MLSP-P2: Evaluation and Adaptation of Foundation Models
Poster
Tue, 5 May, 14:00 - 16:00
Location: Poster Area 5
Session Type: Poster
Session Chair: Peter Gerstoft, University of California, San Diego
Track: Machine Learning for Signal Processing [ML]
Click the to view the manuscript on IEEE Xplore Open Preview
 

MLSP-P2.1: EVALUATING BIAS IN SPOKEN DIALOGUE LLMS FOR REAL-WORLD DECISIONS AND RECOMMENDATIONS
Yihao Wu, Tianrui Wang, Yizhou Peng, Yi-Wen Chao, Xuyi Zhuang, Nanyang Technological University, Singapore; Xinsheng Wang, Shunshun Yin, Soul AI Lab, China; Ziyang Ma, Nanyang Technological University, Singapore
 

MLSP-P2.2: Adaptive Multi-Scale Correlation Meta-Network for Few-Shot Remote Sensing Image Classification
Anurag Kaushish, University of Petroleum and Energy Studies, India; Sudeshna Chakraborty, Galgotias University, India; Ayan Sar, Sampurna Roy, University of Petroleum and Energy Studies, India; Prashant Trivedi, BITS Pilani, India; Tanupriya Choudhury, Kanav Gupta, University of Petroleum and Energy Studies, India
 

MLSP-P2.3: EVALUATING TEST-TIME ADAPTATION FOR FACIAL EXPRESSION RECOGNITION UNDER NATURAL CROSS-DATASET DISTRIBUTION SHIFTS
John Turnbull, Shivam Grover, Amin Jalali, Ali Etemad, Queen's University, Canada
 

MLSP-P2.4: From Base to Novel: Semantic-Guided Visual Concept Transfer in Few-Shot Image Classification
Wen Chen, Yihua Tan, Xuanyu Xiang, Huazhong University of Science and Technology, China
 

MLSP-P2.5: S3: SYNONYMOUS SEMANTIC SPACE FOR IMPROVING ZERO-SHOT GENERALIZATION OF VISION-LANGUAGE MODELS
Xiaojie Yin, Qinghua Hu, Qilong Wang, Tianjin University, China
 

MLSP-P2.6: CAN DATA AUGMENTATION BECOME A PRIVACY SHIELD FOR MODEL INVERSION ATTACKS?
Wenzhe Yi, Xiaoyang Xu, Yong Zhuang, Juan Wang, Wuhan University, China
 

MLSP-P2.7: CZSRSSC: CONTINUAL ZERO-SHOT REMOTE SENSING SCENE CLASSIFICATION
Zhaohui Xu, Lei Zhou, Hainan University, China; Zhenchang Xia, Wuhan University of Technology, China; Zhe Shan, Wenwen Zhang, Chuanqiu Ren, Xia Xie, Hainan University, China

MLSP-P2.8: Sci-Phi: A Large Language Model Spatial Audio Descriptor
Xilin Jiang, Hannes Gamper, Sebastian Braun,

MLSP-P2.9: TOPOLOGICAL PERSISTENCE OF THE NEURAL EMBEDDING OF THE ARCHETYPAL SUBSPACE
Suryaka Suresh, Vinayak Abrol, Kaushik Kalyanaraman, Indraprastha Institute of Information Technology Delhi, India; Sumantra Dutta Roy, IIT Delhi, India

MLSP-P2.10: Adaptability of Vision Foundation Models for 3D Medical Image Segmentation
Suhyun Ahn, Donggyu Lee, Jinah Park,