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.
04.12.2025 17:54
👍 1
🔁 0
💬 0
📌 0
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](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:v5vnvp3l4uy6mdqhuihgnqml/bafkreihdf2ovoznwph5culcrpumajpcg2k24phh4rrotkeybhi6puizgki)
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