MLSP-P20: Emerging Topics in Machine Learning for Signal Processing I
Poster
Wed, 6 May, 09:00 - 11:00
Location: Poster Area 7
Session Type: Poster
Track: Machine Learning for Signal Processing [ML]
Click the to view the manuscript on IEEE Xplore Open Preview

MLSP-P20.1: LEARNING CLASS-CONDITIONAL TEMPERATURE WITH ENTROPY ALIGNMENT FOR MEDICAL IMAGE CLASSIFICATION
Weichao Pan, Shandong Jianzhu University, China; Ruida Liu, Shenzhen MSU-BIT University, China; Chengze Lv, Shandong Jianzhu University, China; Puyu Han, Zhejiang Lab, FUXI AI Lab, China; Luqi Gong, Zhejiang Lab, China; Xu Wang, Shandong Jianzhu University, Zhejiang Lab, China

MLSP-P20.2: SOURCE-FREE DOMAIN ADAPTATION WITH LIGHT-WEIGHT TRANSFORMER AND CONSISTENCY LOSS
Yeeun Kim, Gyemin Lee, Seoul National University of Science and Technology, Korea, Republic of

MLSP-P20.3: RECALL-LO: Enhancing Label-Only Membership Inference Against Large Language Models
Yaxuan Liu, National University of Defense Technology, China; Shaoyang Song, Chunlai Zhou, Renmin University of China, China; Yun Zhou, National University of Defense Technology, China

MLSP-P20.4: Layout Robust Zero Shot Learning for Human Activity Recognition Using Wi-Fi Sensing in Unseen Environments
Rod Koo, Deepak Mishra, Hassan Gharakheili, Aruna Seneviratne, University of New South Wales, Australia

MLSP-P20.5: TIPS Over Tricks: Simple Prompts for Effective Zero-Shot Anomaly Detection
Alireza Salehi, Ehsan Karami, University of Tehran, Iran (Islamic Republic of); Sepehr Noey, Sahand Noey, Amirkabir University of Technology, Iran (Islamic Republic of); Makoto Yamada, Okinawa Institute of Science and Technology, Japan; Reshad Hosseini, University of Tehran, Iran (Islamic Republic of); Mohammad Sabokrou, Okinawa Institute of Science and Technology, Japan

MLSP-P20.6: TMT: Cross-domain Semantic Segmentation with Region-adaptive Transferability Estimation
Enming Zhang, Tsinghua University, China; Zhengyu Li, Shanghai Jiao Tong University, China; Yanru Wu, Jingge Wang, Xiaoping Zhang, Yang Li, Tsinghua University, China

MLSP-P20.7: TOKCOINFER: TOKEN-LEVEL MULTI-MODEL COLLABORATION FOR ENERGY-EFFICIENT LLM INFERENCE
Yijia Zhang, Dongxiang Zhang, Bingqiang Wang, Shixun Zhang, Peng Cheng Laboratory, China

MLSP-P20.8: UnlearnShield: Shielding Forgotten Privacy against Unlearning Inversion
Lulu Xue, Shengshan Hu, Wei Lu, Ziqi Zhou, Yufei Song, Huazhong University of Science and Technology, China; Jianhong Cheng, Institute of Guizhou Aerospace Measuring and Testing Technology, China; Minghui Li, Huazhong University of Science and Technology, China; Yanjun Zhang, University of Technology Sydney, Australia; Leo Yu Zhang, Griffith University, Australia

MLSP-P20.9: DP-LAC: LIGHTWEIGHT ADAPTIVE CLIPPING FOR DIFFERENTIALLY PRIVATE FEDERATED FINE-TUNING OF LANGUAGE MODELS
Haaris Mehmood, Jie Xu, Karthikeyan Saravanan, Samsung R&D Institute UK (SRUK), United Kingdom of Great Britain and Northern Ireland; Rogier Van Dalen, Samsung AI Centre Cambridge, United Kingdom of Great Britain and Northern Ireland; Mete Ozay, Samsung R&D Institute UK (SRUK), United Kingdom of Great Britain and Northern Ireland

MLSP-P20.10: AUGMENT-AND-REGULARIZE: TOWARD RELIABLE SEMI-SUPERVISED DOMAIN GENERALIZATION
Sijun Wang, Ziwei Niu, Shiao Xie, College of Computer Science and Technology, Zhejiang University, Hangzhou, China, China; Pengyu Chen, College of Computer Science, Chongqing University, Chongqing, China, China; Yen-wei Chen, College of Information Science and Engineering, Ritsumeikan University, Kyoto, Japan, China; Ruofeng Tong, Lanfen Lin, College of Computer Science and Technology, Zhejiang University, Hangzhou, China, China