MLSP-P53: Training and Optimization Methods for Deep Neural Networks
Poster
Thu, 7 May, 14:00 - 16:00
Location: Poster Area 4
Session Type: Poster
Track: Machine Learning for Signal Processing [ML]
Click the to view the manuscript on IEEE Xplore Open Preview

MLSP-P53.1: HYPERSPARSE: FINDING COMPETITIVE HIGH-SPARSITY MODELS VIA HYPERNETWORKS
Mingrui Cai, Shiyun Fu, Tsinghua University, China; Jiangtao Wen, New York University, United States of America; Yuxing Han, Tsinghua University, China

MLSP-P53.2: HIPPOCAMPAL-INSPIRED ASSOCIATE MEMORY FRAMEWORK FOR FEW-SHOT CLASSIFICATION
Kexin Di, Beijing Normal University, China; Xinping Chen, Xiuxing Li, Xia Wu, Beijing Institute of Technology, China

MLSP-P53.3: Attention-weighted Centered Kernel Alignment for Knowledge Distillation in Large Audio-Language Models Applied to Speech Emotion Recognition
Qingran Yang, Harbin Institute of Technology, China; Botao Zhao, Zuheng Kang, Ping An Technology (Shenzhen) Co., Ltd., China; Xue Li, Harbin Institute of Technology, China; Yayun He, Chuhang Liu, Xulong Zhang, Xiaoyang Qu, Junqing Peng, Jianzong Wang, Ping An Technology (Shenzhen) Co., Ltd., China

MLSP-P53.4: Aurora: Precise and Lightweight Multimodal Fusion for Efficient Referring Remote Sensing Image Segmentation
Qixiang Yin, Xiangning Ruan, Weize Li, Zhicheng Zhao, Fei Su, Beijing University of Posts and Telecommunications, China

MLSP-P53.5: STRUCTURAL DECOUPLING-DRIVEN LOSS-AWARE FILTER PRUNING
Huoxiang Yang, Haogang Feng, Bohuai Xiao, Shenzhen University, China; Fanyang Meng, Pengcheng Laboratory, China; Yongsheng Liang, Shida Zhong, Shenzhen University, China

MLSP-P53.6: FLASH-UNLEARN: ON-THE-FLY, TRAINING-FREE LARGE LANGUAGE MODELS UNLEARNING THROUGH SUBSPACE DISTRIBUTION FILTERING
Ruyun Wang, Fuqing Zhu, Xiaodan Zhang, iie.ac.cn, China

MLSP-P53.7: FEDZKD: ZEROTH-ORDER DUAL-ADAPTER DISTILLATION FOR FEDERATED FINE-TUNING
Bo Ma, Yongqiang Gao, Yongmei Liu, Mingyu Pang, Inner Mongolia University, China

MLSP-P53.8: BREAKING THE FORGETTING-MEMORIZATION TRADE-OFF: A MEMORY-ADAPTIVE OPTIMIZER FOR EFFECTIVE LARGE LANGUAGE MODELS UNLEARNING
Ruyun Wang, Fuqing Zhu, Xiaodan Zhang, iie.ac.cn, China

MLSP-P53.9: DATKD: DECOUPLED ATTENTION TRANSFER KNOWLEDGE DISTILLATION FOR VISION TRANSFORMERS
Ziyuan Chen, Xuesheng Zhou, Siyu Wang, Chen Chen, Yifan Li, Guitao Cao, East China Normal University, China

MLSP-P53.10: Utilising Gradient-Based Proposals Within Sequential Monte Carlo Samplers for Training of Partial Bayesian Neural Networks
Andrew Millard, Joshua Murphy, University of Liverpool, United Kingdom of Great Britain and Northern Ireland; Zheng Zhao, Linköping University, Sweden; Simon Maskell, University of Liverpool, United Kingdom of Great Britain and Northern Ireland