Hybrid JEMs at intermediate generative-discriminative balance maximize human alignment on perceptual similarity, gloss, uncertainty, robustness, cue conflict, and feature attribution benchmarks.
Martin Schrimpf, Jonas Kubilius, Ha Hong, Najib J
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
The authors propose target-space recovery profiles to diagnose which reproducible dimensions of fMRI brain responses are captured by model predictions, showing that accuracy alone can mask alignment mismatches in visual cortex.
Direction maps and pinwheel structures in MT emerge spontaneously when a spatiotemporal deep network is trained on videos with contrastive self-supervised learning and spatial regularization.
A zero-shot visual world model trained on one child's experience achieves broad competence on physical understanding benchmarks while matching developmental behavioral patterns.
Proposes functional whole-brain models defined by four criteria that integrate empirical connectomes, dynamical realism, and task-performing competence across cognitive domains.
Zebrafish tectal subcircuits are dissociated into spike-efficient information gating and feedback-like robustness stabilization, then transferred to improve ResNet efficiency and noise tolerance.
RSA on 7T fMRI during natural scene viewing identifies ventromedial and lateral occipitotemporal representational routes for scene context versus animate content, with differential alignment to vision and language models.
citing papers explorer
-
Not Too Generative, Not Too Discriminative: The Human Alignment Sweet Spot
Hybrid JEMs at intermediate generative-discriminative balance maximize human alignment on perceptual similarity, gloss, uncertainty, robustness, cue conflict, and feature attribution benchmarks.
-
Beyond Prediction Accuracy: Target-Space Recovery Profiles for Evaluating Model-Brain Alignment
The authors propose target-space recovery profiles to diagnose which reproducible dimensions of fMRI brain responses are captured by model predictions, showing that accuracy alone can mask alignment mismatches in visual cortex.
-
Self-organized MT Direction Maps Emerge from Spatiotemporal Contrastive Optimization
Direction maps and pinwheel structures in MT emerge spontaneously when a spatiotemporal deep network is trained on videos with contrastive self-supervised learning and spatial regularization.
-
Zero-shot World Models Are Developmentally Efficient Learners
A zero-shot visual world model trained on one child's experience achieves broad competence on physical understanding benchmarks while matching developmental behavioral patterns.
-
Functional Whole-Brain Models: A New Framework for Unifying Brain Structure and Cognitive Function
Proposes functional whole-brain models defined by four criteria that integrate empirical connectomes, dynamical realism, and task-performing competence across cognitive domains.
-
Dual-axis attribution of zebrafish tectal microcircuits for energy-efficient and robust neurocomputing
Zebrafish tectal subcircuits are dissociated into spike-efficient information gating and feedback-like robustness stabilization, then transferred to improve ResNet efficiency and noise tolerance.
-
Shared representations in brains and models reveal a two-route cortical organization during scene perception
RSA on 7T fMRI during natural scene viewing identifies ventromedial and lateral occipitotemporal representational routes for scene context versus animate content, with differential alignment to vision and language models.