arXiv Machine Learning August 17, 2026 By Nils Leutenegger

Cross-Species RSA Reveals Conserved Early Visual Alignment but Divergent Higher-Area Rankings Across Human fMRI and Macaque Electrophysiology

Read the original on arXiv Machine Learning →

arXiv:2605. 22401v2 Announce Type: replace Abstract: CORRECTION (August 2026): an evaluation-mode defect in the shared feature-extraction pipeline affected the predictive-coding and STDP conditions.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

safety

arXiv Machine Learning

Aug 17

Supervised Training Rapidly Degrades Early Visual Cortex Alignment Across Biologically Plausible Learning Rules

arXiv:2605. 30556v2 Announce Type: replace Abstract: CORRECTION (August 2026): the central finding of this paper is not supported.

By Nils Leutenegger

safety

arXiv Machine Learning

Aug 17

Untrained CNNs Match Backpropagation at V1: A Systematic RSA Comparison of Four Learning Rules Against Human fMRI

arXiv:2604. 16875v3 Announce Type: replace Abstract: CORRECTION (August 2026): an evaluation-mode defect affected the predictive-coding and STDP conditions of this study; those results should not be used pending re-computation.

By Nils Leutenegger

safety

arXiv Machine Learning

Aug 4

Predicted Cortex Is Not a Domain-General Prior: A Matched-Control Audit of Brain-Encoding Features for Video Memorability

arXiv:2607. 16292v4 Announce Type: replace-cross Abstract: Brain-encoding foundation models predict fMRI responses to video, audio and text well enough to win the Algonauts 2025 challenge.

By Carson Rodrigues

arXiv Machine Learning

Aug 14

Evaluation Resolution Confounds Learning-Rule Comparisons in Model-Brain RSA of Early Visual Cortex

arXiv:2608. 12408v1 Announce Type: cross Abstract: Representational similarity analysis (RSA) is increasingly used to ask which learning rules give convolutional networks brain-like representations.

By Nils Leutenegger

llms safety

arXiv AI

Jul 21

It Depends on the Dataset: When a Brain-Encoding Model's Predicted Responses Beat Their Visual Backbone for Video Memorability

arXiv:2607. 16292v1 Announce Type: cross Abstract: Brain-encoding foundation models predict fMRI responses to video, audio, and text well enough to win the Algonauts 2025 challenge.

By Carson Rodrigues

arXiv AI

4d ago

Which Attention Heads are like the Human Head? Not the Ones that Compute

The study investigates whether attention heads in large language models that align with human EEG signals are causally involved in model computation. By ablating these brain‑aligned heads during a pattern‑completion task, the authors find that while such heads contribute to performance, their removal is less disruptive than removing heads selected by attribution patching. The research also distinguishes two families of brain‑aligned heads—novelty and repetition heads—highlighting that novelty heads track human attention but are less critical than random ablation, whereas repetition heads modestly aid performance and align with abstract‑pattern representations.

By Christopher Pinier, Gustaw Opie{\l}ka, Hannes Rosenbusch, Taylor Webb, Michael D. Nunez, Claire E. Stevenson

llms benchmarks safety

One email a morning, machine-written

Related stories

Supervised Training Rapidly Degrades Early Visual Cortex Alignment Across Biologically Plausible Learning Rules

Untrained CNNs Match Backpropagation at V1: A Systematic RSA Comparison of Four Learning Rules Against Human fMRI

Predicted Cortex Is Not a Domain-General Prior: A Matched-Control Audit of Brain-Encoding Features for Video Memorability

Evaluation Resolution Confounds Learning-Rule Comparisons in Model-Brain RSA of Early Visual Cortex

It Depends on the Dataset: When a Brain-Encoding Model's Predicted Responses Beat Their Visual Backbone for Video Memorability

Which Attention Heads are like the Human Head? Not the Ones that Compute