2nd MMFM-BIOMED Workshop
MMFM-BIOMED @ CVPR 2026
Biomedical data spans diverse modalities across biological scales - from molecular genomics and cellular microscopy to tissue pathology, organ-level radiology, and patient-level electronic health records. While each modality provides unique insights, integrating these heterogeneous data sources remains a significant challenge in creating comprehensive biomedical understanding.
The Multimodal Foundation Models for Biomedicine (MMFM-BIOMED) workshop brings together experts across disciplines to tackle this challenge. The workshop explores two critical questions:
What are the core limitations of existing multimodal learning techniques when applied to biomedical data? Challenges include cross-modal alignment between data with different spatial and temporal resolutions; handling extreme data imbalances between well-annotated and sparse modalities; maintaining modality-specific contexts while enabling knowledge transfer across domains.
What transformative opportunities do multimodal foundation models unlock in biomedicine? Potential breakthroughs include multi-scale disease diagnosis by combining radiology images with pathology slides; personalized treatment by integrating wearable sensor data with genomic profiles; context-aware operations by synchronizing surgical videos with patient records.
Stanford University
Stanford University
EPFL
Princeton University
We invite short, non-archival paper submissions (4 pages maximum excluding references using CVPR 2026 template) that explore both challenges and opportunities in multimodal foundation models for biomedicine. We encourage two types of submissions:
Papers highlighting limitations in existing methods, especially simple yet intuitive approaches that unexpectedly lead to negative outcomes.
Papers showcasing novel applications, especially in underexplored areas such as drug discovery and surgery.
Selected papers will be featured as posters, and four will receive spotlight oral presentations.
Submission platform: OpenReview (MMFM-BIOMED)
Submission deadline: May 1, 2026
Notification date: May 10, 2026
Workshop date: June 3, 2026
Reminder: Please bring your poster (following CVPR 2026 poster requirement) to the workshop
All accepted papers participate in the workshop poster session. Four papers are selected for oral presentations. We will update the poster floor location soon. Please design and print your poster and bring it with you to the workshop.
Poster guidelines: follow the official CVPR 2026 poster printing information for workshop dimensions (half size), templates, logistics, and optional onsite printing.
| Poster Board ID | Format | Title | Authors |
|---|---|---|---|
| TBD | Oral | Automated Report-Derived Oncology VQA Benchmark for Evaluating Vision-Language Models on 3D Medical Imaging | Bo Liu, Hanxue Gu, Xiangru Li, Zheren Zhu, Jacob Ellison, Kang Wang, Janine M. Lupo, Yang Yang, Hui Lin |
| TBD | Oral | Reality vs. Priors: Atypical Anatomy Breaks Vision-Language Models | Leon Mayer, Piotr Kalinowski, Caroline Maria Ebersbach, Marcel Knopp, Tim Rädsch, Evangelia Christodoulou, Annika Reinke, Fiona R. Kolbinger, Lena Maier-Hein |
| TBD | Oral | Challenges in Retrieval and Context Engineering for Multimodal Patient Timelines | Ryan D'Cunha, Ryan Nayebi, Jason Alan Fries |
| TBD | Oral | Too Sure to Be Right: High-Confidence Wrong and Latent Failure Signals in Medical VQA | Haohao Zhu, Jiayu Zhou |
| TBD | Poster | BSMAD: Bridging Semantic and Structural Manifolds for Robust Cross-Modality Medical Anomaly Detection | Shih-Chih Lin, Chia-Lin Lee, Yun-Tung Chu, Jia-Xian Jian, Wei-Chieh Sun, Fang-Yi Lin |
| TBD | Poster | PSF-Med: A Clinician-Audited Benchmark for Paraphrase Sensitivity in Medical Vision-Language Models | Binesh Sadanandan, Vahid Behzadan, Lekshmy Jayan, Arun Gopinatha Kurup |
| TBD | Poster | SCOPE: Self-Consistent Patch Reconstruction with Pathology-Aware Prototype Alignment for Anatomical Neglect in CXR Report Generation | Ngo Xuan Cuong |
