arXiv Computer Vision October 2, 2026 By Yuan Huang, Zihan Chen, Runbin Zhang, Hongwei Ding, Changzeng Fu, Shiqi Zhao

Two Routes to the Middle: Placement Search and Brain Readouts Converge on Where Continual Learners Should Specialize

Read the original on arXiv Computer Vision →

The paper studies where to place task‑specific adapters in a vision transformer to balance storage growth and accuracy. Training all contiguous four‑block placements shows an inverted‑U accuracy curve, peaking at intermediate depths, while simple weight or activation metrics favor the deepest blocks. A neuroscience‑inspired method, LS‑B, uses frozen fMRI readouts of human visual areas to select blocks whose responses vary most across tasks, yielding backbone‑specific allocations that match or exceed the best placements found by search and use only 60% of the adapter storage while staying within 1.5 percentage points of full accuracy.

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 Computer Vision.

arXiv Machine Learning

Sep 11

Breaking the Central Bias: Spatially Partitioned Experts for Coordinate-Based Neuroevolution

The paper investigates a spatial-concentration bias in Evolvable-Substrate HyperNEAT (ES‑HyperNEAT) when applied to MNIST, where evolved networks focus on a central cluster of input pixels. By partitioning the input image into 13 non‑overlapping spatial segments and evolving a separate expert network for each, the authors achieve a 43% mean accuracy—an 106% relative improvement over the baseline—without relying on data‑driven weighting. The study also introduces a receptive‑field diagnostic to detect silent input‑coverage collapse and a spatial‑partitioning remedy to restore full image coverage.

By Romain Claret, Arthur Gygax, Michael O'Neill, Paul Cotofrei, Michael Palma Mendes, Pascal Felber

benchmarks safety

arXiv Machine Learning

Sep 22

Topographic Training Concentrates Causal Circuits Without Improving Neuron Monosemanticity

arXiv:2609.24379v1 Announce Type: cross Abstract: Mechanistic interpretability of vision transformers seeks to decompose model computation into human-readable units, but learned representations entan...

By Gautam Ranka, Shubham Santosh Pandere, Aiden Dsouza

llms efficiency safety

arXiv Computer Vision

5d ago

FlatClip: A Geometry-Aware Surface-Level Baseline for fMRI Representation Learning

arXiv:2609.31204v1 Announce Type: cross Abstract: Recent fMRI foundation models differ substantially in the spatial scale at which they represent brain activity. ROI- and connectivity-based models ar...

By Mo Wang, Wenhao Ye, Zihan Ning, Jiayu Zuo, Junfeng Xia, Hongkai Wen, Quanying Liu

benchmarks

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

Hugging Face Trending Papers

Sep 21

Topographic Training Concentrates Causal Circuits Without Improving Neuron Monosemanticity

Mechanistic interpretability of vision transformers seeks to decompose model computation into human-readable units, but learned representations entangle many concepts in each neuron. Feature superposi...

llms efficiency safety

arXiv AI

Jul 22

Soft-TransFormers for Continual Learning

arXiv:2411. 16073v4 Announce Type: replace-cross Abstract: Inspired by the Well-initialized Lottery Ticket Hypothesis (WLTH), we introduce Soft-TransFormers (Soft-TF), a continual learning framework that adapts a frozen pre-trained Transformer through task-specific soft subnetworks: real-valued multiplicative masks over the query, key, value, and output projections of selected self-attention layers.

By Haeyong Kang, Chang D. Yoo

llms fine-tuning benchmarks

One email a morning, machine-written

Related stories

Breaking the Central Bias: Spatially Partitioned Experts for Coordinate-Based Neuroevolution

Topographic Training Concentrates Causal Circuits Without Improving Neuron Monosemanticity

FlatClip: A Geometry-Aware Surface-Level Baseline for fMRI Representation Learning

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

Topographic Training Concentrates Causal Circuits Without Improving Neuron Monosemanticity

Soft-TransFormers for Continual Learning