Accepted Abstracts

Fourth Workshop on Multimodal AI · 11–12 June 2026 · UCL East Campus, London, UK

NameTitle
Sesha Kiran GonaboyinaMultimodal Telemetry Fusion for Intelligent RAN Operations: Integrating OSS, EDR, and Device Signals at National Scale
Tadiyos Hailemichael MamoCausality-Aware Multimodal Representation Learning for Heart Failure Risk Prediction from EHRs
Chidozie ManagwuA Hybrid Retrieval-Augmented Generation (RAG) and Language Model Framework for Evidence-Grounded Review Systems
Vaibhava Lakshmi RavideshikPredictive vs Discriminative Representation Learning in Multimodal Systems
Raneem KnajMultimodal AI for Mental Health Beyond Benchmark Datasets: Dataset Bias, Limited Ecological Validity, and the Gap Between Technical Performance and Real-World Clinical Utility
Omotayo OmoyemiMultimodal AI for Accessible Communication and Digital Health: The AURA Framework
Bulugahapitiye Mohottalalage Amantha VirajA Synergistic Tri-Modal Framework for Alzheimer’s Disease Diagnosis Using Self-Supervised 3D Swin Transformer and LSTM with Gated Fusion
Jiayang ZhangComputational Design of Grafted Motifs on Protein Scaffold
Ifedamola AdefisoyePredicting Hiring Outcomes from Application Artifacts: A Multi-Modal Learning Approach
Hazrat AliHyperglycaemic Event Prediction through Continuous Glucose Monitoring on Hardware Efficient Deep Learning
Hazrat AliMask-conditioned synthetic prostate MRI volumes using a denoising diffusion probabilistic model
Yanni SunMultimodal analysis of 底层(‘bottom social stratum’) self-Representations on Kuaishou: A scalable video-based approach
Chidiebere NjokuA Behaviour-Aware Multimodal AI System for Personalised Learning and Intelligent Educational Assistance
Shrankhla PandeyAcoustic and Linguistic Speech Markers for Psychosis Severity Prediction
Misbah farooqCMAT: Cross-Modal Attention-Weighted Triplet Loss for Multimodal Emotion Recognition
Satnam SuraeCANOPY - a multi-modal heterograph transformer model for biomanufacturing-relevant strain engineering
Zhenghua ChenRethinking Multimodal Spatial Understanding: From Language to Geometry
Xiang LiFrom Lab to Market: Building Bridges for Multimodal AI Commercialisation
Baraa Al JorfHow Effectively Can LLM Agents Synthesize Multimodal Clinical Data?
Faith SodipeA Unified Multimodal Deep Learning Architecture for Cross-Modal Understanding and Cross-Modal Support
Dhruv MenonA chemical language model for reticular materials design
Dongsheng WenKagome intermetallic database assembled by topology + geometry approach
Zixuan HuangDiffMG-Trans: A Multimodal Framework for Safety-Critical Scenario Generation in Autonomous Vehicle Testing
Haoming XiangData-Driven Resilience in Social Housing: Enhancing Retrofit Strategies via Physics-Informed AI
Lin Yuanbo WuA Multi-Agent Collaborative Framework for Wind Farm Operation and Maintenance with RAG-based Reasoning
Haili YeMultimodal Hypergraph Modelling of Structural-Functional Connectivity Coupling for Interpretable ADHD Brain Network Analysis
Jimin LeeClosing the Loop on UI Bugs: A Multi-Agent Framework using Vision-Language Models for Automated UI Repair
Damith SenadeeraCoLoRSMamba: Conditional LoRA-Steered Mamba for Supervised Multimodal Violence Detection
Jonathan CarterNext-Token Prediction Enables Scalable Learning of Sleep Physiology
Nicola MorleyMaterials Informatics for Magnetostrictive Materials
Shweta ChaturvediMulti model AI and encrypted evidence: Reimagining whatsapp fornsics in india
Jingyu HuProbing and Fusion of Foundation Model Representations for Multimodal Cancer Analysis
Hansa MukherjeeDynamic Marine Protected Areas: Multimodal AI for Climate-Responsive Ocean Governance
Jiin Woei LeeLinking Experimental and Computational Evidence in Biomaterials
Jiang ChangSemantic-Guided Cross-Modal Alignment for Multimodal Depression Detection
Sakib AhammedTowards Fair and Semantic Coverage-Aware Learning for Underrepresented Visual Concepts
Pranjit DekaA Multimodal AI Framework for Healthcare Signature Detection and Sensor Optimisation
Kewei ZhuMOF in Water: Screening Water-Stable Metal-Organic Frameworks via ReadMOF diagram
Kewei ZhuReadMOF: Leveraging Systematic Chemical Nomenclature for Machine Learning Applications in Metal-Organic Frameworks
Francesco MurtasTemporal Dynamics of Brain–Body Responses to Music: A Multimodal Analysis
Mohammod SuvonInterpretable and flexible multimodal AI with high-fidelity modality knowledge transfer for low-cost assessment of cardiac haemodynamics
Jichun LiAn effective fragment-based dual conditional diffusion framework for molecular generation
Ricardo ValenciaAdapting multi-modal variational autoencoders for microbiome data
Arianna De VecchiA Multimodal Dataset for Cognitive Load, Stress, and Behaviour Analysis in a Collaborative Escape Room
Giuseppe TripodiUncertainty-Aware Multimodal Cancer AI: A Conformal Prediction Study across Pathology and Genomics
Longdan HaoMultimodal AI-Driven Framework for Automated Muscle Segmentation and NMD Diagnosis
Reed NaidooGenerative Cross-Modal Alignment Between Morphological and Transcriptomic Representations of Cellular Perturbation
Farah ShamoutMultimodal AI for Patient-Centered Healthcare Technologies
Cristina PalmeroUDIVA-HHOI: A Multimodal Dataset for Context-Aware Multi-Actor Interaction Understanding
George SearleIntegrating ECG and PPG Features for Hypertension Detection Using Multimodal Deep Learning Approaches
Aman JatAssessing Equity Gaps in Artificial Intelligence Tools for Mental Health Diagnosis and Triage: A CPRD Cohort Study of 7.19 Million Adults with Multiple Long-Term Conditions