arXiv Machine Learning July 13, 2026 By William W. Yang, Andrew M. Saxe, Peter E. Latham

How are linear representations learned? Exact solutions to the dynamics of abstraction

Read the original on arXiv Machine Learning →

arXiv:2607. 08843v1 Announce Type: new Abstract: In artificial and biological neural networks, concepts are often encoded as consistent linear directions in representation space.

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.

arXiv AI

3d ago

Temporal Geometry of Deep Networks: Hyperbolic Representations of Training Dynamics for Intrinsic Explainability

arXiv:2610.03000v1 Announce Type: cross Abstract: Intrinsic explainability remains a challenging problem, particularly in contexts where multilayer perceptrons (MLPs) require dynamic re-training with...

By Ambarish Moharil

rag

arXiv Machine Learning

Jun 4

When Both Layers Learn: Training Dynamics of Representing Linear Models via ReLU Networks

arXiv:2606. 04476v1 Announce Type: new Abstract: In this paper, we study the gradient descent dynamics for jointly training both layers of a one-hidden-layer ReLU network to fit a linear target function.

By Berk Tinaz, Changzhi Xie, Mahdi Soltanolkotabi

safety

arXiv Machine Learning

Jun 9

Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior

arXiv:2606. 08454v1 Announce Type: new Abstract: Activation steering provides a lightweight inference-time mechanism for controlling large language models (LLMs) by modifying their internal activation vectors toward desired behaviors.

By Tuc Nguyen, Thai Le

llms diffusion benchmarks safety

arXiv Machine Learning

Jun 30

Scalar Representations of Neural Network Training Dynamics

arXiv:2606. 30384v1 Announce Type: new Abstract: Training in artificial neural networks can be viewed as a trajectory evolving through a high-dimensional loss landscape.

By Pedro Jim\'enez-Gonz\'alez, Miguel C. Soriano, Lucas Lacasa

rag

arXiv Machine Learning

Jul 7

Gradient Descent as Implicit EM in Distance-Based Neural Models

arXiv:2512. 24780v2 Announce Type: replace Abstract: Neural networks trained with standard objectives exhibit behaviors characteristic of probabilistic inference: soft clustering, prototype specialization, and Bayesian uncertainty tracking.

By Alan Oursland

llms

arXiv Machine Learning

Jun 17

A Dynamical Systems Perspective on the Analysis of Neural Networks

arXiv:2507. 05164v2 Announce Type: replace-cross Abstract: In this chapter, we utilize dynamical systems to analyze several aspects of machine learning algorithms.

By Dennis Chemnitz, Maximilian Engel, Christian Kuehn, Sara-Viola Kuntz

rag safety

One email a morning, machine-written

Related stories

Temporal Geometry of Deep Networks: Hyperbolic Representations of Training Dynamics for Intrinsic Explainability

When Both Layers Learn: Training Dynamics of Representing Linear Models via ReLU Networks

Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior

Scalar Representations of Neural Network Training Dynamics

Gradient Descent as Implicit EM in Distance-Based Neural Models

A Dynamical Systems Perspective on the Analysis of Neural Networks