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.
Catalyzing next- generation artificial intelligence through NeuroAI.Nature Communications, 14:1597
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Hybrid ANN-CANN network for visual object tracking that operationalizes bias-variance complementarity to outperform baselines on nine benchmarks.
Explicit memory modeled on the hippocampus is the cornerstone needed to advance LLMs to AGI because their implicit statistical learning cannot produce higher cognitive functions.
Neuromechanical digital twins embed neural controllers in simulated bodies to infer unmeasurable biophysical variables, generate testable hypotheses via perturbations, and bridge neuroscience with robotics and machine learning.
citing papers explorer
-
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.
-
A Theory-grounded Hybrid Neural Network Integrating Complementary Estimation Mechanisms for Stable Visual Object TrackingA
Hybrid ANN-CANN network for visual object tracking that operationalizes bias-variance complementarity to outperform baselines on nine benchmarks.
-
Position: Hippocampal Explicit Memory Is the Cornerstone for AGI
Explicit memory modeled on the hippocampus is the cornerstone needed to advance LLMs to AGI because their implicit statistical learning cannot produce higher cognitive functions.
-
The embodied brain: Bridging the brain, body, and behavior with neuromechanical digital twins
Neuromechanical digital twins embed neural controllers in simulated bodies to infer unmeasurable biophysical variables, generate testable hypotheses via perturbations, and bridge neuroscience with robotics and machine learning.