Hongxin Wei
31 papers · 2020–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+11 more ↓ Show less ↑
π Academic Marathon (5) π Cross-Pollinator (9) π Conference Polyglot (6) π§ Keyword Pioneer π Renaissance Researcher (5)
π
Renaissance Researcher
(5)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(46)
π
Triple Crown
π
Grand Slam
π€
Dynamic Duo
(13)
π₯
Unstoppable
(6)
π
Century Club
(30)
ποΈ
Keyword Collector
(99)
β
The Questioner
(2)
β‘
Prolific Year
(5)
Conferences
ICML (10)
NIPS (8)
ICLR (6)
AAAI (4)
CVPR (2)
JMLR (1)
Top co-authors
Keywords
semi-supervised learning
(3)
out-of-distribution detection
(3)
noisy label
(3)
label noise
(3)
catastrophic forgetting
(2)
representation learning
(2)
noisy label learning
(2)
surrogate loss
(2)
uncertainty quantification
(2)
hierarchical learning
(1)
binary classification
(1)
data poisoning
(1)
matrix decomposition
(1)
conformal prediction
(1)
online learning
(1)
continual learning
(1)
text generation
(1)
in-context learning
(1)
policy learning
(1)
false discovery rate
(1)
Papers
Online Conformal Selection with Accept-to-Reject Changes
AAAI 2026
Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection
ICLR 2025
Exploring Learning Complexity for Efficient Downstream Dataset Pruning
ICLR 2025
Parametric Scaling Law of Tuning Bias in Conformal Prediction
ICML 2025
Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models
ICML 2025
How Contaminated Is Your Benchmark? Measuring Dataset Leakage in Large Language Models with Kernel Divergence
ICML 2025
Fine-tuning can Help Detect Pretraining Data from Large Language Models
ICLR 2025
TorchCP: A Python Library for Conformal Prediction
JMLR 2025
Consistent Multi-Class Classification from Multiple Unlabeled Datasets
ICLR 2024
On the Noise Robustness of In-Context Learning for Text Generation
NIPS 2024
GACL: Exemplar-Free Generalized Analytic Continual Learning
NIPS 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
Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks
ICLR 2024
Conformal Prediction for Deep Classifier via Label Ranking
ICML 2024
Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss
ICML 2024
Open-Vocabulary Calibration for Fine-tuned CLIP
ICML 2024
Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints
ICML 2024
Regression with Cost-based Rejection
NIPS 2023
A Generalized Unbiased Risk Estimator for Learning with Augmented Classes
AAAI 2023
Mitigating Memorization of Noisy Labels by Clipping the Model Prediction
ICML 2023
In Defense of Softmax Parametrization for Calibrated and Consistent Learning to Defer
NIPS 2023
On the Importance of Feature Separability in Predicting Out-Of-Distribution Error
NIPS 2023
Open-Sampling: Exploring Out-of-Distribution data for Re-balancing Long-tailed datasets
ICML 2022
GearNet: Stepwise Dual Learning for Weakly Supervised Domain Adaptation
AAAI 2022
Mitigating Neural Network Overconfidence with Logit Normalization
ICML 2022
Can Adversarial Training Be Manipulated By Non-Robust Features?
NIPS 2022
ACIL: Analytic Class-Incremental Learning with Absolute Memorization and Privacy Protection
NIPS 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
NIPS 2021
Combating Noisy Labels by Agreement: A Joint Training Method with Co-Regularization
CVPR 2020