qinfeng Shi

   International Conference on Learning Representations (ICLR), 2024

   HTML
7. TMM

   

   Continual All-in-One Adverse Weather Removal with Knowledge Replay on a Unified Network Structure

   De Cheng, Yanling Ji, Dong Gong, Yan Li, Nannan Wang, Junwei Han, and Dingwen Zhang

   IEEE Transactions on Multimedia, 2024

   arXiv HTML Code
8. arXiv

   

   Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learning

   Mark D McDonnell, Dong Gong, Ehsan Abbasnejad, and Anton van den Hengel

   arXiv preprint arXiv:2403.07356, 2024

   arXiv HTML Code

2023

1. NeurIPS

   

   RanPAC: Random Projections and Pre-trained Models for Continual Learning

   Mark D McDonnell, Dong Gong, Amin Parvaneh, Ehsan Abbasnejad, and Anton van den Hengel

   Advances in Neural Information Processing Systems (NeurIPS), 2023

   arXiv HTML Code
2. NeurIPS

   

   NPCL: Neural Processes for Uncertainty-Aware Continual Learning

   Saurav Jha, Dong Gong, He Zhao, and Lina Yao

   Advances in Neural Information Processing Systems (NeurIPS), 2023

   arXiv HTML Code
3. CVPR

   

   Learning to Fuse Monocular and Multi-View Cues for Multi-Frame Depth Estimation in Dynamic Scenes

   Rui Li, Dong Gong, Wei Yin, Hao Chen, Yu Zhu, Kaixuan Wang, Xiaozhi Chen, Jinqiu Sun, and Yanning Zhang

   IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023

   arXiv HTML Code Website
4. ICLR

   

   Maximizing Spatio-Temporal Entropy of Deep 3D CNNs for Efficient Video Recognition

   Junyan Wang^*, Zhenhong Sun^*, Yichen Qian, Dong Gong, Xiuyu Sun, Ming Lin, Maurice Pagnucco, and Yang Song

   International Conference on Learning Representations (ICLR), 2023

   arXiv HTML
5. TIP

   

   SharpFormer: Learning Local Feature Preserving Global Representations for Image Deblurring

   Qingsen Yan, Dong Gong, Pei Wang, Zhen Zhang, Yanning Zhang, and Javen Qinfeng Shi

   IEEE Transactions on Image Processing (TIP), 2023

   arXiv HTML

2022

1. CVPR

   

   Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning

   Qingsen Yan^*, Dong Gong^*, Yuhang Liu, Anton van den Hengel, and Javen Qinfeng Shi

   IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022

   HTML
2. NeurIPS

   

   Truncated Matrix Power Iteration for Differentiable DAG Learning

   Zhen Zhang^*, Ignavier Ng^*, Dong Gong, Yuhang Liu, Ehsan Abbasnejad, Mingming Gong, Kun Zhang, and Javen Qinfeng Shi

   Advances in Neural Information Processing Systems (NeurIPS), 2022

   arXiv HTML
3. CVPR-W

   

   A Lightweight Network for High Dynamic Range Imaging

   Qingsen Yan, Song Zhang, Weiye Chen, Yuhang Liu, Zhen Zhang, Yanning Zhang, Javen Qinfeng Shi, and Dong Gong

   IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2022

   HTML
4. IJCV

   

   Dual-Attention-Guided Network for Ghost-Free High Dynamic Range Imaging

   Qingsen Yan^*, Dong Gong^*, Javen Qinfeng Shi, Anton van den Hengel, Chunhua Shen, Ian Reid, and Yanning Zhang

   International Journal of Computer Vision (IJCV), 2022

   arXiv HTML
5. PR

   

   Video Super-Resolution via Mixed Spatial-Temporal Convolution and Selective Fusion

   Wei Sun, Dong Gong, Javen Qinfeng Shi, Anton van den Hengel, and Yanning Zhang

   Pattern Recognition (PR), 2022

   arXiv HTML
6. arXiv

   

   The Neural Process Family: Survey, Applications and Perspectives

   Saurav Jha, Dong Gong, Xuesong Wang, Richard E Turner, and Lina Yao

   arXiv preprint arXiv:2209.00517, 2022

   arXiv HTML

2021

1. ICCV

   

