arXiv (All)
open access
Equivalent Flows, Unequal Learning: Clean-Latent Prediction in Transformers
Flow samplers consume velocity, but the neural network can predict the clean endpoint and convert it to velocity through a fixed affine readout. We study this choice with JLT, a latent Transformer in a frozen variational autoencoder (VAE) representation. For squared error, the optimal clean and velo
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Disentangling Representation Evolution in Transformers through Directional Decomposition#1110000
- STAR-VAE: A Scalable Latent-Variable Transformer for Controllable Molecular Generation#1061644
- The Architecture Behind Generative AI: A Look into Neural Networks#103377
- Identifying interactions across brain areas while accounting for individual-neuron dynamics with a Transformer-based variational autoencoder.#923439
- Kolmogorov-Arnold Energy Models: Fast, Interpretable Generative Modeling#1013425
Record · ID 1129274
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive