About Me

I am currently a Postdoctoral Research Fellow at the Computer Vision Center, Universitat Autònoma de Barcelona, supervised by Dr. Joost Van De Weijer. Before, I was a postdoctoral researcher at the New Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), supervised by Prof. Liang Wang. I received my Ph.D. from the College of Intelligence and Computing, Tianjin University, under the supervision of Prof. Wei Feng. Earlier, I earned my master’s degree from Suzhou University of Science and Technology in 2018, where I was advised by Prof. Fuyuan Hu. My research focuses on Open-World Learning, with an emphasis on Continual Learning and Test-Time Learning. I am particularly interested in building machine learning models that can adapt to dynamic and evolving environments. I also have a solid background in computer vision and multi-modal learning, with several publications in these domains. I have led and participated in multiple research projects and am experienced in managing teams to deliver complex tasks in both academic and applied settings.

News

• 2026.04 | 1 paper was accepted to IEEE TPAMI: Elastic Multi-Gradient Descent for Parallel Continual Learning.
• 2026.04 | 1 paper was accepted to IEEE TCSVT: MultiHuman: Leverage Multimodal Prompts for Controllable Multi-Person Image Synthesizing .
• 2026.03 | 1 paper was accepted to Pattern Recognition: Negative-Weighted Knowledge Distillation Regularized Graph Convolutional Network for Multi-Label Class-Incremental Learning.
• 2026.03 | 1 paper was accepted to ICME 2026: Expansive Geometry Stabilization for Exemplar-free Continual Learning with Pre-trained Models .
• 2026.03 | 1 paper was accepted to IEEE TCSVT: GAIN: Global-Atomic INteraction Graph for Few-Shot Class-Incremental Learning .
• 2026.03 | I was support by EuroHPC, Computing allocation on the Leonardo Booster supercomputer.
• 2026.02 | 2 paper was accepted to CVPR 2026:
  • Subspace Alignment for CLIP-based Continual Learning via Canonical Correlation Analysis
  • Towards Dynamic Modality Alignment in Multimodal Continual Learning
• 2026.01 | 1 paper was accepted to ICLR 2025: Exposing Mixture and Annotating Confusion for Active Universal Test-Time Adaptation.
• 2026.01 | I will serve as a tutor in the CVC Talent Program of Internships.
• 2026.01 | 3 paper was accepted to IEEE ICASSP 2026:
  • From Cold-Start to Stabilization: A Dual-Prototype Framework for Online Any-Shot Continual Learning
  • Low-Level Continual Test-Time Adaptation for Image Restoration
  • Contextual Clue Mining and Class Calibration for Weakly Supervised Video Anomaly Detection
• 2025.11 | 1 paper was accepted to IEEE TCSVT 2025: Mitigating Catastrophic Forgetting in Online Continual Learning with Dual-Margin Contrastive Replay.
• 2025.11 | 1 paper was accepted to AAAI 2026 as Oral: Sparse Tuning Enhances Plasticity in PTM-based Continual Learning.
• 2025.09 | 1 paper was accepted to IEEE TCSVT 2025: MambaPTP: Exploring the Potential of Mamba for Pedestrian Trajectory Prediction.
• 2025.09 | We achieved 4th place in the CLVISION 2025 CVIT Challenge, and our solution report will be released soon.
• 2025.09 | 2 paper was accepted to NeurIPS 2025, and one of them is marked as spotlight:
  • (Spotlight, top 13%) Partition-Then-Adapt: Combating Prediction Bias for Reliable Multi-Modal Test-Time Adaptation
  • DAA: Amplifying Unknown Discrepancy for Test-Time Discovery
• 2025.06 | 1 paper was accepted to IEEE TMM 2025: Constructing Enhanced Mutual Information for Online Class-Incremental Learning.
• 2025.04 | 1 paper was accepted to IEEE TCSVT 2025: Few-Shot Class-Incremental Learning via Asymmetric Supervised Contrastive Learning.
• 2025.03 | 1 paper was accepted to ICME 2025: Controllable Continual Test-Time Adaptation.
• 2025.02 | 3 paper was accepted to CVPR 2025:
  • Maintaining Consistent Inter-Class Topology in Continual Test-Time Adaptation
  • Beyond Background Shift: Rethinking Instance Replay in Continual Semantic Segmentation
  • Dual Semantic Guidance for Open Vocabulary Semantic Segmentation
• 2025.02 | 1 survey was accepted to JIG 2025: A Comprehensive Survey on Continual Learning.
• 2025.02 | Our book of continual learning is published: Continual Artificial Intelligence towards Changing Environment.
• 2025.01 | 1 paper was accepted to AAAI 2025: Rebalancing Multi-Label Class-Incremental Learning.