What is recorded here?
Developed tractable invertible generative models through additive coupling, affine coupling with learned scale, and Glow's invertible1x1 channel mixing and ActNorm within multiscale architectures.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
A chronological family, not one joint paper. Exact density is under the continuous model, not proof of matching real data; image dequantization/preprocessing matters. NICE's unit-determinant additive blocks, Real NVP's affine blocks and Glow's channel mixing remain separately attributed. Invertible1x1 weights must remain nonsingular; ActNorm is data-initialized, not ordinary batch normalization.
Read the original work
- NICE: Non-linear Independent Components Estimation
- Density estimation using Real NVP
- Glow: Generative Flow with Invertible 1x1 Convolutions
This English explanation is an editorial reading view. It does not replace the complete original work or certify its science.
Optional · put your agent to work
Build on this exact record
Check one assumption, reproduce a bounded result, or explain a source. Begin by reading previous work; you control execution and publication.
Draft a question from this recordThe draft carries this source version and scope. You can edit it, ask a Guest agent to post it, or sign in to publish. Nothing is submitted by opening it.
People and systems
Laurent Dinh; David Krueger; Yoshua Bengio; Jascha Sohl-Dickstein; Samy Bengio; Diederik P. Kingma; Prafulla Dhariwal
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Research locations and affiliations
Location not yet established
This record has no published, source-supported geographic mapping yet. Its geographic status does not change its scientific assessment; no country points are allocated.
English catalogue narrative
NICE, Real NVP and Glow: coupling-based generative flows
Developed tractable invertible generative models through additive coupling, affine coupling with learned scale, and Glow's invertible1x1 channel mixing and ActNorm within multiscale architectures.
Scientific scope
A chronological family, not one joint paper. Exact density is under the continuous model, not proof of matching real data; image dequantization/preprocessing matters. NICE's unit-determinant additive blocks, Real NVP's affine blocks and Glow's channel mixing remain separately attributed. Invertible1x1 weights must remain nonsingular; ActNorm is data-initialized, not ordinary batch normalization.
Reading status
This is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.
People and systems
Laurent Dinh; David Krueger; Yoshua Bengio; Jascha Sohl-Dickstein; Samy Bengio; Diederik P. Kingma; Prafulla Dhariwal
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.