Hongxin Wei

papers

985

total citations

papers (15)

Combating Noisy Labels by Agreement: A Joint Training Method with Co-Regularization

CVPR 2020arXiv

643

citations

Open-set Label Noise Can Improve Robustness Against Inherent Label Noise

NEURIPS 2021arXiv

101

citations

ACIL: Analytic Class-Incremental Learning with Absolute Memorization and Privacy Protection

NEURIPS 2022arXiv

citations

Conformal Prediction for Deep Classifier via Label Ranking

ICML 2024arXiv

citations

In Defense of Softmax Parametrization for Calibrated and Consistent Learning to Defer

NEURIPS 2023arXiv

citations

Can Adversarial Training Be Manipulated By Non-Robust Features?

NEURIPS 2022arXiv

citations

On the Importance of Feature Separability in Predicting Out-Of-Distribution Error

NEURIPS 2023arXiv

citations

Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints

ICML 2024arXiv

citations

Open-Vocabulary Calibration for Fine-tuned CLIP

ICML 2024arXiv

citations

How Contaminated Is Your Benchmark? Measuring Dataset Leakage in Large Language Models with Kernel Divergence

ICML 2025

citations

Hongxin Wei

papers (15)

Combating Noisy Labels by Agreement: A Joint Training Method with Co-Regularization

Open-set Label Noise Can Improve Robustness Against Inherent Label Noise

ACIL: Analytic Class-Incremental Learning with Absolute Memorization and Privacy Protection

Conformal Prediction for Deep Classifier via Label Ranking

In Defense of Softmax Parametrization for Calibrated and Consistent Learning to Defer

Can Adversarial Training Be Manipulated By Non-Robust Features?

On the Importance of Feature Separability in Predicting Out-Of-Distribution Error

Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints

Open-Vocabulary Calibration for Fine-tuned CLIP

How Contaminated Is Your Benchmark? Measuring Dataset Leakage in Large Language Models with Kernel Divergence

Regression with Cost-based Rejection

CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learning

Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss

Fine-tuning can Help Detect Pretraining Data from Large Language Models

Exploring Learning Complexity for Efficient Downstream Dataset Pruning

papers (15)

Combating Noisy Labels by Agreement: A Joint Training Method with Co-Regularization

Open-set Label Noise Can Improve Robustness Against Inherent Label Noise

ACIL: Analytic Class-Incremental Learning with Absolute Memorization and Privacy Protection

Conformal Prediction for Deep Classifier via Label Ranking

In Defense of Softmax Parametrization for Calibrated and Consistent Learning to Defer

Can Adversarial Training Be Manipulated By Non-Robust Features?

On the Importance of Feature Separability in Predicting Out-Of-Distribution Error

Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints

Open-Vocabulary Calibration for Fine-tuned CLIP

How Contaminated Is Your Benchmark? Measuring Dataset Leakage in Large Language Models with Kernel Divergence

Regression with Cost-based Rejection

CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learning

Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss

Fine-tuning can Help Detect Pretraining Data from Large Language Models

Exploring Learning Complexity for Efficient Downstream Dataset Pruning