AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

The balance between feature learning and collapse in generative dynamical systems

Julian Brandon, Bruno Loureiro, N Alex Cayco Gajic, Arthur Pellegrino

NeurIPS 2026 · Probabilistic and scientific modeling › Dynamical systems · approach: Switching and law-discovery dynamics

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Theoretical study of how implicit biases in learning dynamics of generative models based on dynamical systems (normalising flows, diffusion) balance feature learning against collapse.

Problem

Representation learning dynamics in generative models built on dynamical systems, such as normalising flows and diffusion models, are poorly understood compared with deep learning theory for discriminative networks.

Approach

Analyses implicit biases of learning dynamics in generative dynamical-system models to characterise when feature learning occurs versus when representations collapse; the abstract is truncated so the specific method is not stated.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy