Sign in

Federico D’Agostino

@fededagos.bsky.social
395 followers 388 following 21 posts

PhD student @ Uni Tübingen | @bethgelab.bsky.social | Computational Neuroscience & ML

PostsRepliesMedia
Federico D’Agostino @fededagos.bsky.social · 30/11/2025
📈 The Result: SceneWalk-X (also re-implemented in #JAX ⚡) These 3 mechanisms double SceneWalk’s explained variance on the MIT1003 dataset (from 35 % → 70 %)! We closed over 56 % of the gap to deep networks, setting a new State-of-the-Art for mechanistic scanpath prediction.
100
Federico D’Agostino @fededagos.bsky.social · 30/11/2025
↔️ 3. Cardinal + Leftward Bias People tend to move their eyes more horizontally, and display a subtle initial bias for leftward movements. Adding this adaptive attentional prior further stabilized the model.
100
Federico D’Agostino @fededagos.bsky.social · 30/11/2025
➡️ 2. Saccadic Momentum The eyes often tend to continue moving in the same direction, especially after long saccades. We captured this bias by adding a dynamic directional map that adapts based on the previous eye movement.
100
Federico D’Agostino @fededagos.bsky.social · 30/11/2025
🔥 1. Time-Dependent Temperature Scaling Early fixations are more focused (exploitative), later ones become more exploratory. We modeled this with a decaying “temperature” that controls the determinism of fixation choices over time.
110
Federico D’Agostino @fededagos.bsky.social · 30/11/2025
💡 Our idea: Use the deep model not just to chase performance, but as a tool for scientific discovery. We isolate "controversial fixations" where DeepGaze's likelihood vastly exceeds SceneWalk's. These reveal where the mechanistic model fails to capture predictable patterns.
121
Federico D’Agostino @fededagos.bsky.social · 30/11/2025
🚨 New paper at #NeurIPS2025! A systematic fixation-level comparison of a performance-optimized DNN scanpath model and a mechanistic cognitive model reveals behaviourally relevant mechanisms that can be added to the mechanistic model to substantially improve performance. 🧵👇
2115
Federico D’Agostino @fededagos.bsky.social · 14/03/2025
The currently supported models follow a Core + Readout architecture: 🔸 Core: Extracts shared retinal features across data recording sessions 🔸 Readout: Maps shared features to individual neuron responses 🔹 Includes pre-trained models & easy dataset loading (6/9)
120
Federico D’Agostino @fededagos.bsky.social · 14/03/2025
Understanding the retina is crucial for decoding how visual information is processed. However, decades of data and models remain scattered across labs and approaches. We introduce openretina to unify retinal system identification. (2/9)
141
Federico D’Agostino @fededagos.bsky.social · 14/03/2025
🚨 New paper alert! 🚨 We’ve just launched openretina, an open-source framework for collaborative retina modeling across datasets and species. A 🧵👇 (1/9)
13820