Toward Trustworthy Vision-Language Models in the Wild: Theory, Algorithm and Application
Overview
Vision-Language Models (VLMs) have revolutionized multimedia applications by enabling open-vocabulary search and generation. While significant strides have been made in developing powerful VLMs, the field remains in the early stages of rigorously evaluating and understanding their real-world vulnerabilities, both empirically and theoretically. In response to this important but under-explored gap, the workshop aims to provide a forum for researchers to share advanced in theories, algorithms and applications of trustworthy multi-modal learning, fostering diverse viewpoints on core principles and emerging techniques for developing trustworthy VLMs in the wild.
Organizers
- Bo Peng (PhD Student at University of Technology Sydney)
- Sean Du (Assistant Professor at Nanyang Technological University)
- Zhen Fang (Lecturer at University of Technology Sydney)
Workshop Website
LSC'26: The 9th Annual ACM Workshop on the Lifelog Search Challenge
Overview
The LSC is a participation workshop where teams compete to develop leading-edge retrieval tools for personal lifelog data. Originally focused on a live interactive search competition, LSC now adds two new tracks to welcome broader lifelog research and lower the barrier to entry for new teams.
Organizers
- Allie Tran (Dublin City University)
- Werner Bailer (Joanneum Research)
- Graham Healy (Dublin City University)
- Steve Hodges (Lancaster University)
- Duc Tien Dang Nguyen (University of Bergen)
- Björn Þór Jónsson (Reykjavik University)
- Wolfgang Hürst (Utrecht University)
- Luca Rossetto (Dublin City University)
- Klaus Schoeffmann (Klagenfurt University)
- Minh-Triet Tran (VNU HCM University of Science)
- Liting Zhou (Dublin City University)
- Cathal Gurrin (Dublin City University)
Workshop Website
The 7th International Workshop on Intelligent Cross-Data Analysis and Retrieval (ICDAR 2026)
Overview
Multimedia retrieval is entering a transformative era. As we move toward 2026, the field is expanding beyond digital archives into Physical AI, where autonomous systems must reason over multimodal sensory data in real-time. Simultaneously, the rise of generative media and decentralized computing has made Media Verification and Privacy-Preserving Learning critical pillars of trustworthy intelligence.
The 7th ICDAR workshop invites researchers to submit "Brave New Ideas" that bridge the gap between digital retrieval, physical interaction, and ethical data governance. We seek contributions that leverage Multimodal AI, Federated Learning, and Neurosymbolic reasoning to make cross-modal analytics more intelligent, secure, and context-aware.
Topics of Interest
We welcome original research and system demonstrations on topics including, but not limited to:
- Physical & Embodied AI: Retrieval for robotics, autonomous agents, and digital twins in smart cities.
- Media Integrity & Trust: Detection of "cheapfakes," re-contextualized misinformation, and AI-generated content verification.
- Decentralized Intelligence: Federated and Edge AI for privacy-preserving cross-modal retrieval.
- Advanced Reasoning: Large Multimodal Models (LMMs) and Neurosymbolic AI for explainable retrieval.
- Human-Centred Applications: Intelligent sensing for healthcare, precision agriculture, and sustainable development goals (SDGs).
Organizers
- Minh-Son Dao (NICT, Japan)
- Son Tran (Deakin University, Australia)
- Duc-Tien Dang-Nguyen (University of Bergen, Norway)
- Cathal Gurrin (DCU, Ireland)
- Michael Riegler (Simula, Norway)
Workshop Website
The 5th ACM International Workshop on Multimedia AI against Disinformation (MAD'26)
Overview
The Multimedia Against Disinformation Workshop, in its 5th Edition, explores AI-driven approaches for detecting, analyzing, and mitigating disinformation across text, audio, images, and video.
With the rise of social networks and AI-mediated communication, disinformation campaigns, from deepfakes to LLM-generated content, pose growing challenges to journalism, fact-checking, and public discourse.
Topics of Interest
We invite contributions on topics such as:
- Multimedia disinformation detection
- Multimodal verification
- Synthetic and manipulated media detection
- Social media analysis
- Robust, fair, and explainable AI tools
- Large Language and Multimodal Models
- Dataset development and governance
- Benchmarking and evaluation frameworks
- Emerging AI-driven threats
Organizers
- Dan-Cristian Stanciu (National University of Science and Technology Politehnica Bucharest, Romania)
- Symeon Papadopoulos (CERTH-ITI, Greece)
- Roberto Caldelli (CNIT and Mercatorum University, Italy)
- Milica Gerhardt (Fraunhofer IDMT, Germany)
- Bogdan Ionescu (National University of Science and Technology Politehnica Bucharest, Romania)
- Giorgos Kordopatis-Zilos (Czech Technical University in Prague, Czechia)
- Adrian Popescu (CEA LIST, France)
- Vera Schmitt (Technical University Berlin, Germany)