Fan Lyu
Scholar

Fan Lyu

Google Scholar ID: eowEXGgAAAAJ
NLPR, CASIA
Computer VisionMachine LearningArtificial Intelligence
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
764
 
H-index
13
 
i10-index
14
 
Publications
20
 
Co-authors
12
list available
Contact
Emailfan.lyu@cripac.ia.ac.cnGitHubOpen ↗
Publications
8 items
Annotation-Efficient Active Test-Time Adaptation with Conformal Prediction
2025
Cited
0
DDP: Dual-Decoupled Prompting for Multi-Label Class-Incremental Learning
2025
Cited
0
Ambiguity-Guided Learnable Distribution Calibration for Semi-Supervised Few-Shot Class-Incremental Learning
2025
Cited
0
Beyond Freezing: Sparse Tuning Enhances Plasticity in Continual Learning with Pre-Trained Models
2025
Cited
0
MM-Prompt: Cross-Modal Prompt Tuning for Continual Visual Question Answering
2025
Cited
0
Beyond Background Shift: Rethinking Instance Replay in Continual Semantic Segmentation
2025
Cited
0
Test-Time Discovery via Hashing Memory
2025
Cited
0
Conformal Uncertainty Indicator for Continual Test-Time Adaptation
2025
Cited
0
Resume (English only)
Academic Achievements
  • Published papers:
  • - AAAI 2026: Sparse Tuning Enhances Plasticity in PTM-based Continual Learning
  • - IEEE TCSVT 2025: MambaPTP: Exploring the Potential of Mamba for Pedestrian Trajectory Prediction
  • - NeurIPS 2025: Partition-Then-Adapt: Combating Prediction Bias for Reliable Multi-Modal Test-Time Adaptation (Spotlight, top 13%); DAA: Amplifying Unknown Discrepancy for Test-Time Discovery
  • - IEEE TMM 2025: Constructing Enhanced Mutual Information for Online Class-Incremental Learning
  • - IEEE TCSVT 2025: Few-Shot Class-Incremental Learning via Asymmetric Supervised Contrastive Learning
  • - ICME 2025: Controllable Continual Test-Time Adaptation
  • - 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
  • - JIG 2025: A Comprehensive Survey on Continual Learning
  • Book published: Continual Artificial Intelligence towards Changing Environment
  • Competition achievement: Achieved 4th place in the CLVISION 2025 CVIT Challenge.
Research Experience
  • Led and participated in multiple research projects, experienced in managing teams to deliver complex tasks in both academic and applied settings.
Education
  • PhD: College of Intelligence and Computing, Tianjin University, supervised by Prof. Wei Feng; Master's degree from Suzhou University of Science and Technology, 2018, advised by Prof. Fuyuan Hu; Currently a Postdoctoral Research Fellow at the New Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), supervised by Prof. Liang Wang.
Background
  • Research interests: Open-World Learning, with an emphasis on Continual Learning and Test-Time Learning. Focused on building machine learning models that can adapt to dynamic and evolving environments. Has a solid background in computer vision and multi-modal learning.
Miscellany
  • Personal interests and hobbies not mentioned
Co-authors
12 total
Fuyuan Hu
Fuyuan Hu
Professor of Suzhou University of Science and Technology
Wei Feng
Wei Feng
School of Computer Science and Technology, College of Intelligence and Computing, Tianjin University
Liang Wan
Liang Wan
College of Intelligence and Computing, Medical College, Tianjin University
Fanhua Shang
Fanhua Shang
Professor at Tianjin University
Zhang Zhang
Zhang Zhang
Institute of Automation, Chinese Academy of Sciences
Song Wang
Song Wang
Professor of Computer Science and Engineering, University of South Carolina
Kaizhu Huang
Kaizhu Huang
Professor, Duke Kunshan University
Liang Wang
Liang Wang
National Lab of Pattern Recognition