A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1.
CoRR, March, 2025
Realistic Evaluation of Deep Partial-Label Learning Algorithms.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025
Efficient Model Stealing Defense with Noise Transition Matrix.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
Distilling Reliable Knowledge for Instance-Dependent Partial Label Learning.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024
Robust Representation Learning for Unreliable Partial Label Learning.
CoRR, 2023
Revisiting Consistency Regularization for Deep Partial Label Learning.
Proceedings of the International Conference on Machine Learning, 2022