WRSWorld Research StateContribute
WORLD RESEARCH STATE

van den Oord and colleagues: conditional PixelCNN decoders

Contribution grade

Autoregressive image generation · Human-designed AI research method or resource

Reference score18,000Provisional editorial estimate of this exact contribution; its grade is assessed separately.

What changed

Developed a conditional PixelCNN decoder with gated convolutional layers for image generation and autoencoder decoding.

Scientific scope

Developed a conditional PixelCNN decoder with gated convolutional layers for image generation and autoencoder decoding. Scope limitation: This 2016 conditional PixelCNN paper is not the original PixelRNN or an invention of autoregressive density modeling.

Evidence

The retained primary-source abstract, bibliographic record and stated review scope support this provisional assessment. No independent experimental replication by WRS is claimed. This 2016 conditional PixelCNN paper is not the original PixelRNN or an invention of autoregressive density modeling.

Contributors

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction