Marius Schneider
banner
mariusschneider.bsky.social
Marius Schneider
@mariusschneider.bsky.social
Computational neuroscience Postdoc @bionicvisionlab.org @ucsantabarbara.bsky.social | former IMPRS PhD Student @Ernst Strüngmann Institute

https://schneidermarius.github.io/
Submit your model. Compete against mice.
Which model architectures solve the task, and which find brain-like solutions?
Let us uncover what it takes to build robust, biologically inspired agents!
Read the whitepaper: arxiv.org/abs/2509.14446
Explore the challenge: robustforaging.github.io
September 22, 2025 at 11:13 PM
🧠 Track 2: Neural Alignment

Do task-trained agents develop brain-like internal representations?

We regress model activations onto 19k+ neurons across all mouse visual areas recorded during the same task.

This lets us test whether brain-like codes emerge naturally from behavior-driven learning.
September 22, 2025 at 11:13 PM
🧭Track 1: Visual Robustness

Track 1 evaluates how well RL agents generalize to unseen visual perturbations, like different weather or lighting changes, while performing a foraging task.

Mice perform the same task in VR—enabling direct behavioral comparisons across species.
September 22, 2025 at 11:13 PM
We built a naturalistic Unity world (not blocky or toy-like) and trained mice to perform a foraging task in it.

Now it’s your turn: train RL agents on the same task and submit your model!
September 22, 2025 at 11:13 PM
Excited for the poster session at #Cosyne tonight!
Come check out the two posters I am involved in—one on neural representations and generalization in mice & RL agents trained on the same foraging task, and another on selective attention in spiking networks.
March 27, 2025 at 9:17 PM