MLSP-L3.2
EMOE: EIGENBASIS-GUIDED ROUTING FOR MIXTURE-OF-EXPERTS
Anzhe Cheng, Shukai Duan, Shixuan Li, Chenzhong Yin, Mingxi Cheng, Shahin Nazarian, Paul Thompson, Paul Bogdan, University of Southern California, United States of America
Session:
MLSP-L3: Deep Learning Architectures for Large-Scale Models Oral
Track:
Machine Learning for Signal Processing [ML]
Location:
Room 117
Presentation Time:
Tue, 5 May, 14:20 - 14:40
Presentation
Discussion
Resources
No resources available.
Session MLSP-L3
MLSP-L3.1: ILSA: Information Loss-guided Sparsity Allocation for Pruning Large Language Models
Lin Li, Yan Wang, Zhuopeng Wang, Feilong Bao, Inner Mongolia University, China
MLSP-L3.2: EMOE: EIGENBASIS-GUIDED ROUTING FOR MIXTURE-OF-EXPERTS
Anzhe Cheng, Shukai Duan, Shixuan Li, Chenzhong Yin, Mingxi Cheng, Shahin Nazarian, Paul Thompson, Paul Bogdan, University of Southern California, United States of America
MLSP-L3.3: Intrinsic Semantic Consistency Enhancement for Robust Hierarchical Understanding in VLMs
Zhongze Wu, Central South University, China; Yitian Long, Fudan University, China; Feng Yang, Southeast University, China; Yueyi Luo, Central South University, China; Shan You, SenseTime Research, China; Xiu Su, Jun Long, Central South University, China
MLSP-L3.4: Dynamic Self-Distillation Former for Weakly Supervised Semantic Segmentation
Fanxuan Kong, Jun Lu, Heilongjiang University, China
MLSP-L3.5: ADAPTIVE SHARED EXPERTS WITH LORA-BASED MIXTURE OF EXPERTS FOR MULTI-TASK LEARNING
Minghao Yang, Ren Togo, Guang Li, Takahiro Ogawa, Miki Haseyama, Hokkaido University, Japan
MLSP-L3.6: nGPT as a Scalable Architecture for Speech Recognition and Translation
Nune Tadevosyan, Nithin Rao Koluguri, Monica Sekoyan, Piotr Zelasko, Nikolay Karpov, Jagadeesh Balam, Boris Ginsburg, NVIDIA, Armenia
Contacts