MO2.L3.5
LANGVISION-LORA-NAS: NEURAL ARCHITECTURE SEARCH FOR VARIABLE LORA RANK IN VISION LANGUAGE MODELS
Krishna Teja Chitty-Venkata, Murali Emani, Venkatram Vishwanath, Argonne National Laboratory, United States
Session:
MO2.L3: Machine Learning in Signal Processing 3 Lecture
Track:
[ML] Machine Learning in Signal Processing
Location:
Room 1
Presentation Time:
Mon, 15 Sep, 11:00 - 11:15 Anchorage Time (UTC -8)
Session Chair:
Hichem Sahbi, CNRS Sorbonne University
Presentation
Discussion
Resources
No resources available.
Session MO2.L3
MO2.L3.1: LINEA: FAST AND ACCURATE LINE DETECTION USING SCALABLE TRANSFORMERS
Sebastian Janampa, Marios Pattichis, The University of New Mexico, United States
MO2.L3.2: CMTM: CROSS-MODAL TOKEN MODULATION FOR UNSUPERVISED VIDEO OBJECT SEGMENTATION
Inseok Jeon, Suhwan Cho, Minhyeok Lee, Seunghoon Lee, Minseok Kang, Jungho Lee, Chaewon Park, Donghyeong Kim, Sangyoun Lee, Yonsei University, Korea (South)
MO2.L3.3: DMSO: A DYNAMIC MOMENTUM-SMOOTHING OPTIMIZER FOR LEARNED IMAGE COMPRESSION
Chao Li, Harbin Institute of Technology, Shenzhen, China; Chuanmin Jia, Peking University, China; Fanyang Meng, Peng Cheng Laboratory, China; Hao Qi, Harbin Institute of Technology, Shenzhen, China; Siwei Ma, Peking University, China; Yongsheng Liang, Harbin Institute of Technology, Shenzhen, China
MO2.L3.4: Robust Multi-Label Learning with Human-Guided and Foundation Model-Aided Crowd Framework
Faizul Rakib Sayem, Shahana Ibrahim, University of Central Florida, United States
MO2.L3.5: LANGVISION-LORA-NAS: NEURAL ARCHITECTURE SEARCH FOR VARIABLE LORA RANK IN VISION LANGUAGE MODELS
Krishna Teja Chitty-Venkata, Murali Emani, Venkatram Vishwanath, Argonne National Laboratory, United States
MO2.L3.6: GEOMETRIC MEAN IMPROVES LOSS FOR FEW-SHOT LEARNING
Tong Wu, University of Tsukuba, Japan; Takumi Kobayashi, National Institute of Advanced Industrial Science and Technology, Japan
Contacts