SLP-P10.5
TASS: TASK ALIGNED SUBSPACE SELECTION FOR KNOWLEDGE PRESERVING FINE-TUNING
Qi Jing, Peng Qiao, Rongchun Li, National University of Defense Technology, China
Session:
SLP-P10: Efficient Learning and Inference for LLMs III Poster
Track:
Speech and Language Processing [SL]
Location:
Poster Area 30
Presentation Time:
Tue, 5 May, 16:30 - 18:30
Presentation
Discussion
Resources
No resources available.
Session SLP-P10
SLP-P10.1: Tackling Data Heterogeneity in Parameter-Efficient Federated Fine-Tuning of Large Language Models
Jun Liu, Yunming Liao, Hongli Xu, Yang Xu, University of Science and Technology of China, China
SLP-P10.2: A Unified Four-Stage Dynamic Cycle for Robust Federated Fine-Tuning of Large Language Models
Benying Tan, Jie Ren, Yujie Li, AHMAD CHADDAD, Guilin University of Electronic Technology, China
SLP-P10.3: HCL-CSC: HIERARCHICAL CONTRASTIVE LEARNING WITH IDS-AWARE CHARACTER SIMILARITY FOR CHINESE SPELLING CORRECTION
Shuo Wang, Chaodong Tong, Lei Jiang, Institute of Information Engineering, Chinese Academy of Sciences, China
SLP-P10.4: PARSIMONY, ORDER AND BALANCE: PRINCIPLES FOR COMPRESSING MIXTURE-OF-EXPERTS MODELS
Shuangyou Feng, University of Science and Technology of China, China; Chenyu Xu, Iowa State University, China; Yi Ding, University of Science and Technology of China, China; Zhi Liang, Kangma (Shanghai) Biotech Ltd, China; Sihai Zhang, University of Science and Technology of China, China
SLP-P10.5: TASS: TASK ALIGNED SUBSPACE SELECTION FOR KNOWLEDGE PRESERVING FINE-TUNING
Qi Jing, Peng Qiao, Rongchun Li, National University of Defense Technology, China
SLP-P10.6: FGGM: FISHER-GUIDED GRADIENT MASKING FOR CONTINUAL LEARNING
Chao-Hong Tan, Qian Chen, Wen Wang, Yukun Ma, Chong Zhang, Chong Deng, Qinglin Zhang, Xiangang Li, Jieping Ye, Alibaba Group, China
SLP-P10.7: SCFusion: Semantic and Contextual Fusion for Document-level Event Argument Extraction
Rong Wang, Zhicheng Wu, Fan Gao, Qingqiang Wu, Meihong Wang, School of Informatics, Xiamen University, China
SLP-P10.8: ADAEVOL: DYNAMIC ADAPTER MERGING FOR EFFECTIVE CONTINUAL LEARNING AND KNOWLEDGE TRANSFER IN LARGE LANGUAGE MODELS
Ran Liu, Min Yu, Jianguo Jiang, Institute of Information Engineering, Chinese Academy of Sciences. University of Chinese Academy of Sciences., China; Gang Li, Deakin University, Australia; Rongsheng Li, Harbin Engineering University, China; Mingqi Liu, Institute of Information Engineering, Chinese Academy of Sciences, China; Zhen Xu, Weiqing Huang, Institute of Information Engineering, Chinese Academy of Sciences. University of Chinese Academy of Sciences., China; Ming Liu, Deakin University, Australia
SLP-P10.9: VIEWLEARNER: GNN-DRIVEN PRE-BUILT VIEWS FOR MULTI-TABLE NL2SQL
Gege Qi, Computer Network Information Center, Chinese Academy of Sciences;University of Chinese Academy of Sciences, China; Chenfeng Su, University of Chinese Academy of Sciences, China; Wenjing Chang, Computer Network Information Center, Chinese Academy of Sciences;University of Chinese Academy of Sciences, China; Yue wang, Jianjun Yu, Computer Network Information Center, Chinese Academy of Sciences, China
SLP-P10.10: Spectral Logit Sculpting: Adaptive Low-Rank Logit Transformation for Controlled Text Generation
Jin Li, Zhebo Wang, Zhejiang University, China; Tianliang Lu, People’s Public Security University of China, China; Mohan Li, Guangzhou University, China; Wenpeng Xing, Meng Han, Zhejiang University, China
Contacts