arXiv Machine Learning
Breakdown of Local Denoising as Semantic Speciation
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jun 2
The Entropic Signature of Class Speciation in Diffusion Models
arXiv:2602. 09651v2 Announce Type: replace-cross Abstract: Diffusion models do not recover semantic structure uniformly over time.
arXiv Machine Learning
Jul 10
An exact information theory of generalization phase transitions in Bayesian diffusion models
arXiv:2607. 08041v1 Announce Type: new Abstract: How diffusion models circumvent the curse of dimensionality to learn complex distributions over high dimensional spaces from a finite training set, instead of memorizing it, remains a fundamental mystery.
Hugging Face Trending Papers
Jul 9
An exact information theory of generalization phase transitions in Bayesian diffusion models
How diffusion models circumvent the curse of dimensionality to learn complex distributions over high dimensional spaces from a finite training set, instead of memorizing it, remains a fundamental mystery. To address this, we introduce analytically tractable Bayesian information restricted diffusion (BIRD) models, in which each pixel observes restricted information about noisy data.
Hugging Face Trending Papers
Jul 27
Context Is King: How In-Context Specification Shapes the Geometry of Concepts
Large language models place structured concepts on geometrically faithful manifolds: weekdays lie on a circle, months on another, usually taken to be a fixed world-model the network stores and looks up. We show that context is king: the structure a model actually uses is set by the in-context specification.
arXiv Machine Learning
Jul 28
Context Is King: How In-Context Specification Shapes the Geometry of Concepts
arXiv:2607. 24425v1 Announce Type: new Abstract: Large language models place structured concepts on geometrically faithful manifolds: weekdays lie on a circle, months on another, usually taken to be a fixed world-model the network stores and looks up.
arXiv AI
Jul 8
Few Channels Draw The Whole Picture: Revealing Massive Activations in Diffusion Transformers
arXiv:2605. 13974v2 Announce Type: replace-cross Abstract: Diffusion Transformers (DiTs) and related flow-based architectures are now among the strongest text-to-image generators, yet the internal mechanisms through which prompts shape image semantics remain poorly understood.