MO3.R15.1
GEOREASON: ALIGNING THINKING AND ANSWERING IN REMOTE SENSING VISION-LANGUAGE MODELS VIA LOGICAL CONSISTENCY REINFORCEMENT LEARNING
Wenshuai Li, Xiantai Xiang, Zixiao Wen, Guangyao Zhou, Ben Niu, Feng Wang, Lijia Huang, Qiantong Wang, Yuxin Hu, Aerospace Information Research Institute, Chinese Academy of Sciences, China
Session:
MO3.R15: Vision-Language & Reasoning in Remote Sensing Oral
Track:
AI and Big Data
Location:
TBD
Presentation Time:
Mon, 10 Aug, 13:45 - 14:00
Session Co-Chairs:
Gülsen Taskin, and Hongruixuan Chen, RIKEN Center for Advanced Intelligence Project (AIP)
Presentation
Discussion
Resources
No resources available.
Session MO3.R15
MO3.R15.1: GEOREASON: ALIGNING THINKING AND ANSWERING IN REMOTE SENSING VISION-LANGUAGE MODELS VIA LOGICAL CONSISTENCY REINFORCEMENT LEARNING
Wenshuai Li, Xiantai Xiang, Zixiao Wen, Guangyao Zhou, Ben Niu, Feng Wang, Lijia Huang, Qiantong Wang, Yuxin Hu, Aerospace Information Research Institute, Chinese Academy of Sciences, China
MO3.R15.2: INSTRUCT-ICL: INSTRUCTION-GUIDED IN-CONTEXT LEARNING FOR POST-DISASTER DAMAGE ASSESSMENT
Armin Zarbaft, Ehsan Karimi, Nhut Le, Maryam Rahnemoonfar, Lehigh University, United States
MO3.R15.3: THINK FIRST, ASSIGN NEXT: A COMPARISON-BASED CHAIN-OF-THOUGHT FRAMEWORK FOR POST-DISASTER DAMAGE ASSESSMENT
Ehsan Karimi, Nhut Le, Maryam Rahnemoonfar, Lehigh University, United States
MO3.R15.4: TOPOLOGY-AWARE PARAMETER-EFFICIENT ADAPTATION OF VISION FOUNDATION MODELS FOR ROAD EXTRACTION
Changhao Fan, Nanjing University of Science and Technology, China; Peng Zheng, Southeast University, China; Zebin Wu, Jin Sun, Junlong Zhou, Zhihui Wei, Nanjing University of Science and Technology, China
Contacts