IVMSP-P35: LLMs for Image Generation and Processing
Poster
Thu, 7 May, 14:00 - 16:00
Location: Poster Area 17
Session Type: Poster
Track: Image, Video and Multidimensional Signal Processing [IV]
Click the to view the manuscript on IEEE Xplore Open Preview

IVMSP-P35.1: LLMs Cannot Reliably Generate Architectural Design Images (Yet?): A Comprehensive Evaluation, Framework, and Benchmarks
Xiaoyang Fan, Wales College, Lanzhou University, Lanzhou 730000, Gansu, China, China; Wenjie Hou, School of Information Science & Engineering, Lanzhou University, Lanzhou 730000, Gansu, China, China; Ziteng Wang, Haoen Xin, Wales College, Lanzhou University, Lanzhou 730000, Gansu, China, China; Qingyuan Fei, School of Information Science & Engineering, Lanzhou University, Lanzhou 730000, Gansu, China, China

IVMSP-P35.2: LLM BASED EDGE-ASSISTED UAV INFERENCE AGAINST JAMMING
Liqing Ye, Changjin Yu, Liang Xiao, Jieling Li, Haoyu Chen, Xiaoyu Xu, Hongyi Chen, Xiamen University, China

IVMSP-P35.3: JUDGE BEFORE ANSWER: CAN MLLM DISCERN THE FALSE PREMISE IN QUESTION?
Jidong Li, Lingyong Fang, Haodong Zhao, Sufeng Duan, Gongshen Liu, Shanghai Jiao Tong University, China

IVMSP-P35.4: AN EFFECTIVE DATA AUGMENTATION METHOD BY ASKING QUESTIONS ABOUT SCENE TEXT IMAGES
Xu Yao, Lei Kang, Computer Vision Center, Spain

IVMSP-P35.5: CIDER: A Causal Cure for Brand-Obsessed Text-to-Image Models
Fangjian Shen, Zifeng Liang, Sun Yat-Sen University, China; Chao Wang, Sun Yat-Sen university, China; Wushao Wen, Sun Yat-Sen University, China

IVMSP-P35.6: BRIDGING VISION AND LANGUAGE WITH QUANTUM STATE FOR VIDEO-TEXT RETRIEVAL
Xingbang Liu, Ruonan Zhang, Libo Liu, Ningxia University, China

IVMSP-P35.7: LATENT DPO FOR CONCEPT ERASURE IN TEXT-TO-VIDEO DIFFUSION MODELS
Baisen Wang, Xiaomeng Fu, Runze He, Qiao Li, Chinese Academy of Sciences; University of Chinese Academy of Sciences, China; Yue Liao, National University of Singapore, Singapore; Si Liu, Beihang University, Singapore; Jiao Dai, Jizhong Han, Chinese Academy of Sciences; University of Chinese Academy of Sciences, China

IVMSP-P35.8: PSGS: TEXT-DRIVEN PANORAMA SLIDING SCENE GENERATION VIA GAUSSIAN SPLATTING
Xin Zhang, East China University of Science and Technology, China; Shen Chen, Zhejiang University, China; Jiale Zhou, East China University of Science and Technology, China; Lei Li, Beijing Institute of Technology, United States of America

IVMSP-P35.9: STIMULI-AWARE EMOTION ADAPTOR FOR ENHANCING LLM IN AFFECTIVE EXPLANATION CAPTIONING
Zhiyan Zhang, Peipei Song, University of Science and Technology of China, China; Jinpeng Hu, Hefei University of Technology, China; Weidong Chen, Lin Ni, Xun Yang, University of Science and Technology of China, China

IVMSP-P35.10: DISCRETE VISION TOKENIZATION FOR VISION-LANGUAGE ALIGNMENT IN AUTONOMOUS DRIVING
Junjie Xu, Beijing University of Posts and Telecommunications, China; Hang Zhao, None, China; Yitao Xiao, Shaoyong Guo, Jiewei Chen, Beijing University of Posts and Telecommunications, China; Yiquan Liang, Xifeng Hua, Xi Zhou, None, China