Xuanchi Ren(@xuanchi13):The latent-vs-pixel debate misses the point. GPT Image 2 shows what users notice: pixel-level fidelity. Latent models show what scales: compact semantic structure. We connect them by replacing VAE/RAE decoders with a Pixel Diffusion Decoder. Code and Model available: https://t.co/JjtecJzF0W 🧵(1/N)

Xuanchi Ren

@xuanchi13

Ex-Senior Research Scientist @NVIDIAAI. PhD @UofTCompSci. Working on GenAI and world models

参加 March 2021

590 フォロー中 1.5K ファン

Xuanchi Ren@xuanchi13

2026.05.26 15:41

The latent-vs-pixel debate misses the point. GPT Image 2 shows what users notice: pixel-level fidelity. Latent models show what scales: compact semantic structure. We connect them by replacing VAE/RAE decoders with a Pixel Diffusion Decoder. Code and Model available: 🧵(1/N)