Hongxin Wei

Online Conformal Selection with Accept-to-Reject Changes AAAI 2026 Semi-Supervised Conformal Prediction With Unlabeled Nonconformity Score CVPR 2026 Toward Early Quality Assessment of Text-to-Image Diffusion Models CVPR 2026 Exploring Learning Complexity for Efficient Downstream Dataset Pruning ICLR 2025 Fine-tuning can Help Detect Pretraining Data from Large Language Models ICLR 2025 How Contaminated Is Your Benchmark? Measuring Dataset Leakage in Large Language Models with Kernel Divergence ICML 2025 Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection ICLR 2025 Parametric Scaling Law of Tuning Bias in Conformal Prediction ICML 2025 TorchCP: A Python Library for Conformal Prediction JMLR 2025 Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models ICML 2025 Conformal Prediction for Deep Classifier via Label Ranking ICML 2024 Consistent Multi-Class Classification from Multiple Unlabeled Datasets ICLR 2024 CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learning CVPR 2024 DOS: Diverse Outlier Sampling for Out-of-Distribution Detection ICLR 2024 GACL: Exemplar-Free Generalized Analytic Continual Learning NeurIPS 2024 Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss ICML 2024 On the Noise Robustness of In-Context Learning for Text Generation NeurIPS 2024 Open-Vocabulary Calibration for Fine-tuned CLIP ICML 2024 Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints ICML 2024 Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks ICLR 2024 A Generalized Unbiased Risk Estimator for Learning with Augmented Classes AAAI 2023 In Defense of Softmax Parametrization for Calibrated and Consistent Learning to Defer NeurIPS 2023 Mitigating Memorization of Noisy Labels by Clipping the Model Prediction ICML 2023 On the Importance of Feature Separability in Predicting Out-Of-Distribution Error NeurIPS 2023 Regression with Cost-based Rejection NeurIPS 2023 ACIL: Analytic Class-Incremental Learning with Absolute Memorization and Privacy Protection NeurIPS 2022 Can Adversarial Training Be Manipulated By Non-Robust Features? NeurIPS 2022 GearNet: Stepwise Dual Learning for Weakly Supervised Domain Adaptation AAAI 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 Commission Fee is not Enough: A Hierarchical Reinforced Framework for Portfolio Management AAAI 2021 Open-set Label Noise Can Improve Robustness Against Inherent Label Noise NeurIPS 2021 Combating Noisy Labels by Agreement: A Joint Training Method with Co-Regularization CVPR 2020