← Authors

Lei Feng

79 papers · 2018–2026 · 10 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (7) 🌍 Conference Polyglot (10) 🌈 Renaissance Researcher (6) 🐝 Cross-Pollinator (11) 🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (15) 🧭 Keyword Pioneer 🏠 Conference Loyalist (23) πŸ† Keyword Champion (2) πŸ‘‘ Triple Crown πŸ† Grand Slam 🌱 Topic Pioneer πŸ”¬ Deep Specialist (29) 🀝 Dynamic Duo (28) πŸš€ Conference Pioneer ⚑ Prolific Year (17) ❓ The Questioner (3) πŸ’Ž Century Club (78) πŸ—ƒοΈ Keyword Collector (53) πŸ”₯ Unstoppable (8)

Conferences

ICML (23) NIPS (13) AAAI (10) ICLR (10) IJCAI (8) CVPR (6) ICCV (4) AISTATS (3) ACL (1) EMNLP (1)

Top co-authors

Bo An (28) Haobo Wang (13) Gang Niu (13) Hongxin Wei (13) Yuzhou Cao (12) Masashi Sugiyama (10) Feng Liu (10) Junbo Zhao (10) Gang Chen (8) Shuo He (8)

Keywords

weakly supervised learning (13) label noise (10) representation learning (8) semi-supervised learning (6) partial-label learning (6) partial label learning (5) candidate label (5) binary classification (5) multi-class classification (5) noisy label (5) contrastive learning (4) risk estimation (4) deep neural network (4) loss function (3) consistency regularization (3) out-of-distribution detection (3) label disambiguation (3) optimal transport (3) noisy label learning (3) multi-label learning (3)

Papers

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