Lei Feng

An Invariant Latent Space Perspective on Language Model Inversion AAAI 2026 Test-Time Attention Purification for Backdoored Large Vision Language Models CVPR 2026 A Closer Look at Backdoor Attacks on CLIP ICML 2025 Attribute-based Visual Reprogramming for Vision-Language Models ICLR 2025 Endowing Visual Reprogramming with Adversarial Robustness ICLR 2025 Enhancing the Influence of Labels on Unlabeled Nodes in Graph Convolutional Networks ICML 2025 Exploiting Presentative Feature Distributions for Parameter-Efficient Continual Learning of Large Language Models ICML 2025 Improving Generalization of Deep Neural Networks by Optimum Shifting AAAI 2025 Influence-Based Fair Selection for Sample-Discriminative Backdoor Attack AAAI 2025 Instance-dependent Early Stopping ICLR 2025 Prototype-based Optimal Transport for Out-of-Distribution Detection IJCAI 2025 Representation Surgery in Model Merging with Probabilistic Modeling ICML 2025 Rethinking Chain-of-Thought from the Perspective of Self-Training ICML 2025 Test-Time Multimodal Backdoor Detection by Contrastive Prompting ICML 2025 Towards Reverse Engineering of Language Models: A Survey EMNLP 2025 Towards Robust Incremental Learning Under Ambiguous Supervision IJCAI 2025 Understanding Model Reprogramming for CLIP via Decoupling Visual Prompts ICML 2025 A General Framework for Learning from Weak Supervision ICML 2024 Bayesian-guided Label Mapping for Visual Reprogramming NeurIPS 2024 Candidate Label Set Pruning: A Data-centric Perspective for Deep Partial-label Learning ICLR 2024 Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Data ICML 2024 Consistent Hierarchical Classification with A Generalized Metric AISTATS 2024 Consistent Multi-Class Classification from Multiple Unlabeled Datasets ICLR 2024 CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learning CVPR 2024 Early Stopping Against Label Noise Without Validation Data ICLR 2024 Exploiting Human-AI Dependence for Learning to Defer ICML 2024 Investigating and Mitigating the Side Effects of Noisy Views for Self-Supervised Clustering Algorithms in Practical Multi-View Scenarios CVPR 2024 Learning Geometry-Aware Representations for New Intent Discovery ACL 2024 Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss ICML 2024 Mitigating Underfitting in Learning to Defer with Consistent Losses AISTATS 2024 On the Vulnerability of Adversarially Trained Models Against Two-faced Attacks ICLR 2024 Positive and Unlabeled Learning with Controlled Probability Boundary Fence ICML 2024 Positive-Unlabeled Learning by Latent Group-Aware Meta Disambiguation CVPR 2024 Robust Node Classification on Graph Data with Graph and Label Noise AAAI 2024 Sample-specific Masks for Visual Reprogramming-based Prompting ICML 2024 Targeted Representation Alignment for Open-World Semi-Supervised Learning CVPR 2024 Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models ICML 2024 A Generalized Unbiased Risk Estimator for Learning with Augmented Classes AAAI 2023 ALIM: Adjusting Label Importance Mechanism for Noisy Partial Label Learning NeurIPS 2023 A Universal Unbiased Method for Classification from Aggregate Observations ICML 2023 Binary Classification with Confidence Difference NeurIPS 2023 Candidate-aware Selective Disambiguation Based On Normalized Entropy for Instance-dependent Partial-label Learning ICCV 2023 Consistent Complementary-Label Learning via Order-Preserving Losses AISTATS 2023 Fine-Grained Classification With Noisy Labels CVPR 2023 In Defense of Softmax Parametrization for Calibrated and Consistent Learning to Defer NeurIPS 2023 Late Stopping: Avoiding Confidently Learning from Mislabeled Examples ICCV 2023 Mitigating Memorization of Noisy Labels by Clipping the Model Prediction ICML 2023 Multi-Label Knowledge Distillation ICCV 2023 On the Importance of Feature Separability in Predicting Out-Of-Distribution Error NeurIPS 2023 Partial-Label Regression AAAI 2023 ProMix: Combating Label Noise via Maximizing Clean Sample Utility IJCAI 2023 Regression with Cost-based Rejection NeurIPS 2023 SPA: A Graph Spectral Alignment Perspective for Domain Adaptation NeurIPS 2023 Weakly Supervised Regression with Interval Targets ICML 2023 Can Adversarial Training Be Manipulated By Non-Robust Features? NeurIPS 2022 Exploiting Class Activation Value for Partial-Label Learning ICLR 2022 GearNet: Stepwise Dual Learning for Weakly Supervised Domain Adaptation AAAI 2022 Generalizing Consistent Multi-Class Classification with Rejection to be Compatible with Arbitrary Losses NeurIPS 2022 Mitigating Neural Network Overconfidence with Logit Normalization ICML 2022 Open-Sampling: Exploring Out-of-Distribution data for Re-balancing Long-tailed datasets ICML 2022 PiCO: Contrastive Label Disambiguation for Partial Label Learning ICLR 2022 SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning NeurIPS 2022 Who Is Your Right Mixup Partner in Positive and Unlabeled Learning ICLR 2022 With False Friends Like These, Who Can Notice Mistakes? AAAI 2022 Attention Is Not Enough: Mitigating the Distribution Discrepancy in Asynchronous Multimodal Sequence Fusion ICCV 2021 Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training NeurIPS 2021 Learning from Complementary Labels via Partial-Output Consistency Regularization IJCAI 2021 Learning from Similarity-Confidence Data ICML 2021 Pointwise Binary Classification with Pairwise Confidence Comparisons ICML 2021 Rethinking Calibration of Deep Neural Networks: Do Not Be Afraid of Overconfidence NeurIPS 2021 Can Cross Entropy Loss Be Robust to Label Noise? IJCAI 2020 Combating Noisy Labels by Agreement: A Joint Training Method with Co-Regularization CVPR 2020 Discovering Latent Class Labels for Multi-Label Learning IJCAI 2020 Learning with Multiple Complementary Labels ICML 2020 Progressive Identification of True Labels for Partial-Label Learning ICML 2020 Provably Consistent Partial-Label Learning NeurIPS 2020 Collaboration Based Multi-Label Learning AAAI 2019 Partial Label Learning by Semantic Difference Maximization IJCAI 2019 Partial Label Learning with Self-Guided Retraining AAAI 2019 Leveraging Latent Label Distributions for Partial Label Learning IJCAI 2018