MMSP-L4: Factuality and Hallucination Mitigation in LMMs
Oral
Fri, 8 May, 09:00 - 11:00
Location: Room 131+132
Session Type: Oral
Track: Multimedia Signal Processing [MM]
Click the to view the manuscript on IEEE Xplore Open Preview
Fri, 8 May, 09:00 - 09:20

MMSP-L4.1: Bifrost: An Adaptive Decision Framework for Regulating Depth of Thought in LLM Agents

Yanfang Zhou, Yuntao Liu, Academy of Military Sciences, China; Xiaodong Li, Jinlong Tian, National University of Defense Technology, China; Xinhai Xu, Academy of Military Sciences, China
Fri, 8 May, 09:20 - 09:40

MMSP-L4.2: CVSTIM: MITIGATING OBJECT HALLUCINATION IN MLLMS VIA CO-OCCURRENCE GUIDED VISUAL STIMULATION

Lan Wang, Ping Kuang, University of Electronic Science and Technology of China, China
Fri, 8 May, 09:40 - 10:00

MMSP-L4.3: Entropy-Aware Multimodal Preference Optimization for Factuality Alignment in Medical Visual Question Answering

Zhi Chen, Beiji Zou, Xiaoyan Kui, Central South University, China; Wenqi Lu, Manchester Metropolitan University, United Kingdom of Great Britain and Northern Ireland; Jinming Duan, University of Manchester, United Kingdom of Great Britain and Northern Ireland
Fri, 8 May, 10:00 - 10:20

MMSP-L4.4: SCHROMIND: MITIGATING HALLUCINATIONS IN MULTIMODAL LARGE LANGUAGE ¨ MODELS VIA SOLVING THE SCHRODINGER BRIDGE PROBLEM

Ziqiang Shi, Rujie Liu, Fujitsu Research & Development Center Co.,LTD., China; Shanshan Yu, Satoshi Munakata, Koichi Shirahata, Fujitsu Limited, Japan
Fri, 8 May, 10:20 - 10:40

MMSP-L4.5: MMFAST: RETHINKING VISION-LANGUAGE INTERACTION IN EFFICIENT MLLMS

shengyi xiong, independent researcher, Australia
Fri, 8 May, 10:40 - 11:00

MMSP-L4.6: ATTENTION TO DETAILS, LOGITS TO TRUTH: VISUAL-AWARE ATTENTION AND LOGITS ENHANCEMENT TO MITIGATE HALLUCINATIONS IN LVLMS

Jingyi Wang, Fei Li, Rujie Liu, Fujitsu Research and Development Center, China