arXiv Machine Learning August 7, 2026 By Kanishka Reddy

Diffusion Operator Geometry of Feedforward Representations

Read the original on arXiv Machine Learning →

arXiv:2605. 01107v2 Announce Type: replace Abstract: Feedforward neural networks transform data through learned representations whose geometry shapes how classes separate and relate across successive layers.

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.

diffusion

arXiv Machine Learning

Sep 10

Revisiting Spectral Representations in Generative Diffusion Models

arXiv:2609.08253v1 Announce Type: new Abstract: Diffusion models have shown remarkable performance on diverse generation tasks. Recent work finds that imposing representation alignment on the hidden...

By Yuehao Wang, Peihao Wang, Hanwen Jiang, Ziyi Yang, Qixing Huang, Zhangyang Wang

rag diffusion efficiency safety

arXiv Machine Learning

Jun 15

Recursively Trained Diffusion Models: Limiting Collapse Distribution and Spectral Characterization

arXiv:2606. 13796v1 Announce Type: cross Abstract: Recursive training of generative models on their own outputs can lead to model collapse, a compounding drift away from the true data distribution.

By Na\"il B. Khelifa, Richard E. Turner, Ramji Venkataramanan

diffusion

arXiv Machine Learning

2d ago

Dynamics to decision: A mathematical theory of Lyapunov spectra and decision boundaries in deep classifiers

arXiv:2609.39190v1 Announce Type: new Abstract: A deep classifier is defined not only by the decision it produces, but also by the sequence of transformations through which that decision is formed. T...

By Shirin Panahi, Amirhossein Nazerian, Ali Pezeshki

fine-tuning

arXiv AI

Jun 10

Temporal Sheaf Neural Networks with Dynamic Orthogonal Transport

arXiv:2606. 10071v1 Announce Type: cross Abstract: We introduce Temporal Sheaf Neural Networks (TSNN), a temporal link prediction framework that equips each node with a time-varying orthogonal frame and compares node states only after explicit transport between local coordinate systems.

By Md Sadek Hossain Asif, Tanzila Khan, Md. Mosaddek Khan

rag diffusion benchmarks

Hugging Face Trending Papers

3d ago

Dynamics to decision: A mathematical theory of Lyapunov spectra and decision boundaries in deep classifiers

A deep classifier is defined not only by the decision it produces, but also by the sequence of transformations through which that decision is formed. Treating this evolution as a dynamical system acro...

fine-tuning

arXiv Machine Learning

Jun 8

Generalization of Diffusion Models Arises with a Balanced Representation Space

arXiv:2512. 20963v3 Announce Type: replace Abstract: Diffusion models excel at generating high-quality, diverse samples, yet they risk memorizing training data when overfit to the training objective.

By Zekai Zhang, Xiao Li, Xiang Li, Lianghe Shi, Meng Wu, Molei Tao, Qing Qu

diffusion

One email a morning, machine-written

Related stories

Revisiting Spectral Representations in Generative Diffusion Models

Recursively Trained Diffusion Models: Limiting Collapse Distribution and Spectral Characterization

Dynamics to decision: A mathematical theory of Lyapunov spectra and decision boundaries in deep classifiers

Temporal Sheaf Neural Networks with Dynamic Orthogonal Transport

Dynamics to decision: A mathematical theory of Lyapunov spectra and decision boundaries in deep classifiers

Generalization of Diffusion Models Arises with a Balanced Representation Space