arXiv Machine Learning July 10, 2026 By Dan Yamins, Aran Nayebi

Contravariance Theory: Strong Alignment for Minimal Solutions to Hard Tasks

Read the original on arXiv Machine Learning →

arXiv:2607. 08561v1 Announce Type: new Abstract: A series of results from the NeuroAI over the past fifteen years have raised core questions both about how to compare Deep Neural Network (DNN) models to the brain, and about how much convergent evolution to expect between artificial networks and real brain networks.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

safety

arXiv Machine Learning

Jul 7

A Complete Symmetry Classification of Shallow ReLU Networks

arXiv:2604. 14037v2 Announce Type: replace Abstract: Parameter space is not function space for neural network architectures.

By Pranavkrishnan Ramakrishnan

arXiv AI

Jun 4

A Unified Geometric Space for Topological Alignment Between Transformer-Based Models and Human Brain Networks

arXiv:2510. 24342v2 Announce Type: replace Abstract: Prior brain-AI alignment studies are typically constrained by specific inputs and tasks, limiting their ability to capture organizational properties across models with different modalities.

By Silin Chen, Yuzhong Chen, Caiwei Wang, Zifan Wang, Junhao Wang, Zifeng Jia, Keith M Kendrick, Tuo Zhang, Lin Zhao, Dezhong Yao, Tianming Liu, Xi Jiang

llms fine-tuning multimodal safety

arXiv Machine Learning

Jun 24

Similarity of Neural Network Representations in Superposition

arXiv:2604. 00208v2 Announce Type: replace Abstract: Comparing internal representations is a central goal in neuroscience and machine learning, but standard linear alignment metrics (Representational Similarity Analysis, Centered Kernel Alignment, and linear regression) are frequently applied to neural activity coordinates rather than on the underlying features.

By Sunny Liu, Habon Issa, Andr\'e Longon, Liv Gorton, Meenakshi Khosla, Alex Williams, David Klindt

llms safety

arXiv Machine Learning

Jun 4

Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability

arXiv:2606. 04754v1 Announce Type: new Abstract: Many striking phenomena in deep learning, such as linear mode connectivity and the structured behavior of training dynamics, are closely tied to parameter symmetries: transformations that leave the realized function unchanged.

By Vincent B\"urgin, Daniel Herbst, Ya-Wei Eileen Lin, Stefanie Jegelka

safety

arXiv Machine Learning

Jun 18

InTrain: Intrinsic Trainability for Zero-Cost Neural Architecture Search

arXiv:2606. 18676v1 Announce Type: new Abstract: Training-free neural architecture search promises efficient discovery of high-performance networks without costly training.

By Qinqin Zhou, Fuhai Chen, Jipeng Wu, Zhiwei Chen, Zhikai Hu, Weiwei Cai

benchmarks

arXiv Machine Learning

Jul 30

Automorphism-Induced Non-Canonicity in Top-k Explanations of Graph Neural Networks

arXiv:2607. 26344v1 Announce Type: new Abstract: A gradient-based GNN explainer given a molecule with two chemically equivalent nitro groups assigns them attribution scores that are equal to the last bit.

By Xin Xu, Siru Tao, Kaizhen Tan

efficiency

Related stories

A Complete Symmetry Classification of Shallow ReLU Networks

A Unified Geometric Space for Topological Alignment Between Transformer-Based Models and Human Brain Networks

Similarity of Neural Network Representations in Superposition

Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability

InTrain: Intrinsic Trainability for Zero-Cost Neural Architecture Search

Automorphism-Induced Non-Canonicity in Top-k Explanations of Graph Neural Networks