王登豹 - 东南大学 - 计算机科学与工程学院

个人简介

王登豹，东南大学计算机科学与工程学院讲师，硕士生导师。2024年于东南大学计算机科学与工程学院获得博士学位，导师为张敏灵教授。研究领域为人工智能、机器学习，近期主要关注模型置信度校准、大模型不确定性评估、多模态模型幻觉检测与缓解等问题，在机器学习、数据挖掘、人工智能相关领域的顶级会议与权威期刊上（ICML、NeurIPS、KDD、AAAI、IEEE TPAMI 、IEEE TKDE 等）发表论文十余篇，获批首届 “NSFC 博士生基金” 项目，获德国学术交流中心 DAAD AInet Fellow 计划等奖励，并担任多个著名国际会议的程序委员以及期刊审稿人。

研究领域

人工智能机器学习模型置信度校准大模型不确定性评估多模态模型幻觉检测与缓解

近期论文

查看导师新发文章（温馨提示：请注意重名现象，建议点开原文通过作者单位确认）

Calibration Bottleneck: Over-compressed Representations are Less Calibratable Deng-Bao Wang, Min-Ling Zhang International Conference on Machine Learning (ICML), 2024 We empirically observed a U-shaped pattern on calibratability of intermediate features, spanning from the lower to the upper layers. Distilling Reliable Knowledge for Instance-Dependent Partial Label Learning Dong-Dong Wu†, Deng-Bao Wang†, Min-Ling Zhang AAAI Conference on Artificial Intelligence (AAAI), 2024 On the Pitfall of Mixup for Uncertainty Calibration Deng-Bao Wang, Lanqing Li, Peilin Zhao, Pheng-Ann Heng, Min-Ling Zhang IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023 Appendix We pointed out the pitfall of Mixup on calibration and propose a simple yet effective strategy named Mixup Inference in Training. Adaptive Graph Guided Disambiguation for Partial Label Learning Deng-Bao Wang, Min-Ling Zhang, Li Li IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022 Revisiting Consistency Regularization for Deep Partial Label Learning Dong-Dong Wu†, Deng-Bao Wang†, Min-Ling Zhang International Conference on Machine Learning (ICML), 2022 Rethinking Calibration of Deep Neural Networks: Don't Be Afraid of Overconfidence Deng-Bao Wang, Lei Feng, Min-Ling Zhang Advances in Neural Information Processing Systems (NeurIPS), 2021 We for the first time found that despite those regularized models are better calibrated, they suffer from not being calibratable. Learning from Complementary Labels via Partial-Output Consistency Regularization Deng-Bao Wang, Lei Feng, Min-Ling Zhang International Joint Conference on Artificial Intelligence (IJCAI), 2021 Learning from Noisy Labels with Complementary Loss Functions Deng-Bao Wang, Yong Wen, Lujia Pan, Min-Ling Zhang AAAI Conference on Artificial Intelligence (AAAI), 2021 Adaptive Graph Guided Disambiguation for Partial Label Learning Deng-Bao Wang, Li Li, Min-Ling Zhang ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2019

学术兼职

担任多个著名国际会议的程序委员以及期刊审稿人