   Memory-Augmented Dynamic Neural Relational Inference

   Dong Gong, Zhen Zhang, Javen Qinfeng Shi, and Anton van den Hengel

   The International Conference on Computer Vision (ICCV), 2021

   HTML
2. TIP

   

   Learning to Zoom-in via Learning to Zoom-Out: Real-World Super-Resolution by Generating and Adapting Degradation

   Dong Gong^*, Wei Sun^*, Qinfeng Shi, Anton van den Hengel, and Yanning Zhang

   IEEE Transactions on Image Processing (TIP), 2021

   arXiv HTML
3. PR

   

   High Dynamic Range Imaging via Gradient-Aware Context Aggregation Network

   Qingsen Yan, Dong Gong, Javen Qinfeng Shi, Anton van den Hengel, Jinqiu Sun, Yu Zhu, and Yanning Zhang

   Pattern Recognition (PR), 2021

   HTML
4. PR

   

   Boundarymix: Generating Pseudo-Training Images for Improving Segmentation with Scribble Annotations

   Wanxuan Lu, Dong Gong, Kun Fu, Xian Sun, Wenhui Diao, and Lingqiao Liu

   Pattern Recognition (PR), 2021
5. IEEE-BigData

   

   COVID-19 Chest CT Image Segmentation Network by Multi-Scale Fusion and Enhancement Operations

   Qingsen Yan, Bo Wang, Dong Gong, Chuan Luo, Wei Zhao, Jianhu Shen, Jingyang Ai, Qinfeng Shi, Yanning Zhang, Shuo Jin, Liang Zhang, and Zheng You

   IEEE Transactions on Big Data, 2021

2020

1. TNNLS

   

   Learning Deep Gradient Descent Optimization for Image Deconvolution

   Dong Gong, Zhen Zhang, Qinfeng Shi, Anton van den Hengel, Chunhua Shen, and Yanning Zhang

   IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2020

   arXiv HTML Code
2. ECCV

   

   Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation

   Tong He^*, Dong Gong^*, Zhi Tian, and Chunhua Shen

   The European Conference on Computer Vision (ECCV), 2020

   arXiv HTML
3. TMM

   

   Deep Single Image Deraining via Modeling Haze-Like Effect

   Yinglong Wang, Dong Gong, Jie Yang, Qinfeng Shi, Dehua Xie, and Bing Zeng

   IEEE Transactions on Multimedia (TMM), 2020
4. TITS

   

   Part-Guided Attention Learning for Vehicle Instance Retrieval

   Xinyu Zhang, Rufeng Zhang, Jiewei Cao, Dong Gong, Mingyu You, and Chunhua Shen

   IEEE Transactions on Intelligent Transportation Systems (TITS), 2020

   arXiv HTML
5. arXiv

   

   Memorizing Comprehensively to Learn Adaptively: Unsupervised Cross-Domain Person Re-ID with Multi-Level Memory

   Xinyu Zhang^*, Dong Gong^*, Jiewei Cao, and Chunhua Shen

   arXiv preprint arXiv:2001.04123, 2020

   arXiv HTML

2019

1. ICCV

   

   Memorizing Normality to Detect Anomaly: Memory-Augmented Deep Autoencoder for Unsupervised Anomaly Detection

   Dong Gong, Lingqiao Liu, Vuong Le, Budhaditya Saha, Moussa Reda Mansour, Svetha Venkatesh, and Anton van den Hengel

   The International Conference on Computer Vision (ICCV), 2019

   arXiv HTML Code
2. CVPR

   

   Attention-Guided Network for Ghost-Free High Dynamic Range Imaging

   Qingsen Yan^*, Dong Gong^*, Qinfeng Shi, Anton van den Hengel, Chunhua Shen, Ian Reid, and Yanning Zhang

   IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019

   arXiv HTML Code
3. CVPR

   

   Knowledge Adaptation for Efficient Semantic Segmentation

   Tong He, Chunhua Shen, Zhi Tian, Dong Gong, Changming Sun, and Youliang Yan

   IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019

   HTML
4. CVPR

   

   Variational Bayesian Dropout with a Hierarchical Prior

   Yuhang Liu, Wenyong Dong, Lei Zhang, Dong Gong, and Qinfeng Shi

   IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019

   HTML Website
5. CVPR

   

   RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion

   Jie Li, Yu Liu, Dong Gong, Qinfeng Shi, Xia Yuan, Chunxia Zhao, and Ian Reid

   IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019

   HTML
6. TIP

   

   MPTV: Matching Pursuit-Based Total Variation Minimization for Image Deconvolution

   Dong Gong, Mingkui Tan, Qinfeng Shi, Anton van den Hengel, and Yanning Zhang

   IEEE Transactions on Image Processing, 2019

   arXiv HTML
7. TIP

   

   Two-Stream Convolutional Networks for Blind Image Quality Assessment

   Qingsen Yan^*, Dong Gong^*, and Yanning Zhang

   IEEE Transactions on Image Processing, 2019

   Code
8. TIP

   

   An Adaptive Markov Random Field for Structured Compressive Sensing

   Suwichaya Suwanwimolkul, Lei Zhang, Dong Gong, Zhen Zhang, Chao Chen, Damith C Ranasinghe, and Javen Qinfeng Shi

   IEEE Transactions on Image Processing, 2019

   arXiv HTML
9. arXiv

   

   Regularizing Proxies with Multi-Adversarial Training for Unsupervised Domain-Adaptive Semantic Segmentation

   Tong Shen, Dong Gong, Wei Zhang, Chunhua Shen, and Tao Mei

   arXiv preprint arXiv:1907.12282, 2019

   arXiv HTML Code
10. TKDE

    

    Learning Sparse PCA with Stabilized ADMM Method on Stiefel Manifold

    Mingkui Tan, Zhibin Hu, Yuguang Yan, Jiezhang Cao, Dong Gong, and Qingyao Wu

    IEEE Transactions on Knowledge and Data Engineering (TKDE), 2019
11. TKDE

    

    Learning Distilled Graph for Large-Scale Social Network Data Clustering

    Wenhe Liu, Dong Gong, Mingkui Tan, Javen Qinfeng Shi, Yi Yang, and Alexander G Hauptmann

    IEEE Transactions on Knowledge and Data Engineering (TKDE), 2019

2018

1. ECCV

   

   Seeing Deeply and Bidirectionally: A Deep Learning Approach for Single Image Reflection Removal

   Jie Yang^*, Dong Gong^*, Lingqiao Liu, and Qinfeng Shi

   European Conference on Computer Vision (ECCV), 2018

   HTML Code
2. ECCV

   

   Deblurring Natural Image Using Super-Gaussian Fields

   Yuhang Liu, Wenyong Dong, Dong Gong, Lei Zhang, and Qinfeng Shi

   European Conference on Computer Vision (ECCV), 2018

   HTML

2017

1. ICCV

   

   Self-Paced Kernel Estimation for Robust Blind Image Deblurring

   Dong Gong, Mingkui Tan, Yanning Zhang, Anton van den Hengel, and Qinfeng Shi

   IEEE International Conference on Computer Vision (ICCV), 2017

   HTML
2. CVPR

   

   From Motion Blur to Motion Flow: A Deep Learning Solution for Removing Heterogeneous Motion Blur

   Dong Gong, Jie Yang, Lingqiao Liu, Yanning Zhang, Ian Reid, Chunhua Shen, Anton van den Hengel, and Qinfeng Shi

   IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2017

   arXiv HTML
3. AAAI

   

   MPGL: An Efficient Matching Pursuit Method for Generalized LASSO

   Dong Gong, Mingkui Tan, Yanning Zhang, Anton van den Hengel, and Qinfeng Shi

   AAAI Conference on Artificial Intelligence (AAAI), 2017

   HTML Code

2016

1. CVPR

   

   Blind Image Deconvolution by Automatic Gradient Activation

   Dong Gong, Mingkui Tan, Yanning Zhang, Anton van den Hengel, and Qinfeng Shi

   IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2016

   HTML Code

2015

1. ICPR

   

   Joint Motion Deblurring with Blurred/Noisy Image Pair

   Haisen Li, Yanning Zhang, Jinqiu Sun, and Dong Gong

   International Conference on Pattern Recognition (ICPR), 2015
2. ICIP

   

   Neighbor Combination for Atmospheric Turbulence Image Reconstruction

   Dong Gong, Yanning Zhang, Shaobo Dang, and Jinqiu Sun

   IEEE International Conference on Image Processing (ICIP), 2015