MLSP-P22: Robust and Trustworthy Machine Learning II
Poster
Wed, 6 May, 09:00 - 11:00
Location: Poster Area 9
Session Type: Poster
Track: Machine Learning for Signal Processing [ML]
Click the to view the manuscript on IEEE Xplore Open Preview

MLSP-P22.1: BOUNDING MEMORIZATION WITH LOSS CURVATURE AND CONNECTIONS TO COMPRESSION
Leah Woldemariam, Anna Scaglione, Cornell University, United States of America

MLSP-P22.2: ROBUST RUMOR DETECTION ON SOCIAL MEDIA WITH DYNAMIC CONTRASTIVE LEARNING
Mei Guo, Chen Chen, Nankai University, China; Chunyan Hou, Tianjin University of Technology, China; Yike Wu, Xiaojie Yuan, Nankai University, China

MLSP-P22.3: Moral5D: A Five-Dimensional Human-centered Method for Evaluating and Enhancing LLM Moral Reasoning
Siyu Wang, Yifan Li, Guitao Cao, Xidong Xi, Ziyuan Chen, Chen Chen, East China Normal University, China

MLSP-P22.4: MULTI-AGENT BRAINSTORMING FOR INTERPRETING AND MITIGATING HALLUCINATION IN MULTIMODAL-LLM
Zheng Lin, Zhenxing Niu, Xidian University, China; Zhibin Wang, INF Tech Co., Ltd., China; Xinghui Xu, Fudan University, China; Haofeng Liu, Haichang Gao, Xidian University, China

MLSP-P22.5: TrajRS: Towards Certified Robustness in Pedestrian Trajectory Prediction
Liang Zhang, Gaojie Jin, Institute of Software, Chinese Academy of Sciences, China; Yao Shi, Hangzhou Institute for Advanced Study, UCAS, China; Quanzhi Li, Institute of Software, Chinese Academy of Sciences, China; Cheng-Chao Huang, Nanjing Institute of Software Technology, Chinese Academy of Sciences, China; David N. Jansen, Lijun Zhang, Institute of Software, Chinese Academy of Sciences, China

MLSP-P22.6: CAN UNLEARNING OF MODELS LEAD TO ADVERSARIAL ROBUSTNESS?
Mridul Sharma, Parimala Kancharla, Indian Institute of Technology, Mandi, India

MLSP-P22.7: GAMMA: GENERALIZABLE AI-GENERATED IMAGE DETECTION VIA MULTI-TASK AND MANIPULATION-AUGMENTED SUPERVISION
Haozhen Yan, Shanghai Jiao Tong University, China; Yan Hong, Ant Group, China; Suning Lang, Jiahui Zhan, Yikun Ji, Yujie Gao, Shanghai Jiao Tong University, China; Huijia Zhu, Jun Lan, Ant Group, China; Jianfu Zhang, Shanghai Jiao Tong University, China

MLSP-P22.8: XMix: Combating Extremely Noisy Labels via Local Smoothness in Self-Supervised Feature Space
Chengqi Li, Yangdi Lu, Zhihao Shi, Wenbo He, McMaster University, Canada; Chamseddine Talhi, Nadjia Kara, École de Technologie Supérieure, Canada

MLSP-P22.9: RELIABLE AI VIA AGE-BALANCED VALIDATION: FAIR MODEL SELECTION FOR PARKINSON’S DETECTION FROM VOICE
Niloofar Momeni, Susanna Whitling, Andreas Jakobsson, Lund University, Sweden

MLSP-P22.10: SOURCE-FREE CONCEPT BOTTLENECK MODEL ADAPTATION WITH CONFIDENCE-ADAPTIVE CONDITIONAL ENSEMBLE
Minseon Park, Jitae Shin, Sungkyunkwan University, Korea, Republic of