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.

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

2d ago

Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks

arXiv:2609.38998v1 Announce Type: new Abstract: A foundational principle of connectionism is that perception, action, and cognition emerge from parallel computations among simple, interconnected unit...

By Lukas Braun, Erin Grant, Andrew M. Saxe

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

4d ago

Traversing the solution space of neural networks with Hessian Null Space Continuation

arXiv:2609.38081v1 Announce Type: new Abstract: On a single task, deep networks can learn many solutions, depending on their optimizer, training data, architecture, and hyperparameters. Many of these...

By Ann Huang, Mitchell Ostrow, Zhouyang Lu, William T. Redman, Leo Kozachkov, Kanaka Rajan

llms agents fine-tuning 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

One email a morning, machine-written

Related stories

Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks

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

Traversing the solution space of neural networks with Hessian Null Space Continuation

Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability