Scholar
Jiang-Xin Shi
Google Scholar ID: KEgtGncAAAAJ
Nanjing University
Citations & Impact
Citations
394
H-index
10
i10-index
12
Publications
16
Co-authors
11
list available
Publications
Resume (English only)
Academic Achievements
- Journal Paper: 'Long-Tail Learning with Context-Aware Re-sampling', Frontiers of Computer Science (FCS), In Press
- Journal Paper: 'Robust Long-Tailed Learning under Label Noise', Frontiers of Computer Science (FCS), In Press
- Journal Paper: 'Residual Diverse Ensemble for Long-Tailed Multi-Label Text Classification', SCIENCE CHINA Information Sciences (SCIS), 2024
- Journal Paper: 'Transfer and Share: Semi-Supervised Learning from Long-Tailed Data', Machine Learning (MLJ), 2022
- Conference Paper: 'X-Mahalanobis: Transformer Feature Mixing for Reliable OOD Detection', NeurIPS 2025
- Conference Paper: 'Vision-Language Models are Strong Noisy Label Detectors', NeurIPS 2024
- Conference Paper: 'Efficient and Long-Tailed Generalization for Pre-trained Vision-Language Model', KDD 2024
- Conference Paper: 'Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts', ICML 2024
- Conference Paper: 'DeCoOp: Robust Prompt Tuning with Out-of-Distribution Detection', ICML 2024
- Conference Paper: 'How Re-sampling Helps for Long-Tail Learning?', NeurIPS 2023
- Conference Paper: 'Prototypical Classifier for Robust Class-Imbalanced Learning', PAKDD 2022 (Best Paper Award)
- Conference Paper: 'Probabilistic Label Tree for Streaming Multi-Label Learning', KDD 2021
- Other Paper: 'Memory-Efficient Fine-Tuning via Low-Rank Activation Compression', arXiv:2509.23472, 2025
Background
- Research interests include Machine Learning and Data Mining, particularly Long-Tail Learning, Efficient Machine Learning, and Weakly Supervised Learning.
Miscellany
- Personal interests not provided
