IDSIA
@idsia • Istituto Dalle Molle di Studi sull'Intelligenza Artificiale . Use this route to separate flagship concentration from portfolio breadth before you treat a publisher as broadly strong.
Portfolio concentration
64%
Top three share
Shows whether the organization is driven by one breakout repo or several visible projects.
Breadth
30 repos
Visible snapshot
3 repositories updated in the last 90 days.
Leading language
Python
Portfolio mix
Python (17), Java (5), Jupyter Notebook (5)
Average size
21
Stars per repository
Useful for distinguishing one flagship-heavy publisher from a repeatable portfolio.
Updated: 2026-06-02(85d ago)GitHub API fallback30 repositories
64%
of the visible star count comes from this organization's top three repositories.
21
stars per repository in this same snapshot.
Python
is the most common language here, with 3 repositories updated in the last 90 days.
Why this rank
This organization stands out because its public portfolio is relatively balanced across 30 repositories.
Balanced portfolio across 30 reposTop 3 share 64%
Organization pages work best when you separate portfolio breadth from flagship concentration. In IDSIA's case, the visible top three repositories account for about 64% of total stars in this snapshot, which helps explain whether the organization is known for one breakout project or for a broader repeatable portfolio.
The dominant language mix here is Python (17), Java (5), Jupyter Notebook (5). That makes this page useful not just for popularity checks, but also for seeing what technical shape an organization's public ecosystem actually has.
Top Repositories
| # | Repository | Language | Stars |
|---|---|---|---|
| 1 | idsia/modern-srwm Official repository for the paper "A Modern Self-Referential Weight Matrix That Learns to Modify Itself" (ICML 2022 & NeurIPS 2021 Deep RL Workshop) and "Accelerating Neural Self-Improvement via Bootstrapping" (ICLR 2023 Workshop) | Python | 178 |
| 2 | idsia/hhmarl_2D Heterogeneous Hierarchical Multi Agent Reinforcement Learning for Air Combat | Python | 166 |
| 3 | idsia/recurrent-fwp Official repository for the paper "Going Beyond Linear Transformers with Recurrent Fast Weight Programmers" (NeurIPS 2021) | Python | 52 |
| 4 | idsia/neuraldiffeq-fwp Official repository for the paper "Neural Differential Equations for Learning to Program Neural Nets Through Continuous Learning Rules" (NeurIPS 2022) | Python | 24 |
| 5 | idsia/lmtool-fwp PyTorch Language Modeling Toolkit for Fast Weight Programmers | Python | 22 |
| 6 | idsia/credici Credici: Credal Inference for Causal Inference | Java | 22 |
| 7 | idsia/automated-cl Official repository for the paper "Automating Continual Learning" | Python | 20 |
| 8 | idsia/gpforecasting | Python | 18 |
| 9 | idsia/novel2graph | Python | 14 |
| 10 | idsia/rtrl-elstm Official repository for the paper "Exploring the Promise and Limits of Real-Time Recurrent Learning" (ICLR 2024) | Python | 13 |
| 11 | idsia/kohonen-vae Official repository for the paper "Topological Neural Discrete Representation Learning à la Kohonen" (ICML 2023 Workshop on Sampling and Optimization in Discrete Space) | Python | 13 |
| 12 | idsia/fpainter Official repository for the paper "Images as Weight Matrices: Sequential Image Generation Through Synaptic Learning Rules" (ICLR 2023) | Python | 12 |
| 13 | idsia/crema Crema: Credal Models Algorithms | Java | 12 |
| 14 | idsia/GoGePo Official repository for the paper "Goal-Conditioned Generators of Deep Policies" | Python | 11 |
| 15 | idsia/bayesRecon Source of bayesRecon R package 📈 | R | 9 |
| 16 | idsia/MLprod Machine Learning in Production | Jupyter Notebook | 6 |
| 17 | idsia/policyevaluator Official repository for the paper "General Policy Evaluation and Improvement by Learning to Identify Few But Crucial States" | Python | 6 |
| 18 | idsia/fwp-formal-lang Official repository for the paper "Practical Computational Power of Linear Transformers and Their Recurrent and Self-Referential Extensions" (EMNLP 2023) | Cuda | 5 |
| 19 | idsia/NewTechnoWar New Techno War, an IDSIA project in collaboration with Armasuisse. | Jupyter Notebook | 4 |
| 20 | idsia/adapquest ADAPtive QUESTtionnaire, an IDSIA tool for adaptive tests, surveys, and questionnaires. | Java | 3 |
| 21 | idsia/causal-ai-clinician Causal Inference for Critical Decision Making | Python | 2 |
| 22 | idsia/CLIER Repository for the article "Protocol for interpretable and context-specific single-cell informed deconvolution of bulk RNA-seq data" (STAR Protocols, 2025) | R | 2 |
| 23 | idsia/flotta A federated learning framework for researchers. | Python | 2 |
| 24 | idsia/crepo | Java | 2 |
| 25 | idsia/FL-Bioinformatics Repository for the review article "Technical Insights and Legal Considerations for Advancing Federated Learning in Bioinformatics", currently under evaluation for publication in OUP Bioinformatics. | Jupyter Notebook | 1 |
| 26 | idsia/rexasi-pro | Jupyter Notebook | 1 |
| 27 | idsia/FPLIER FPLIER: Federated Pathway-Level Information ExtractoR | Python | 0 |
| 28 | idsia/SPEARHEAD Source code produced within the Innosuisse Flagship SPEARHEAD | Python | 0 |
| 29 | idsia/crema-adaptive Experiments on adaptive surveys using credal and bayesian networks with our CREMA library. | Java | 0 |
| 30 | idsia/cjuice | Jupyter Notebook | 0 |
Next step after the organization read
Open a flagship repository, compare a couple of portfolio leaders, or return to the organization map when you want a broader concentration read.
Learn and methodology
Keep trust-building context reachable, but behind the first data read instead of ahead of it.
How to read this organization snapshot
Total stars are useful as a discovery signal, but they do not tell you whether a team maintains every repository equally. Pair this page with release cadence, maintainer activity, and the flagship concentration shown above before making adoption decisions.
For broader background on GitStar's ranking logic and editorial guidance, see Methodology & Editorial Standards.