2025春季学期
2025.6.25
- 卢昕怡 UNLOCKING THE POTENTIAL OF MODEL CALIBRATION IN FEDERATED LEARNING [paper][slides]
2025.6.18
- 郑腾鑫陵 Generalized Category Discovery[paper][slides]
- 蒋明忠 AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detection[paper][slides]
- 王子晨 Inducing Neural Collapse to a Fixed Hierarchy-Aware Frame for Reducing Mistake Severity[paper][slides]
2025.6.11
- 刘天泽 Towards Robust and Generalized Parameter-Efficient Fine-Tuning for Noisy Label Learning[paper][slides]
2025.6.4
- 张文良 Dual Consolidation for Pre-Trained Model-Based Domain-Incremental Learning[paper][slides]
2025.5.21
- 王远见 debiased and denoised entity recognition from distant supervision Paper Conference[paper][slides]
2025.5.15
- 卢昕怡 Harmonizing Generalization and Personalization in Federated Prompt Learning[paper][slides]
- 郑腾鑫陵:
- Contrast-Aware Calibration for Fine-Tuned CLIP Leveraging Image-Text Alignment [paper]
- Open-Vocabulary Calibration for Fine-tuned CLIP.pdf [paper]
- [slides]
2025.5.7
- 蒋明忠：Efficient Test-Time Adaptation of Vision-Language Models[paper] [slides]
- 王子晨：Masked Autoencoders Are Scalable Vision Learners [paper] [slides]
2025.4.16
- 郑金鹏：
- 郑腾鑫陵：Discovering and Mitigating Visual Biases through Keyword Explanation[paper][slides]
- 卢昕怡：Denoising after Entropy-Based Debiasing a Robust Training Method for Dataset Bias with Noisy Labels [paper][slides]
2025.3.19
- 郑腾鑫陵：AMU-Tuning Effective Logit Bias for CLIP-based Few-shot Learning [paper][slides]
- 卢昕怡：FedES: Federated Early-Stopping for Hindering Memorizing Heterogeneous Label Noise [paper][slides]