I'm glad you like it! Indeed I thought a lot about the talk you gave some time ago in Tübingen while working on this project.

I'm very excited to present our paper together with @fededagos.bsky.social here at #NeurIPS2025 today at 4:30pm, poster no 2103. Come by if you want to see how DNNs can help build better mechanistic models of human behaviour!

Check out our new paper at #NeurIPS2025!

We found that less than 20 interpretable parameters are responsible for most of the performance drop on unseen datasets and that they can be adapted in a very data efficient way

[ICCV 2025] Modeling Saliency Dataset Bias YouTube video by Bethgelab

On my way to @iccv.bsky.social and looking forward to meeting many interesting people! I will present our work on Modeling Saliency Dataset Bias for better predictions on new datasets: youtu.be/gOkVY4cNVLo