| TBD | Poster | Fine-Tuning BiomedParse for Stroke Detection and Segmentation on CT: A Comparison with Gemini 2.5 Pro and GPT-5 | Artun Gunturkun, Halil Ibrahim Gulluk, Özgür Ilker Koska, Olivier Gevaert |
| TBD | Poster | Exploring Prompt Alignment with Clinical Factors in Zero-Shot Segmentation VLMs for NSCLC Tumor Segmentation | Suraj Pai, Thibault Heintz, Cosmin Ciausu, Marion Tonneau, Hugo Aerts, Raymond Mak |
| TBD | Poster | Position: Why Medical AI for the Global South Must Be Built on Different Technical Principles | Azmine Toushik Wasi, Mohsin Mahmud Topu, Mahfuz Ahmed Anik, Md. Manjurul Ahsan |
| TBD | Poster | Multimodal Predictors of Heterogeneity of Treatment Effects in Transcranial Direct Current Stimulation for Knee Osteoarthritis Pain: A Machine Learning Analysis | Seoyoung Kim, Yeri Kim, Chiyoung Lee, Juyoung Park, Allison Huff, Huanrui Yang, Heewon Kim |
| TBD | Poster | Does Language Shift Break Medical Vision-Language Models? Indonesian Radiology Visual Question Answering Case Study | Pieter Christy Yan Yudhistira, Dzaki Rafif Malik, Novanto Yudistira |
| TBD | Poster | Directional Pathology–Omics Discordance from Frozen Whole-Slide Foundation Embeddings Across Lung and Kidney Cancer | Kuan-Ting Wu |
| TBD | Poster | When Pretraining Fails to Transfer: Diagnosing Representation Failure in fMRI Foundation Models | Vijay Srinivas P., Amrutha Veluppal |
| TBD | Poster | Self-Supervised Vision Transformers for CBCT-Based Detection of Temporomandibular Joint Osteoarthritis | Shradhdha Trivedi, Vrundan Sojitra |
| TBD | Poster | Label-Efficient Multimodal Trust Mapping for MRI | Jacob Ellison, Amir Sadikov, Duan Xu, Janine M. Lupo |
| TBD | Poster | RadDiff: Describing Differences in Radiology Image Sets with Natural Language | Xiaoxian Shen, Yuhui Zhang, Sahithi Ankireddy, Xiaohan Wang, Maya Varma, Henry Guo, Curtis Langlotz, Serena Yeung-Levy |
| TBD | Poster | When Prompts Mislead: Textual Dominance and Diagnostic Bias in MLLMs | Inhyuk Park, Doohyun Park |
| TBD | Poster | JASPR: Joint Spatial Representation learning of histology and spatial genomics for improved virtual genomic screening and clinical prognostication | Marija Pizurica, Eric Zimmermann, Neil Tenenholtz, James Brian Hall, Olivier Gevaert, Ava P. Amini, Lorin Crawford, Kristen A. Severson |
| TBD | Poster | Foundation Model–Driven Interpretable Discovery of Prognostic Signals Beyond Clinical Records in Histology and Spatial Proteomics | Yutong Sun, Kyeong Joo Jung, James D. Brooks, Chrystal Chadwick, Sanghee Cho, Soumya Ghose, Elizabeth McDonough, Jianwei Qiu, Robert West, Fiona Ginty, Raghu Machiraju, Parag Mallick |
| TBD | Poster | Multimodal Alignment Improves Generalizability of Genomic Biomarker Prediction in Computational Pathology | Ekaterina Redekop, Eric Zimmermann, Ava P. Amini, Alex Xijie Lu, Neil Tenenholtz, James Brian Hall, Lorin Crawford, Kristen A. Severson |
| TBD | Poster | Predicting Brain Tumor Recurrence from Multimodal, Longitudinal Patient Data | Divyanshu Tak, Diya Sreedhar, Hugo Aerts, Benjamin H. Kann |
| TBD | Poster | On the Trade-offs of LLM-Augmented Multimodal Foundation Models for Clinical Image Classification | Zhaohui Liang, Niccolo Marini, Sivaramakrishnan Rajaraman, Zhiyun Xue, Sameer Antani |
| TBD | Poster | Objective-Aligned Direct Answer SFT for Robust Multi-Frame Medical VQA | Site Li, Jianyi Hao, Xiaofeng Liu |
| TBD | Poster | When Multimodal Models Stop Listening: Modality Imbalance Induces Dominant-Modality Bias in Biomedicine | Dineth Jayakody |
| TBD | Poster | A Landmark-Based Panoramic Radiograph Dataset for Periodontal Severity and Comprehensive Dental Screening | Nayoon Kwon, Jongwon Choi, Jung Seok Lee |
| TBD | Poster | An Open Multi-Center Whole-Body FDG PET/CT Foundation Model for Tumor Segmentation | Xiaofeng Liu, Qianru Zhang, Thibault Marin, Menghua Xia, Chi Liu, Georges El Fakhri, Jinsong Ouyang |
Stanford University
Stanford University
UCLA
University of Michigan
MBZUAI
Johns Hopkins University
Microsoft Research
Stanford University
1st edition: MMFM-BIOMED @ CVPR 2025