I am very excited to announce that we are organizing a workshop at ICML 2024 titled "Accessible and Efficient Foundation Models for Biological Discovery." Our workshop aims to bridge the growing gap between machine learning research on biology-inspired problems and the actual broad-based use of ML in the lab or the clinic, with a focus on accessibility and efficiency concerns surrounding large ML models. We want to highlight work that makes foundation models (and broader ML) more accessible to biologists, truly incorporating them into the discovery process. This could involve considerations like efficiency, lowering GPU requirements, democratization via web-accessible frameworks, lab-in-the-loop frameworks, etc.
We welcome submissions on a wide range of topics, including but not limited to:
Parameter-, memory-, and compute-efficient foundation models for biological or clinical data
Algorithms for training efficient generative models in biology
Efficient fine-tuning, compression, and quantization of biomedical and clinical foundation models
Accessible cloud/web-based methods to enable biological discovery
Knowledge distillation and transfer learning across biological contexts
Lab in the loop: iterative approaches to refine ML models based on initial experimental results
Hypothesis-driven machine learning in biology and uncertainty modeling in biological foundation models.
Submission Instructions
Submissions must present original research that has not been previously published or is under review elsewhere. The main body of the paper can be up to four pages long. For detailed submission instructions, template, and the OpenReview submission link, please visit the workshop webpage at https://accml.bio.
Journal Partner
We are in discussions with a partner journal to provide an expedited review process to some of the accepted papers. We will share more details on that soon on our website.
Key Dates
Submission Portal Opens: April 5, 2024
Submission Deadline: May 20, 2024 (Anywhere on Earth)
Notification of Acceptance: June 17, 2024 (Anywhere on Earth)
Workshop Date: July 27, 2024.