Entity · model

Channel-wise Autoregressive (CAR)

modelactivechannel-wise-autoregressive-car--58376924·1 events·first seen May 26, 2026

Aliases: Channel-wise Autoregressive (CAR)

Co-occurring entities

Channel-wise Vector Quantization DPG Benchmark GenEval Vector Quantization next-channel prediction

More like this (12)

autoregressive transformer canonical correlation analysis CARV Training-Free Semantic Correction for Autoregressive Visual Models 8B autoregressive language model Feature Auto-Encoder conditional variational autoencoder Autoregressive Boltzmann Generators Latent Memory Palace: Reasoning for Control as Autoregressive Variational Inference CVaR (Conditional Value at Risk)multivariate time series representation learning Channel-wise Vector Quantization

Recent events (1)

6arXiv · cs.AI·May 26, 2026·source ↗

Channel-wise Vector Quantization (CVQ): A New Image Tokenization Paradigm with Next-Channel Prediction

Researchers introduce Channel-wise Vector Quantization (CVQ), which replaces conventional patch-wise discrete tokens with channel-wise tokens that represent an image as discrete levels of visual detail. Built on CVQ, the Channel-wise Autoregressive (CAR) model uses a 'next-channel prediction' objective, generating images by progressively refining from global structure to fine-grained attributes. CVQ achieves 100% codebook utilization with a 16K+ codebook and the CAR model scores 86.7 on DPG and 0.79 on GenEval for text-to-image generation. The approach offers a structural alternative to raster-order patch-based autoregressive image generation.

Frontier Model Releases Evaluation and Benchmarking Channel-wise Vector Quantization DPG Benchmark GenEval +4 more