Introduction to the Workshop

The rapid evolution of Foundation Models and Cognitive AI is reshaping biomedical research, clinical decision-making, and healthcare innovation. Large Language Models, Vision-Language Models, multimodal foundation models, and Vision-Language-Action Models are enabling new approaches to biomedical imaging, pathology, multi-omics analysis, drug discovery, personalized medicine, clinical decision support, and robotic-assisted interventions. In parallel, Cognitive AI is advancing systems with capabilities for reasoning, contextual understanding, evidence integration, adaptive decision-making, and effective AI-human experts collaboration. Bringing these complementary directions together creates new opportunities for AI systems that can process complex biomedical data while providing more reliable, interpretable, and context-aware support for scientific and clinical decisions. Important challenges remain in data scarcity and heterogeneity, generalization, factual grounding, hallucination mitigation, uncertainty estimation, interpretability, fairness, reproducibility, human–AI interaction, and safe real-world deployment. The WACV 2027 Workshop on Foundation AI for Biomedical Reasoning, Imaging, and Cognition (FABRIC 2027) brings together researchers, clinicians, practitioners, and industry experts to advance both the development of foundation models for biomedical applications and the emerging capabilities required for trustworthy Cognitive AI. The workshop will provide a forum for presenting original research, fostering interdisciplinary collaboration, and exploring advances in multimodal learning, reasoning, model design, human–AI collaboration, evaluation, trustworthiness, and ethical deployment. We invite contributions spanning foundational model development, biomedical reasoning, performance optimization, multimodal integration, knowledge representation, adaptive and human-in-the-loop AI, real-world biomedical applications, and the broader societal impact of these technologies.

 WORKSHOP CHAIRS

Call for Papers

We invite original research contributions related to Large Foundation Models (LFMs) for biology and biomedicine in (but not limited to) the following areas:

• Model Development and Adaptation

  • Pre-training and fine-tuning LFMs for biomedical and clinical domains

  • Multimodal data acquisition, curation, and annotation

  • Development, scalability, and optimization of architectures for biomedical data analysis
    
    

• Cognitive AI, Reasoning, and Human–AI Collaboration

  • Cognitive and reasoning-based AI for biomedical and clinical decision support 

  • Contextual understanding, evidence integration, and adaptive decision-making 

  • Human–AI interaction, clinician-in-the-loop systems, and collaborative workflows 

  • Communication of supporting evidence, uncertainty, and AI–human disagreement 

  • Adaptive and interactive learning from human feedback and new evidence

• Performance Enhancement Techniques

  • Prompt engineering, chain-of-thought (CoT) reasoning, and retrieval-augmented generation (RAG)

  • Reinforcement learning with human feedback (RLHF)

  • Data resampling for class balancing and integration of auxiliary weak learner models
    
    

• Knowledge Engineering and Representation

  • Generating knowledge graphs, biological networks, ontologies, and taxonomies

  • Multimodal alignment for biomedical question answering and decision support
    
    

• Applications in Biomedicine and Healthcare

  • Clinical risk prediction, disease diagnosis and prognosis, surgical planning, and personalized treatment

  • Drug discovery, pharmacogenomics, and personalized medicine

  • Biomedical imaging applications (radiology, pathology, histology, cells, transcriptomics, etc.)

  • Visual reasoning and question answering in clinical and biological domains

  • Nutrition-focused applications (dietary assessment, calorie estimation, meal analysis)

  • Case studies and real-world deployment in healthcare
    
    

• Evaluation, Benchmarking, and Reproducibility

  • Creation of benchmark datasets and evaluation metrics

  • Reproducibility challenges in biomedical LFM research
    
    

• Trustworthiness, Ethics, and Societal Impact

  • Trustworthiness, explainability, hallucination, and validation of results

  • Equity, fairness, bias, safety, and reliability in biomedical applications

  • Ethical considerations and interpretability of LFMs

Submission Guidelines

Please check: Call for Papers

All accepted papers will be published in the WACV Workshop 2027 proceedings and made publicly available approximately two weeks before the main WACV 2027 conference. 

Updates