AI researchers
Contribute representation, generative and graph learning, causal inference and reliability—while redefining tasks and evaluation with domain experts.
OPEN COMMUNITY
AI4SC is not a closed laboratory built around one discipline. We aim for problem-led collaboration that respects expertise and shares standards of evidence, so different research languages can genuinely understand one another.
Contribute representation, generative and graph learning, causal inference and reliability—while redefining tasks and evaluation with domain experts.
Frame biologically meaningful questions, identify measurement boundaries and carry important predictions into validation.
Connect data, algorithms and users through reproducible pipelines, robust software and maintainable infrastructure.
Clarify real-world value, sample and ethical boundaries, and the evidence needed to move toward disease insight and application.
Agree on the scientific question, use context and success criteria before choosing data, models and experiments.
Plan independent validation, negative controls, external generalization and failure criteria from the start.
Create papers, methods, data standards, benchmarks, software or public resources with clear maintenance and attribution.
Respect data rights, ethics and contribution; disclose limitations rather than presenting exploration as certainty.
High-quality collaboration needs clear rules for research integrity, data responsibility, attribution and release.
AI4SC intends to establish transparent processes for proposals, data use, contributions, software stewardship, publication and conflicts of interest. These policies and participation channels will be published after review; this preview does not invent partner lists or commitments.