2:00 PM – 2:05 PM

Opening Remarks and Welcome

Session I: Multimodal Misinformation, Safety, and Social Good

2:05 PM – 3:00 PM

• Laxmi Thapa et al. — Concept-Grounded Detection of Vaccine Misinformation in Multimodal Content Using Interpretable Vision-Language Models

• Siyuan Chen et al. — No Evidence, No Problem: When Less is More for Out of Context Multimodal Misinformation Detection

• Ali Anaissi et al.— MAF-GAN: Modality-Aware Fusion GAN for Multimodal Fake News Detection

• Mohamed Bayan Kmainasi et al. — Can Thinking Models Think to Detect Hateful Memes?

• Siam Shibly Antar et al. — UniSafe: Modality-Agnostic Hateful Content Detection via Shared-Space Projection

• Gianmarco Cafferata et al. — Fair Geolocation Extraction from Humanitarian Documents using Large Language Models

• Ke Zhu — Constitutional Agents: Auditing and Mitigating Intersectional Bias in Multimodal Decision-Making Chains

3:00 PM – 3:40 PM

Keynote I (Tom Gedeon, Curtin University, Perth, WA, Australia)

Session II: Multimodal Learning, Foundation Models, and AI Systems

3:40 PM – 4:35 PM

• Mohammadhossein Ahmadi et al. — Frugal Agents: Efficient Bio Reasoning via Long-Sequence Compression and Prompt-Gated Memory

• Muhammad Haseeb et al. — From Code to Rubrics: A Multimodal Evaluation of LLM Systems for Automated Feedback Generation

• Zixing Song and Irwin King — Semi-supervised Instruction Tuning for Large Language Models on Text-Attributed Graphs

• Qianqi Zhang et al. — Fed-S2: Adversarially Disentangled Federated Multimodal RAG for Safety-Critical Long-Tail Fault Diagnosis

• Qian Liu et al. — Mixture of Orthogonal Decomposition for Semantically Generalisable Multimodal Deepfake Detection with Deepfake Manifold Disentanglement

• Jialu Yang et al. — Multimodal Deployment Risks in Manufacturing AI: A Survey of Boundary Failures, Taxonomy, and Governance in Industry 5.0

• Md Rafiqul Islam et al. — Do You Think What I Think? A Qualitative Study for Maximizing User Engagement through Latent Visual Properties

4:35 PM – 5:15 PM

Keynote II (Kyriaki Kalimeri, ISI, Italy; UNICEF)

Session III: Human-Centered Multimodal AI Applications

5:15 PM – 5:30 PM

• Niranjana Arun Menon et al. — Exploring the Influence of Lifestyle, Social Health, and Demographic Factors on Psychological Well-being and Engagement Levels

• Sumeet Kumar et al. — Analyzing the Impact of Image Novelty and Text Emotion on Meme Engagement: Evidence from Roe vs. Wade Verdict

5:30 PM

Closing Remarks