The DevoWorm group has developed an open-source Graph neural network (GNN) framework for embryogenetic data called DevoGraph. Developmental GNNs (D-GNNs) allow us to characterize a growing network that undergoes shape transformations along with increases in size. This is ultimately important for understanding formation of the connectome and the origins of embodied behavior. For this year’s project, the successful applicant will work on extending our two outcomes from last year. The first direction involves working with Neural Developmental Programs to build growing neural networks. This provides a means to model the function of embryogenetic networks, developing connectomes, and other growth processes. The second direction involves working with hyper graph representations, enabling multiscale modeling from a network perspective. We aim to tie our D-GNN work into the group’s ongoing theoretical and computational work. As such, this project will require the ability to work with mathematical models and associated algorithms. Knowledge of graph and/or network theory is helpful, but not required.
Project #6, INCF Description on Neurostars
Open-source communities are only as powerful as their ability to collectively complete tasks and projects. One way to enable the functional capacity of such a community is to model the collective behavioral and cognitive aspects of day-to-day project engagement. Your current involvement will involve the maintenance, development, and further implementation of two models from past years: a Reinforcement Learning model, and a hybrid Agent-based/Large Language Model. The candidate will build an analytical model that incorporates features such as general feedback loops (recurrent relationships) and causal loops (reciprocal causality). This might be in the form of a traditional boxes and arrows (input-output) model, or something more exotic such as Reinforcement Learning.
Project #7 (Reinforcement Learning), INCF Description on Neurostars
Project #8 (Reinforcement Learning), INCF Description on Neurostars
We strongly encourage you to share your proposal drafts with the mentors well before the deadline so we can review them and provide feedback. Early drafts help us guide you in refining your approach and significantly improve the quality of the final submission.
Please make sure your proposal clearly outlines:
• The problem you plan to address.
• Your proposed technical approach.
• Expected deliverables and milestones in the Timeline section.
• How your work aligns with the research direction and project goals.
As mentioned earlier, reviewing the previous project reports and related links will help you understand the context, metrics, and expectations we have for this year’s proposals.
All submissions will be made using best practices.
Note on AI Usage
Use of AI is not prohibited, but please avoid relying on it blindly for both proposals and code contributions.
What we care about most is your own understanding, reasoning, and technical thinking. This is true of propposals whether you use AI in its creation or not.
Mentors review many proposals every year, and purely AI-generated content is usually very easy to identify.
Proposals filled with generic explanations or boilerplate text tend to stand out quickly. A few clear bullet points explaining your approach, research direction, and implementation plan will communicate your thinking much better than long AI-generated paragraphs.
-
Onboarding guide for 2026 (DevoWorm).
-
Prior GSoC projects have lead to: DevoLearn, Developmental Braitenberg Vehicles, Contextual Geometric Structures, Open-source Collective Behavior and Ethics, D-GNNs, Digital Microspheres.