CogFormer: Learn All Your Models Once

Jerry M. Huang, Lukas Schumacher, Niek Stevenson, Stefan T. Radev
Proceedings of The 1st Symposium on Probabilistic Machine Learning, PMLR 327:444-521, 2026.

Abstract

Simulation-based inference (SBI) with neural networks has accelerated and transformed cognitive modeling workflows. SBI enables modelers to fit complex models that were previously difficult or impossible to estimate, while also allowing rapid estimation across large numbers of datasets. However, the utility of SBI for iterating over varying modeling assumptions remains limited: changes to parameterizations, generative functions, priors , and design variables all necessitate model retraining, thereby diminishing the benefits of amortization. To address these issues, we pilot the CogFormer, a meta-amortized framework for cognitive modeling. Our framework trains a transformer-based architecture that remains valid across a combinatorial number of structurally similar models, allowing for changing data types, parameters, design matrices, and sample sizes. We present promising quantitative results across families of decision-making models for binary, multi-alternative, and continuous responses. Our evaluation suggests that CogFormer can accurately estimate parameters across model families with minimal amortization offset, making it a potentially powerful engine that catalyzes cognitive modeling workflows.

Cite this Paper

BibTeX
@InProceedings{pmlr-v327-huang26a, title = {CogFormer: Learn All Your Models Once}, author = {Huang, Jerry M. and Schumacher, Lukas and Stevenson, Niek and Radev, Stefan T.}, booktitle = {Proceedings of The 1st Symposium on Probabilistic Machine Learning}, pages = {444--521}, year = {2026}, editor = {Swaroop, Siddharth and Rügamer, David and Kristiadi, Agustinus}, volume = {327}, series = {Proceedings of Machine Learning Research}, month = {05 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v327/main/assets/huang26a/huang26a.pdf}, url = {https://proceedings.mlr.press/v327/huang26a.html}, abstract = { Simulation-based inference (SBI) with neural networks has accelerated and transformed cognitive modeling workflows. SBI enables modelers to fit complex models that were previously difficult or impossible to estimate, while also allowing rapid estimation across large numbers of datasets. However, the utility of SBI for iterating over varying modeling assumptions remains limited: changes to parameterizations, generative functions, priors , and design variables all necessitate model retraining, thereby diminishing the benefits of amortization. To address these issues, we pilot the CogFormer, a meta-amortized framework for cognitive modeling. Our framework trains a transformer-based architecture that remains valid across a combinatorial number of structurally similar models, allowing for changing data types, parameters, design matrices, and sample sizes. We present promising quantitative results across families of decision-making models for binary, multi-alternative, and continuous responses. Our evaluation suggests that CogFormer can accurately estimate parameters across model families with minimal amortization offset, making it a potentially powerful engine that catalyzes cognitive modeling workflows. } }
Endnote
%0 Conference Paper %T CogFormer: Learn All Your Models Once %A Jerry M. Huang %A Lukas Schumacher %A Niek Stevenson %A Stefan T. Radev %B Proceedings of The 1st Symposium on Probabilistic Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Siddharth Swaroop %E David Rügamer %E Agustinus Kristiadi %F pmlr-v327-huang26a %I PMLR %P 444--521 %U https://proceedings.mlr.press/v327/huang26a.html %V 327 %X Simulation-based inference (SBI) with neural networks has accelerated and transformed cognitive modeling workflows. SBI enables modelers to fit complex models that were previously difficult or impossible to estimate, while also allowing rapid estimation across large numbers of datasets. However, the utility of SBI for iterating over varying modeling assumptions remains limited: changes to parameterizations, generative functions, priors , and design variables all necessitate model retraining, thereby diminishing the benefits of amortization. To address these issues, we pilot the CogFormer, a meta-amortized framework for cognitive modeling. Our framework trains a transformer-based architecture that remains valid across a combinatorial number of structurally similar models, allowing for changing data types, parameters, design matrices, and sample sizes. We present promising quantitative results across families of decision-making models for binary, multi-alternative, and continuous responses. Our evaluation suggests that CogFormer can accurately estimate parameters across model families with minimal amortization offset, making it a potentially powerful engine that catalyzes cognitive modeling workflows.
APA
Huang, J.M., Schumacher, L., Stevenson, N. & Radev, S.T.. (2026). CogFormer: Learn All Your Models Once. Proceedings of The 1st Symposium on Probabilistic Machine Learning, in Proceedings of Machine Learning Research 327:444-521 Available from https://proceedings.mlr.press/v327/huang26a.html.

Related Material